2022-03-30 14:02:06 -04:00
[ [ package ] ]
name = "ansiwrap"
version = "0.8.4"
description = "textwrap, but savvy to ANSI colors and styles"
category = "dev"
optional = false
python-versions = "*"
[ package . dependencies ]
textwrap3 = ">=0.9.2"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "anyio"
version = "3.6.1"
description = "High level compatibility layer for multiple asynchronous event loop implementations"
category = "dev"
optional = false
python-versions = ">=3.6.2"
[ package . dependencies ]
idna = ">=2.8"
sniffio = ">=1.1"
[ package . extras ]
doc = [ "packaging" , "sphinx-rtd-theme" , "sphinx-autodoc-typehints (>=1.2.0)" ]
test = [ "coverage[toml] (>=4.5)" , "hypothesis (>=4.0)" , "pytest (>=7.0)" , "pytest-mock (>=3.6.1)" , "trustme" , "contextlib2" , "uvloop (<0.15)" , "mock (>=4)" , "uvloop (>=0.15)" ]
trio = [ "trio (>=0.16)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "appnope"
2022-04-18 18:12:18 -04:00
version = "0.1.3"
2021-06-28 16:16:14 -04:00
description = "Disable App Nap on macOS >= 10.9"
category = "main"
optional = false
python-versions = "*"
2021-08-24 15:40:54 -05:00
[ [ package ] ]
2022-02-03 17:05:51 -05:00
name = "argon2-cffi"
version = "21.3.0"
description = "The secure Argon2 password hashing algorithm."
2021-08-24 15:40:54 -05:00
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-08-24 15:40:54 -05:00
[ package . dependencies ]
2022-02-03 17:05:51 -05:00
argon2-cffi-bindings = "*"
2021-08-24 15:40:54 -05:00
[ package . extras ]
2022-02-03 17:05:51 -05:00
dev = [ "pre-commit" , "cogapp" , "tomli" , "coverage[toml] (>=5.0.2)" , "hypothesis" , "pytest" , "sphinx" , "sphinx-notfound-page" , "furo" ]
docs = [ "sphinx" , "sphinx-notfound-page" , "furo" ]
tests = [ "coverage[toml] (>=5.0.2)" , "hypothesis" , "pytest" ]
2021-08-24 15:40:54 -05:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
2022-02-03 17:05:51 -05:00
name = "argon2-cffi-bindings"
version = "21.2.0"
description = "Low-level CFFI bindings for Argon2"
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2022-02-03 17:05:51 -05:00
cffi = ">=1.0.1"
2021-06-28 16:16:14 -04:00
[ package . extras ]
2022-02-03 17:05:51 -05:00
dev = [ "pytest" , "cogapp" , "pre-commit" , "wheel" ]
tests = [ "pytest" ]
2021-06-28 16:16:14 -04:00
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "astroid"
2022-08-11 16:34:56 -04:00
version = "2.11.7"
2021-08-02 12:16:38 -04:00
description = "An abstract syntax tree for Python with inference support."
2021-11-09 16:32:46 -05:00
category = "main"
2021-08-02 12:16:38 -04:00
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6.2"
2021-08-02 12:16:38 -04:00
[ package . dependencies ]
lazy-object-proxy = ">=1.4.0"
2021-09-22 12:31:03 -04:00
typing-extensions = { version = ">=3.10" , markers = "python_version < \"3.10\"" }
2022-03-31 13:56:10 -04:00
wrapt = ">=1.11,<2"
2021-08-02 12:16:38 -04:00
2021-08-05 15:35:54 -04:00
[ [ package ] ]
name = "atomicwrites"
2022-08-11 16:34:56 -04:00
version = "1.4.1"
2021-08-05 15:35:54 -04:00
description = "Atomic file writes."
category = "dev"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "attrs"
2022-08-11 16:34:56 -04:00
version = "22.1.0"
2021-06-28 16:16:14 -04:00
description = "Classes Without Boilerplate"
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.5"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
dev = [ "coverage[toml] (>=5.0.2)" , "hypothesis" , "pympler" , "pytest (>=4.3.0)" , "mypy (>=0.900,!=0.940)" , "pytest-mypy-plugins" , "zope.interface" , "furo" , "sphinx" , "sphinx-notfound-page" , "pre-commit" , "cloudpickle" ]
docs = [ "furo" , "sphinx" , "zope.interface" , "sphinx-notfound-page" ]
tests = [ "coverage[toml] (>=5.0.2)" , "hypothesis" , "pympler" , "pytest (>=4.3.0)" , "mypy (>=0.900,!=0.940)" , "pytest-mypy-plugins" , "zope.interface" , "cloudpickle" ]
tests_no_zope = [ "coverage[toml] (>=5.0.2)" , "hypothesis" , "pympler" , "pytest (>=4.3.0)" , "mypy (>=0.900,!=0.940)" , "pytest-mypy-plugins" , "cloudpickle" ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "babel"
version = "2.10.3"
description = "Internationalization utilities"
category = "dev"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
pytz = ">=2015.7"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "backcall"
version = "0.2.0"
description = "Specifications for callback functions passed in to an API"
category = "main"
optional = false
python-versions = "*"
2022-03-17 23:19:23 -04:00
[ [ package ] ]
name = "beautifulsoup4"
2022-04-18 18:12:18 -04:00
version = "4.11.1"
2022-03-17 23:19:23 -04:00
description = "Screen-scraping library"
category = "main"
optional = false
2022-04-18 18:12:18 -04:00
python-versions = ">=3.6.0"
2022-03-17 23:19:23 -04:00
[ package . dependencies ]
soupsieve = ">1.2"
[ package . extras ]
html5lib = [ "html5lib" ]
lxml = [ "lxml" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "black"
2022-02-03 17:05:51 -05:00
version = "21.12b0"
2021-06-28 16:16:14 -04:00
description = "The uncompromising code formatter."
category = "dev"
optional = false
python-versions = ">=3.6.2"
[ package . dependencies ]
click = ">=7.1.2"
mypy-extensions = ">=0.4.3"
2021-09-14 17:28:59 -04:00
pathspec = ">=0.9.0,<1"
platformdirs = ">=2"
2021-07-21 16:10:32 -04:00
tomli = ">=0.2.6,<2.0.0"
2021-09-14 17:28:59 -04:00
typing-extensions = [
{ version = ">=3.10.0.0" , markers = "python_version < \"3.10\"" } ,
{ version = "!=3.10.0.1" , markers = "python_version >= \"3.10\"" } ,
]
2021-06-28 16:16:14 -04:00
[ package . extras ]
colorama = [ "colorama (>=0.4.3)" ]
2022-02-03 17:05:51 -05:00
d = [ "aiohttp (>=3.7.4)" ]
2021-09-14 17:28:59 -04:00
jupyter = [ "ipython (>=7.8.0)" , "tokenize-rt (>=3.2.0)" ]
2022-02-03 17:05:51 -05:00
python2 = [ "typed-ast (>=1.4.3)" ]
2021-06-28 16:16:14 -04:00
uvloop = [ "uvloop (>=0.15.2)" ]
[ [ package ] ]
name = "bleach"
2022-08-11 16:34:56 -04:00
version = "5.0.1"
2021-06-28 16:16:14 -04:00
description = "An easy safelist-based HTML-sanitizing tool."
category = "main"
optional = false
2022-04-18 18:12:18 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
six = ">=1.9.0"
webencodings = "*"
2022-04-18 18:12:18 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
css = [ "tinycss2 (>=1.1.0,<1.2)" ]
dev = [ "build (==0.8.0)" , "flake8 (==4.0.1)" , "hashin (==0.17.0)" , "pip-tools (==6.6.2)" , "pytest (==7.1.2)" , "Sphinx (==4.3.2)" , "tox (==3.25.0)" , "twine (==4.0.1)" , "wheel (==0.37.1)" , "black (==22.3.0)" , "mypy (==0.961)" ]
2022-04-18 18:12:18 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "censusdata"
2022-03-31 13:56:10 -04:00
version = "1.15.post1"
2021-06-28 16:16:14 -04:00
description = "Download data from U.S. Census API"
category = "main"
optional = false
python-versions = ">=2.7"
[ package . dependencies ]
pandas = "*"
requests = "*"
[ [ package ] ]
name = "certifi"
2022-08-11 16:34:56 -04:00
version = "2022.6.15"
2021-06-28 16:16:14 -04:00
description = "Python package for providing Mozilla's CA Bundle."
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "cffi"
2022-08-11 16:34:56 -04:00
version = "1.15.1"
2021-06-28 16:16:14 -04:00
description = "Foreign Function Interface for Python calling C code."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
pycparser = "*"
[ [ package ] ]
2021-07-21 16:10:32 -04:00
name = "charset-normalizer"
2022-08-11 16:34:56 -04:00
version = "2.1.0"
2021-07-21 16:10:32 -04:00
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.6.0"
2021-07-21 16:10:32 -04:00
[ package . extras ]
unicode_backport = [ "unicodedata2" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "click"
2022-03-02 16:50:04 -05:00
version = "8.0.4"
2021-06-28 16:16:14 -04:00
description = "Composable command line interface toolkit"
category = "main"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
colorama = { version = "*" , markers = "platform_system == \"Windows\"" }
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "click-plugins"
version = "1.1.1"
description = "An extension module for click to enable registering CLI commands via setuptools entry-points."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
click = ">=4.0"
[ package . extras ]
dev = [ "pytest (>=3.6)" , "pytest-cov" , "wheel" , "coveralls" ]
[ [ package ] ]
name = "cligj"
version = "0.7.2"
description = "Click params for commmand line interfaces to GeoJSON"
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, <4"
[ package . dependencies ]
click = ">=4.0"
[ package . extras ]
test = [ "pytest-cov" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "colorama"
2022-08-11 16:34:56 -04:00
version = "0.4.5"
2021-06-28 16:16:14 -04:00
description = "Cross-platform colored terminal text."
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "configparser"
2022-02-03 17:05:51 -05:00
version = "5.2.0"
2021-08-02 12:16:38 -04:00
description = "Updated configparser from Python 3.8 for Python 2.6+."
category = "dev"
optional = false
python-versions = ">=3.6"
[ package . extras ]
2022-02-03 17:05:51 -05:00
docs = [ "sphinx" , "jaraco.packaging (>=8.2)" , "rst.linker (>=1.9)" , "jaraco.tidelift (>=1.4)" ]
testing = [ "pytest (>=6)" , "pytest-checkdocs (>=2.4)" , "pytest-flake8" , "pytest-cov" , "pytest-enabler (>=1.0.1)" , "types-backports" , "pytest-black (>=0.3.7)" , "pytest-mypy" ]
2021-08-02 12:16:38 -04:00
2021-08-24 15:40:54 -05:00
[ [ package ] ]
name = "cycler"
2022-02-03 17:05:51 -05:00
version = "0.11.0"
2021-08-24 15:40:54 -05:00
description = "Composable style cycles"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-08-24 15:40:54 -05:00
2021-07-12 15:50:44 -04:00
[ [ package ] ]
name = "debugpy"
2022-08-16 14:44:39 -04:00
version = "1.6.3"
2021-07-12 15:50:44 -04:00
description = "An implementation of the Debug Adapter Protocol for Python"
category = "main"
optional = false
2022-03-31 13:56:10 -04:00
python-versions = ">=3.7"
2021-07-12 15:50:44 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "decorator"
2022-02-03 17:05:51 -05:00
version = "5.1.1"
2021-06-28 16:16:14 -04:00
description = "Decorators for Humans"
category = "main"
optional = false
python-versions = ">=3.5"
[ [ package ] ]
name = "defusedxml"
version = "0.7.1"
description = "XML bomb protection for Python stdlib modules"
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
2022-03-31 13:56:10 -04:00
[ [ package ] ]
name = "dill"
2022-08-11 16:34:56 -04:00
version = "0.3.5.1"
2022-03-31 13:56:10 -04:00
description = "serialize all of python"
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
2022-03-31 13:56:10 -04:00
[ package . extras ]
graph = [ "objgraph (>=1.7.2)" ]
2021-07-29 14:00:20 -04:00
[ [ package ] ]
name = "distlib"
2022-08-11 16:34:56 -04:00
version = "0.3.5"
2021-07-29 14:00:20 -04:00
description = "Distribution utilities"
category = "dev"
optional = false
python-versions = "*"
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "dparse"
2022-08-11 16:34:56 -04:00
version = "0.5.2"
2021-08-02 12:16:38 -04:00
description = "A parser for Python dependency files"
category = "dev"
optional = false
python-versions = ">=3.5"
[ package . dependencies ]
packaging = "*"
toml = "*"
[ package . extras ]
pipenv = [ "pipenv" ]
2022-08-11 16:34:56 -04:00
conda = [ "pyyaml" ]
2021-08-02 12:16:38 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "dynaconf"
2022-08-11 16:34:56 -04:00
version = "3.1.9"
2021-06-28 16:16:14 -04:00
description = "The dynamic configurator for your Python Project"
category = "main"
optional = false
2021-09-14 17:28:59 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
all = [ "redis" , "ruamel.yaml" , "configobj" , "hvac" ]
2022-08-16 14:44:39 -04:00
configobj = [ "configobj" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
ini = [ "configobj" ]
redis = [ "redis" ]
test = [ "pytest" , "pytest-cov" , "pytest-xdist" , "pytest-mock" , "flake8" , "pep8-naming" , "flake8-debugger" , "flake8-print" , "flake8-todo" , "radon" , "flask (>=0.12)" , "django" , "python-dotenv" , "toml" , "codecov" , "redis" , "hvac" , "configobj" ]
toml = [ "toml" ]
vault = [ "hvac" ]
yaml = [ "ruamel.yaml" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "entrypoints"
2022-02-03 17:05:51 -05:00
version = "0.4"
2021-06-28 16:16:14 -04:00
description = "Discover and load entry points from installed packages."
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
2021-08-09 10:39:59 -04:00
[ [ package ] ]
name = "et-xmlfile"
version = "1.1.0"
description = "An implementation of lxml.xmlfile for the standard library"
category = "dev"
optional = false
python-versions = ">=3.6"
2022-04-18 18:12:18 -04:00
[ [ package ] ]
name = "fastjsonschema"
2022-08-11 16:34:56 -04:00
version = "2.16.1"
2022-04-18 18:12:18 -04:00
description = "Fastest Python implementation of JSON schema"
category = "main"
optional = false
python-versions = "*"
[ package . extras ]
devel = [ "colorama" , "jsonschema" , "json-spec" , "pylint" , "pytest" , "pytest-benchmark" , "pytest-cache" , "validictory" ]
2021-07-29 14:00:20 -04:00
[ [ package ] ]
name = "filelock"
2022-08-11 16:34:56 -04:00
version = "3.8.0"
2021-07-29 14:00:20 -04:00
description = "A platform independent file lock."
category = "dev"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7"
2021-11-01 18:05:05 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
docs = [ "furo (>=2022.6.21)" , "sphinx (>=5.1.1)" , "sphinx-autodoc-typehints (>=1.19.1)" ]
testing = [ "covdefaults (>=2.2)" , "coverage (>=6.4.2)" , "pytest (>=7.1.2)" , "pytest-cov (>=3)" , "pytest-timeout (>=2.1)" ]
2021-07-29 14:00:20 -04:00
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "fiona"
2022-03-02 16:50:04 -05:00
version = "1.8.21"
2021-07-21 16:10:32 -04:00
description = "Fiona reads and writes spatial data files"
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
attrs = ">=17"
certifi = "*"
click = ">=4.0"
click-plugins = ">=1.0"
cligj = ">=0.5"
munch = "*"
six = ">=1.7"
[ package . extras ]
2022-03-02 16:50:04 -05:00
all = [ "boto3 (>=1.2.4)" , "pytest-cov" , "shapely" , "pytest (>=3)" , "mock" ]
2021-07-21 16:10:32 -04:00
calc = [ "shapely" ]
s3 = [ "boto3 (>=1.2.4)" ]
test = [ "pytest (>=3)" , "pytest-cov" , "boto3 (>=1.2.4)" , "mock" ]
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "flake8"
version = "3.9.2"
description = "the modular source code checker: pep8 pyflakes and co"
category = "dev"
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
[ package . dependencies ]
mccabe = ">=0.6.0,<0.7.0"
pycodestyle = ">=2.7.0,<2.8.0"
pyflakes = ">=2.3.0,<2.4.0"
2022-02-03 17:05:51 -05:00
[ [ package ] ]
name = "fonttools"
2022-08-16 14:44:39 -04:00
version = "4.35.0"
2022-02-03 17:05:51 -05:00
description = "Tools to manipulate font files"
category = "main"
optional = false
python-versions = ">=3.7"
[ package . extras ]
2022-04-27 15:59:10 -04:00
all = [ "fs (>=2.2.0,<3)" , "lxml (>=4.0,<5)" , "zopfli (>=0.1.4)" , "lz4 (>=1.7.4.2)" , "matplotlib" , "sympy" , "skia-pathops (>=0.5.0)" , "uharfbuzz (>=0.23.0)" , "brotlicffi (>=0.8.0)" , "scipy" , "brotli (>=1.0.1)" , "munkres" , "unicodedata2 (>=14.0.0)" , "xattr" ]
2022-02-03 17:05:51 -05:00
graphite = [ "lz4 (>=1.7.4.2)" ]
interpolatable = [ "scipy" , "munkres" ]
lxml = [ "lxml (>=4.0,<5)" ]
pathops = [ "skia-pathops (>=0.5.0)" ]
plot = [ "matplotlib" ]
2022-04-27 15:59:10 -04:00
repacker = [ "uharfbuzz (>=0.23.0)" ]
2022-02-03 17:05:51 -05:00
symfont = [ "sympy" ]
type1 = [ "xattr" ]
ufo = [ "fs (>=2.2.0,<3)" ]
unicode = [ "unicodedata2 (>=14.0.0)" ]
woff = [ "zopfli (>=0.1.4)" , "brotlicffi (>=0.8.0)" , "brotli (>=1.0.1)" ]
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "geopandas"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
version = "0.11.1"
2021-07-21 16:10:32 -04:00
description = "Geographic pandas extensions"
category = "main"
optional = false
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
python-versions = ">=3.8"
2021-07-21 16:10:32 -04:00
[ package . dependencies ]
fiona = ">=1.8"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
packaging = "*"
pandas = ">=1.0.0"
pyproj = ">=2.6.1.post1"
shapely = ">=1.7,<2"
2021-07-21 16:10:32 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "idna"
2021-11-01 18:05:05 -04:00
version = "3.3"
2021-06-28 16:16:14 -04:00
description = "Internationalized Domain Names in Applications (IDNA)"
category = "main"
optional = false
2021-07-21 16:10:32 -04:00
python-versions = ">=3.5"
2021-06-28 16:16:14 -04:00
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "importlib-metadata"
version = "4.12.0"
description = "Read metadata from Python packages"
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
zipp = ">=0.5"
[ package . extras ]
docs = [ "sphinx" , "jaraco.packaging (>=9)" , "rst.linker (>=1.9)" ]
perf = [ "ipython" ]
testing = [ "pytest (>=6)" , "pytest-checkdocs (>=2.4)" , "pytest-flake8" , "pytest-cov" , "pytest-enabler (>=1.3)" , "packaging" , "pyfakefs" , "flufl.flake8" , "pytest-perf (>=0.9.2)" , "pytest-black (>=0.3.7)" , "pytest-mypy (>=0.9.1)" , "importlib-resources (>=1.3)" ]
2021-07-12 15:50:44 -04:00
[ [ package ] ]
2022-02-03 17:05:51 -05:00
name = "importlib-resources"
2022-08-11 16:34:56 -04:00
version = "5.9.0"
2022-02-03 17:05:51 -05:00
description = "Read resources from Python packages"
2021-07-12 15:50:44 -04:00
category = "main"
optional = false
2022-03-31 13:56:10 -04:00
python-versions = ">=3.7"
2021-07-12 15:50:44 -04:00
[ package . dependencies ]
2022-02-03 17:05:51 -05:00
zipp = { version = ">=3.1.0" , markers = "python_version < \"3.10\"" }
2021-07-12 15:50:44 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
docs = [ "sphinx" , "jaraco.packaging (>=9)" , "rst.linker (>=1.9)" , "jaraco.tidelift (>=1.4)" ]
testing = [ "pytest (>=6)" , "pytest-checkdocs (>=2.4)" , "pytest-flake8" , "pytest-cov" , "pytest-enabler (>=1.3)" , "pytest-black (>=0.3.7)" , "pytest-mypy (>=0.9.1)" ]
2021-07-12 15:50:44 -04:00
2021-08-05 15:35:54 -04:00
[ [ package ] ]
name = "iniconfig"
version = "1.1.1"
description = "iniconfig: brain-dead simple config-ini parsing"
category = "dev"
optional = false
python-versions = "*"
2021-11-09 16:32:46 -05:00
[ [ package ] ]
name = "ipdb"
version = "0.13.9"
description = "IPython-enabled pdb"
category = "main"
optional = false
python-versions = ">=2.7"
[ package . dependencies ]
decorator = { version = "*" , markers = "python_version > \"3.6\"" }
ipython = { version = ">=7.17.0" , markers = "python_version > \"3.6\"" }
toml = { version = ">=0.10.2" , markers = "python_version > \"3.6\"" }
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "ipykernel"
2022-08-11 16:34:56 -04:00
version = "6.15.1"
2021-06-28 16:16:14 -04:00
description = "IPython Kernel for Jupyter"
category = "main"
optional = false
2021-07-12 15:50:44 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2021-07-21 16:10:32 -04:00
appnope = { version = "*" , markers = "platform_system == \"Darwin\"" }
2022-04-18 18:12:18 -04:00
debugpy = ">=1.0"
2022-02-03 17:05:51 -05:00
ipython = ">=7.23.1"
2022-04-18 18:12:18 -04:00
jupyter-client = ">=6.1.12"
matplotlib-inline = ">=0.1"
2022-02-03 17:05:51 -05:00
nest-asyncio = "*"
2022-04-18 18:12:18 -04:00
packaging = "*"
2022-03-17 23:19:23 -04:00
psutil = "*"
2022-08-11 16:34:56 -04:00
pyzmq = ">=17"
2022-04-18 18:12:18 -04:00
tornado = ">=6.1"
traitlets = ">=5.1.0"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "flaky" , "ipyparallel" , "pre-commit" , "pytest-cov" , "pytest-timeout" , "pytest (>=6.0)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "ipython"
2022-08-11 16:34:56 -04:00
version = "7.34.0"
2021-06-28 16:16:14 -04:00
description = "IPython: Productive Interactive Computing"
category = "main"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
appnope = { version = "*" , markers = "sys_platform == \"darwin\"" }
backcall = "*"
colorama = { version = "*" , markers = "sys_platform == \"win32\"" }
decorator = "*"
jedi = ">=0.16"
matplotlib-inline = "*"
pexpect = { version = ">4.3" , markers = "sys_platform != \"win32\"" }
pickleshare = "*"
prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0"
pygments = "*"
traitlets = ">=4.2"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
all = [ "Sphinx (>=1.3)" , "ipykernel" , "ipyparallel" , "ipywidgets" , "nbconvert" , "nbformat" , "nose (>=0.10.1)" , "notebook" , "numpy (>=1.17)" , "pygments" , "qtconsole" , "requests" , "testpath" ]
2022-08-16 14:44:39 -04:00
doc = [ "Sphinx (>=1.3)" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
kernel = [ "ipykernel" ]
nbconvert = [ "nbconvert" ]
nbformat = [ "nbformat" ]
notebook = [ "notebook" , "ipywidgets" ]
parallel = [ "ipyparallel" ]
qtconsole = [ "qtconsole" ]
test = [ "nose (>=0.10.1)" , "requests" , "testpath" , "pygments" , "nbformat" , "ipykernel" , "numpy (>=1.17)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "ipython-genutils"
version = "0.2.0"
description = "Vestigial utilities from IPython"
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "ipywidgets"
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
version = "8.0.1"
description = "Jupyter interactive widgets"
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
ipykernel = ">=4.5.1"
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
ipython = ">=6.1.0"
jupyterlab-widgets = ">=3.0,<4.0"
2021-06-28 16:16:14 -04:00
traitlets = ">=4.3.1"
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
widgetsnbextension = ">=4.0,<5.0"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "jsonschema" , "pytest (>=3.6.0)" , "pytest-cov" , "pytz" ]
2021-06-28 16:16:14 -04:00
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "isort"
2022-02-03 17:05:51 -05:00
version = "5.10.1"
2021-08-02 12:16:38 -04:00
description = "A Python utility / library to sort Python imports."
2021-11-09 16:32:46 -05:00
category = "main"
2021-08-02 12:16:38 -04:00
optional = false
python-versions = ">=3.6.1,<4.0"
[ package . extras ]
pipfile_deprecated_finder = [ "pipreqs" , "requirementslib" ]
requirements_deprecated_finder = [ "pipreqs" , "pip-api" ]
colors = [ "colorama (>=0.4.3,<0.5.0)" ]
plugins = [ "setuptools" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jedi"
2022-02-03 17:05:51 -05:00
version = "0.18.1"
2021-06-28 16:16:14 -04:00
description = "An autocompletion tool for Python that can be used for text editors."
category = "main"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
parso = ">=0.8.0,<0.9.0"
[ package . extras ]
qa = [ "flake8 (==3.8.3)" , "mypy (==0.782)" ]
2022-02-03 17:05:51 -05:00
testing = [ "Django (<3.1)" , "colorama" , "docopt" , "pytest (<7.0.0)" ]
2021-06-28 16:16:14 -04:00
2021-08-10 15:28:50 -04:00
[ [ package ] ]
name = "jellyfish"
version = "0.6.1"
description = "a library for doing approximate and phonetic matching of strings."
category = "main"
optional = false
python-versions = "*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jinja2"
2022-08-11 16:34:56 -04:00
version = "3.1.2"
2021-06-28 16:16:14 -04:00
description = "A very fast and expressive template engine."
category = "main"
optional = false
2022-03-29 17:11:57 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
MarkupSafe = ">=2.0"
[ package . extras ]
i18n = [ "Babel (>=2.7)" ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "json5"
version = "0.9.9"
description = "A Python implementation of the JSON5 data format."
category = "dev"
optional = false
python-versions = "*"
[ package . extras ]
dev = [ "hypothesis" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jsonschema"
2022-08-16 14:44:39 -04:00
version = "4.10.0"
2021-06-28 16:16:14 -04:00
description = "An implementation of JSON Schema validation for Python"
category = "main"
optional = false
2021-11-01 18:05:05 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
attrs = ">=17.4.0"
2022-02-03 17:05:51 -05:00
importlib-resources = { version = ">=1.4.0" , markers = "python_version < \"3.9\"" }
2022-08-11 16:34:56 -04:00
pkgutil-resolve-name = { version = ">=1.3.10" , markers = "python_version < \"3.9\"" }
2021-11-01 18:05:05 -04:00
pyrsistent = ">=0.14.0,<0.17.0 || >0.17.0,<0.17.1 || >0.17.1,<0.17.2 || >0.17.2"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
format = [ "fqdn" , "idna" , "isoduration" , "jsonpointer (>1.13)" , "rfc3339-validator" , "rfc3987" , "uri-template" , "webcolors (>=1.11)" ]
format-nongpl = [ "fqdn" , "idna" , "isoduration" , "jsonpointer (>1.13)" , "rfc3339-validator" , "rfc3986-validator (>0.1.0)" , "uri-template" , "webcolors (>=1.11)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyter"
version = "1.0.0"
description = "Jupyter metapackage. Install all the Jupyter components in one go."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
ipykernel = "*"
ipywidgets = "*"
jupyter-console = "*"
nbconvert = "*"
notebook = "*"
qtconsole = "*"
[ [ package ] ]
name = "jupyter-client"
2022-08-11 16:34:56 -04:00
version = "7.3.4"
2021-06-28 16:16:14 -04:00
description = "Jupyter protocol implementation and client libraries"
category = "main"
optional = false
2022-03-31 13:56:10 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2021-09-14 17:28:59 -04:00
entrypoints = "*"
2022-03-31 13:56:10 -04:00
jupyter-core = ">=4.9.2"
nest-asyncio = ">=1.5.4"
python-dateutil = ">=2.8.2"
2022-08-11 16:34:56 -04:00
pyzmq = ">=23.0"
2022-03-31 13:56:10 -04:00
tornado = ">=6.0"
2021-06-28 16:16:14 -04:00
traitlets = "*"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
doc = [ "ipykernel" , "myst-parser" , "sphinx-rtd-theme" , "sphinx (>=1.3.6)" , "sphinxcontrib-github-alt" ]
test = [ "codecov" , "coverage" , "ipykernel (>=6.5)" , "ipython" , "mypy" , "pre-commit" , "pytest" , "pytest-asyncio (>=0.18)" , "pytest-cov" , "pytest-timeout" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyter-console"
2022-08-11 16:34:56 -04:00
version = "6.4.4"
2021-06-28 16:16:14 -04:00
description = "Jupyter terminal console"
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
ipykernel = "*"
ipython = "*"
2022-03-17 23:19:23 -04:00
jupyter-client = ">=7.0.0"
2021-06-28 16:16:14 -04:00
prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0"
pygments = "*"
[ package . extras ]
test = [ "pexpect" ]
[ [ package ] ]
name = "jupyter-contrib-core"
2022-08-11 16:34:56 -04:00
version = "0.4.0"
2021-06-28 16:16:14 -04:00
description = "Common utilities for jupyter-contrib projects."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
jupyter-core = "*"
notebook = ">=4.0"
tornado = "*"
traitlets = "*"
[ package . extras ]
2022-08-11 16:34:56 -04:00
testing_utils = [ "mock" , "nose" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyter-contrib-nbextensions"
version = "0.5.1"
description = "A collection of Jupyter nbextensions."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
ipython-genutils = "*"
jupyter-contrib-core = ">=0.3.3"
jupyter-core = "*"
jupyter-highlight-selected-word = ">=0.1.1"
jupyter-latex-envs = ">=1.3.8"
jupyter-nbextensions-configurator = ">=0.4.0"
lxml = "*"
nbconvert = ">=4.2"
notebook = ">=4.0"
pyyaml = "*"
tornado = "*"
traitlets = ">=4.1"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "mock" , "requests" , "pip" , "nose" , "nbformat" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyter-core"
2022-08-11 16:34:56 -04:00
version = "4.11.1"
2021-06-28 16:16:14 -04:00
description = "Jupyter core package. A base package on which Jupyter projects rely."
category = "main"
optional = false
2022-04-18 18:12:18 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2021-09-22 12:31:03 -04:00
pywin32 = { version = ">=1.0" , markers = "sys_platform == \"win32\" and platform_python_implementation != \"PyPy\"" }
2021-06-28 16:16:14 -04:00
traitlets = "*"
2022-04-18 18:12:18 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "ipykernel" , "pre-commit" , "pytest" , "pytest-cov" , "pytest-timeout" ]
2022-04-18 18:12:18 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyter-highlight-selected-word"
version = "0.2.0"
description = "Jupyter notebook extension that enables highlighting every instance of the current word in the notebook."
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "jupyter-latex-envs"
version = "1.4.6"
description = "Jupyter notebook extension which supports (some) LaTeX environments within markdown cells. Also provides support for labels and crossreferences, document wide numbering, bibliography, and more..."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
ipython = "*"
jupyter_core = "*"
nbconvert = "*"
notebook = ">=4.0"
traitlets = ">=4.1"
[ [ package ] ]
name = "jupyter-nbextensions-configurator"
2022-08-11 16:34:56 -04:00
version = "0.5.0"
2021-06-28 16:16:14 -04:00
description = "jupyter serverextension providing configuration interfaces for nbextensions."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
2022-08-11 16:34:56 -04:00
jupyter-contrib-core = ">=0.3.3"
jupyter-core = "*"
notebook = ">=6.0"
2021-06-28 16:16:14 -04:00
pyyaml = "*"
tornado = "*"
traitlets = "*"
[ package . extras ]
2022-08-11 16:34:56 -04:00
test = [ "mock" , "selenium" , "requests" , "nose" , "jupyter-contrib-core" ]
2021-06-28 16:16:14 -04:00
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "jupyter-server"
version = "1.18.1"
description = "The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applications."
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
anyio = ">=3.1.0,<4"
argon2-cffi = "*"
jinja2 = "*"
jupyter-client = ">=6.1.12"
jupyter-core = ">=4.7.0"
nbconvert = ">=6.4.4"
nbformat = ">=5.2.0"
packaging = "*"
prometheus-client = "*"
pywinpty = { version = "*" , markers = "os_name == \"nt\"" }
pyzmq = ">=17"
Send2Trash = "*"
terminado = ">=0.8.3"
tornado = ">=6.1.0"
traitlets = ">=5.1"
websocket-client = "*"
[ package . extras ]
test = [ "coverage" , "ipykernel" , "pre-commit" , "pytest-console-scripts" , "pytest-cov" , "pytest-mock" , "pytest-timeout" , "pytest-tornasync" , "pytest (>=6.0)" , "requests" ]
[ [ package ] ]
name = "jupyterlab"
version = "3.4.5"
description = "JupyterLab computational environment"
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
ipython = "*"
jinja2 = ">=2.1"
jupyter-core = "*"
jupyter-server = ">=1.16,<2.0"
jupyterlab-server = ">=2.10,<3.0"
nbclassic = "*"
notebook = "<7"
packaging = "*"
tornado = ">=6.1.0"
[ package . extras ]
test = [ "check-manifest" , "coverage" , "jupyterlab-server" , "pre-commit" , "pytest (>=6.0)" , "pytest-cov" , "pytest-console-scripts" , "pytest-check-links (>=0.5)" , "requests" , "requests-cache" , "virtualenv" ]
ui-tests = [ "build" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyterlab-pygments"
2022-04-18 18:12:18 -04:00
version = "0.2.2"
2021-06-28 16:16:14 -04:00
description = "Pygments theme using JupyterLab CSS variables"
category = "main"
optional = false
2022-04-18 18:12:18 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "jupyterlab-server"
version = "2.15.0"
description = "A set of server components for JupyterLab and JupyterLab like applications."
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
babel = "*"
importlib-metadata = { version = ">=3.6" , markers = "python_version < \"3.10\"" }
jinja2 = ">=3.0.3"
json5 = "*"
jsonschema = ">=3.0.1"
jupyter-server = ">=1.8,<2"
packaging = "*"
requests = "*"
[ package . extras ]
openapi = [ "openapi-core (>=0.14.2)" , "ruamel-yaml" ]
test = [ "codecov" , "ipykernel" , "jupyter-server" , "openapi-core (>=0.14.2)" , "openapi-spec-validator (<0.5)" , "pytest-console-scripts" , "pytest-cov" , "pytest (>=5.3.2)" , "ruamel-yaml" , "strict-rfc3339" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "jupyterlab-widgets"
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
version = "3.0.2"
description = "Jupyter interactive widgets for JupyterLab"
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2021-08-24 15:40:54 -05:00
[ [ package ] ]
name = "kiwisolver"
2022-08-11 16:34:56 -04:00
version = "1.4.4"
2021-08-24 15:40:54 -05:00
description = "A fast implementation of the Cassowary constraint solver"
category = "main"
optional = false
2021-09-14 17:28:59 -04:00
python-versions = ">=3.7"
2021-08-24 15:40:54 -05:00
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "lazy-object-proxy"
2022-02-03 17:05:51 -05:00
version = "1.7.1"
2021-08-02 12:16:38 -04:00
description = "A fast and thorough lazy object proxy."
2021-11-09 16:32:46 -05:00
category = "main"
2021-08-02 12:16:38 -04:00
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "liccheck"
2022-02-03 17:05:51 -05:00
version = "0.6.5"
2021-08-02 12:16:38 -04:00
description = "Check python packages from requirement.txt and report issues"
category = "dev"
optional = false
python-versions = ">=2.7"
[ package . dependencies ]
configparser = { version = "*" , markers = "python_version >= \"3.4\"" }
semantic-version = ">=2.7.0"
toml = "*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "lxml"
2022-07-07 17:09:49 -04:00
version = "4.9.1"
2021-06-28 16:16:14 -04:00
description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
[ package . extras ]
2022-08-16 14:44:39 -04:00
cssselect = [ "cssselect (>=0.7)" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
html5 = [ "html5lib" ]
htmlsoup = [ "beautifulsoup4" ]
source = [ "Cython (>=0.29.7)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "markupsafe"
2022-03-17 23:19:23 -04:00
version = "2.1.1"
2021-06-28 16:16:14 -04:00
description = "Safely add untrusted strings to HTML/XML markup."
category = "main"
optional = false
2022-03-02 16:50:04 -05:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2022-03-31 13:56:10 -04:00
[ [ package ] ]
name = "marshmallow"
2022-08-11 16:34:56 -04:00
version = "3.17.0"
2022-03-31 13:56:10 -04:00
description = "A lightweight library for converting complex datatypes to and from native Python datatypes."
category = "main"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
2022-08-11 16:34:56 -04:00
packaging = ">=17.0"
2022-03-31 13:56:10 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
dev = [ "pytest" , "pytz" , "simplejson" , "mypy (==0.961)" , "flake8 (==4.0.1)" , "flake8-bugbear (==22.6.22)" , "pre-commit (>=2.4,<3.0)" , "tox" ]
docs = [ "sphinx (==4.5.0)" , "sphinx-issues (==3.0.1)" , "alabaster (==0.7.12)" , "sphinx-version-warning (==1.1.2)" , "autodocsumm (==0.2.8)" ]
lint = [ "mypy (==0.961)" , "flake8 (==4.0.1)" , "flake8-bugbear (==22.6.22)" , "pre-commit (>=2.4,<3.0)" ]
2022-03-31 13:56:10 -04:00
tests = [ "pytest" , "pytz" , "simplejson" ]
[ [ package ] ]
name = "marshmallow-dataclass"
2022-08-11 16:34:56 -04:00
version = "8.5.8"
2022-03-31 13:56:10 -04:00
description = "Python library to convert dataclasses into marshmallow schemas."
category = "main"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
marshmallow = ">=3.13.0,<4.0"
typing-inspect = ">=0.7.1"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
dev = [ "marshmallow-enum" , "typeguard" , "pre-commit (>=2.17,<3.0)" , "sphinx" , "pytest (>=5.4)" , "pytest-mypy-plugins (>=1.2.0)" , "typing-extensions (>=3.7.2)" ]
2022-08-16 14:44:39 -04:00
docs = [ "sphinx" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
enum = [ "marshmallow-enum" ]
lint = [ "pre-commit (>=2.17,<3.0)" ]
tests = [ "pytest (>=5.4)" , "pytest-mypy-plugins (>=1.2.0)" , "typing-extensions (>=3.7.2)" ]
union = [ "typeguard" ]
2022-03-31 13:56:10 -04:00
[ [ package ] ]
name = "marshmallow-enum"
version = "1.5.1"
description = "Enum field for Marshmallow"
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
marshmallow = ">=2.0.0"
2021-08-24 15:40:54 -05:00
[ [ package ] ]
name = "matplotlib"
2022-08-16 14:44:39 -04:00
version = "3.5.3"
2021-08-24 15:40:54 -05:00
description = "Python plotting package"
category = "main"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
cycler = ">=0.10"
2022-02-03 17:05:51 -05:00
fonttools = ">=4.22.0"
2021-08-24 15:40:54 -05:00
kiwisolver = ">=1.0.1"
2022-02-03 17:05:51 -05:00
numpy = ">=1.17"
packaging = ">=20.0"
2021-08-24 15:40:54 -05:00
pillow = ">=6.2.0"
pyparsing = ">=2.2.1"
python-dateutil = ">=2.7"
2022-08-16 14:44:39 -04:00
setuptools_scm = ">=4,<7"
2021-08-24 15:40:54 -05:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "matplotlib-inline"
2021-09-14 17:28:59 -04:00
version = "0.1.3"
2021-06-28 16:16:14 -04:00
description = "Inline Matplotlib backend for Jupyter"
category = "main"
optional = false
python-versions = ">=3.5"
[ package . dependencies ]
traitlets = "*"
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "mccabe"
version = "0.6.1"
description = "McCabe checker, plugin for flake8"
2021-11-09 16:32:46 -05:00
category = "main"
2021-08-02 12:16:38 -04:00
optional = false
python-versions = "*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "mistune"
version = "0.8.4"
description = "The fastest markdown parser in pure Python"
category = "main"
optional = false
python-versions = "*"
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "munch"
version = "2.5.0"
description = "A dot-accessible dictionary (a la JavaScript objects)"
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
six = "*"
[ package . extras ]
testing = [ "pytest" , "coverage" , "astroid (>=1.5.3,<1.6.0)" , "pylint (>=1.7.2,<1.8.0)" , "astroid (>=2.0)" , "pylint (>=2.3.1,<2.4.0)" ]
yaml = [ "PyYAML (>=5.1.0)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "mypy"
version = "0.910"
description = "Optional static typing for Python"
category = "dev"
optional = false
python-versions = ">=3.5"
[ package . dependencies ]
mypy-extensions = ">=0.4.3,<0.5.0"
toml = "*"
typing-extensions = ">=3.7.4"
[ package . extras ]
dmypy = [ "psutil (>=4.0)" ]
python2 = [ "typed-ast (>=1.4.0,<1.5.0)" ]
[ [ package ] ]
name = "mypy-extensions"
version = "0.4.3"
description = "Experimental type system extensions for programs checked with the mypy typechecker."
2022-03-31 13:56:10 -04:00
category = "main"
2021-06-28 16:16:14 -04:00
optional = false
python-versions = "*"
2022-03-02 16:50:04 -05:00
[ [ package ] ]
name = "nb-black"
version = "1.0.7"
description = "A simple extension for Jupyter Notebook and Jupyter Lab to beautify Python code automatically using Black."
category = "dev"
optional = false
python-versions = "*"
[ package . dependencies ]
ipython = "*"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "nbclassic"
version = "0.4.3"
description = "A web-based notebook environment for interactive computing"
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
argon2-cffi = "*"
ipykernel = "*"
ipython-genutils = "*"
jinja2 = "*"
jupyter-client = ">=6.1.1"
jupyter-core = ">=4.6.1"
jupyter-server = ">=1.8"
nbconvert = ">=5"
nbformat = "*"
nest-asyncio = ">=1.5"
notebook-shim = ">=0.1.0"
prometheus-client = "*"
pyzmq = ">=17"
Send2Trash = ">=1.8.0"
terminado = ">=0.8.3"
tornado = ">=6.1"
traitlets = ">=4.2.1"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
docs = [ "sphinx" , "nbsphinx" , "sphinxcontrib-github-alt" , "sphinx-rtd-theme" , "myst-parser" ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
json-logging = [ "json-logging" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "pytest" , "coverage" , "requests" , "testpath" , "nbval" , "selenium (==4.1.5)" , "pytest-cov" , "pytest-tornasync" , "requests-unixsocket" ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "nbclient"
2022-08-11 16:34:56 -04:00
version = "0.6.6"
2021-06-28 16:16:14 -04:00
description = "A client library for executing notebooks. Formerly nbconvert's ExecutePreprocessor."
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7.0"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
jupyter-client = ">=6.1.5"
nbformat = ">=5.0"
nest-asyncio = "*"
2022-08-11 16:34:56 -04:00
traitlets = ">=5.2.2"
2021-06-28 16:16:14 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
sphinx = [ "autodoc-traits" , "mock" , "moto" , "myst-parser" , "Sphinx (>=1.7)" , "sphinx-book-theme" ]
2022-04-18 18:12:18 -04:00
test = [ "black" , "check-manifest" , "flake8" , "ipykernel" , "ipython (<8.0.0)" , "ipywidgets (<8.0.0)" , "mypy" , "pip (>=18.1)" , "pre-commit" , "pytest (>=4.1)" , "pytest-asyncio" , "pytest-cov (>=2.6.1)" , "setuptools (>=60.0)" , "testpath" , "twine (>=1.11.0)" , "xmltodict" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "nbconvert"
2022-08-16 14:44:39 -04:00
version = "6.5.3"
2021-06-28 16:16:14 -04:00
description = "Converting Jupyter Notebooks"
category = "main"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
2022-03-17 23:19:23 -04:00
beautifulsoup4 = "*"
2021-06-28 16:16:14 -04:00
bleach = "*"
defusedxml = "*"
entrypoints = ">=0.2.2"
2022-04-18 18:12:18 -04:00
jinja2 = ">=3.0"
jupyter-core = ">=4.7"
2021-06-28 16:16:14 -04:00
jupyterlab-pygments = "*"
2022-08-11 16:34:56 -04:00
lxml = "*"
2022-03-31 13:56:10 -04:00
MarkupSafe = ">=2.0"
2021-06-28 16:16:14 -04:00
mistune = ">=0.8.1,<2"
2022-04-18 18:12:18 -04:00
nbclient = ">=0.5.0"
nbformat = ">=5.1"
packaging = "*"
2021-06-28 16:16:14 -04:00
pandocfilters = ">=1.4.1"
pygments = ">=2.4.1"
2022-04-18 18:12:18 -04:00
tinycss2 = "*"
2021-06-28 16:16:14 -04:00
traitlets = ">=5.0"
[ package . extras ]
2022-04-18 18:12:18 -04:00
all = [ "pytest" , "pytest-cov" , "pytest-dependency" , "ipykernel" , "ipywidgets (>=7)" , "pre-commit" , "pyppeteer (>=1,<1.1)" , "tornado (>=6.1)" , "sphinx (>=1.5.1)" , "sphinx-rtd-theme" , "nbsphinx (>=0.2.12)" , "ipython" ]
2021-06-28 16:16:14 -04:00
docs = [ "sphinx (>=1.5.1)" , "sphinx-rtd-theme" , "nbsphinx (>=0.2.12)" , "ipython" ]
2022-04-18 18:12:18 -04:00
serve = [ "tornado (>=6.1)" ]
test = [ "pytest" , "pytest-cov" , "pytest-dependency" , "ipykernel" , "ipywidgets (>=7)" , "pre-commit" , "pyppeteer (>=1,<1.1)" ]
2022-03-02 16:50:04 -05:00
webpdf = [ "pyppeteer (>=1,<1.1)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "nbformat"
2022-08-11 16:34:56 -04:00
version = "5.4.0"
2021-06-28 16:16:14 -04:00
description = "The Jupyter Notebook format"
category = "main"
optional = false
2022-03-17 23:19:23 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2022-04-18 18:12:18 -04:00
fastjsonschema = "*"
jsonschema = ">=2.6"
2021-06-28 16:16:14 -04:00
jupyter-core = "*"
2022-08-11 16:34:56 -04:00
traitlets = ">=5.1"
2021-06-28 16:16:14 -04:00
[ package . extras ]
2022-04-18 18:12:18 -04:00
test = [ "check-manifest" , "testpath" , "pytest" , "pre-commit" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "nest-asyncio"
2022-04-18 18:12:18 -04:00
version = "1.5.5"
2021-06-28 16:16:14 -04:00
description = "Patch asyncio to allow nested event loops"
category = "main"
optional = false
python-versions = ">=3.5"
[ [ package ] ]
name = "notebook"
2022-07-07 17:10:03 -04:00
version = "6.4.12"
2021-06-28 16:16:14 -04:00
description = "A web-based notebook environment for interactive computing"
category = "main"
optional = false
2022-07-07 17:10:03 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
argon2-cffi = "*"
ipykernel = "*"
ipython-genutils = "*"
jinja2 = "*"
jupyter-client = ">=5.3.4"
jupyter-core = ">=4.6.1"
2022-03-17 23:19:23 -04:00
nbconvert = ">=5"
2021-06-28 16:16:14 -04:00
nbformat = "*"
2022-02-03 17:05:51 -05:00
nest-asyncio = ">=1.5"
2021-06-28 16:16:14 -04:00
prometheus-client = "*"
pyzmq = ">=17"
2022-02-03 17:05:51 -05:00
Send2Trash = ">=1.8.0"
2021-06-28 16:16:14 -04:00
terminado = ">=0.8.3"
tornado = ">=6.1"
traitlets = ">=4.2.1"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
docs = [ "sphinx" , "nbsphinx" , "sphinxcontrib-github-alt" , "sphinx-rtd-theme" , "myst-parser" ]
2021-06-28 16:16:14 -04:00
json-logging = [ "json-logging" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "pytest" , "coverage" , "requests" , "testpath" , "nbval" , "selenium" , "pytest-cov" , "requests-unixsocket" ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "notebook-shim"
version = "0.1.0"
description = "A shim layer for notebook traits and config"
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
jupyter-server = ">=1.8,<2.0"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "pytest" , "pytest-tornasync" , "pytest-console-scripts" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "numpy"
2022-08-16 14:44:39 -04:00
version = "1.23.2"
2021-06-28 16:16:14 -04:00
description = "NumPy is the fundamental package for array computing with Python."
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.8"
2021-06-28 16:16:14 -04:00
2021-08-09 10:39:59 -04:00
[ [ package ] ]
name = "openpyxl"
2022-08-11 16:34:56 -04:00
version = "3.0.10"
2021-08-09 10:39:59 -04:00
description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
category = "dev"
optional = false
2021-11-01 18:05:05 -04:00
python-versions = ">=3.6"
2021-08-09 10:39:59 -04:00
[ package . dependencies ]
et-xmlfile = "*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "packaging"
2022-02-03 17:05:51 -05:00
version = "21.3"
2021-06-28 16:16:14 -04:00
description = "Core utilities for Python packages"
category = "main"
optional = false
2021-07-12 15:50:44 -04:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2022-02-03 17:05:51 -05:00
pyparsing = ">=2.0.2,<3.0.5 || >3.0.5"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pandas"
2022-08-11 16:34:56 -04:00
version = "1.4.3"
2021-06-28 16:16:14 -04:00
description = "Powerful data structures for data analysis, time series, and statistics"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.8"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
2021-11-01 18:05:05 -04:00
numpy = [
2022-08-16 14:44:39 -04:00
{ version = ">=1.18.5" , markers = "platform_machine != \"aarch64\" and platform_machine != \"arm64\" and python_version < \"3.10\"" } ,
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
{ version = ">=1.19.2" , markers = "platform_machine == \"aarch64\" and python_version < \"3.10\"" } ,
{ version = ">=1.20.0" , markers = "platform_machine == \"arm64\" and python_version < \"3.10\"" } ,
{ version = ">=1.21.0" , markers = "python_version >= \"3.10\"" } ,
2021-11-01 18:05:05 -04:00
]
2022-02-03 17:05:51 -05:00
python-dateutil = ">=2.8.1"
pytz = ">=2020.1"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "hypothesis (>=5.5.3)" , "pytest (>=6.0)" , "pytest-xdist (>=1.31)" ]
2021-06-28 16:16:14 -04:00
2022-01-13 13:17:30 -05:00
[ [ package ] ]
name = "pandas-vet"
2022-03-02 16:50:04 -05:00
version = "0.2.3"
2022-01-13 13:17:30 -05:00
description = "A flake8 plugin to lint pandas in an opinionated way"
category = "dev"
optional = false
python-versions = "*"
[ package . dependencies ]
attrs = "*"
flake8 = ">3.0.0"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pandocfilters"
2021-09-14 17:28:59 -04:00
version = "1.5.0"
2021-06-28 16:16:14 -04:00
description = "Utilities for writing pandoc filters in python"
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
2022-03-30 14:02:06 -04:00
[ [ package ] ]
name = "papermill"
2022-08-16 14:44:39 -04:00
version = "2.4.0"
2022-03-30 14:02:06 -04:00
description = "Parametrize and run Jupyter and nteract Notebooks"
category = "dev"
optional = false
2022-08-16 14:44:39 -04:00
python-versions = ">=3.7"
2022-03-30 14:02:06 -04:00
[ package . dependencies ]
ansiwrap = "*"
click = "*"
entrypoints = "*"
nbclient = ">=0.2.0"
nbformat = ">=5.1.2"
pyyaml = "*"
requests = "*"
tenacity = "*"
tqdm = ">=4.32.2"
[ package . extras ]
2022-08-16 14:44:39 -04:00
all = [ "boto3" , "azure-datalake-store (>=0.0.30)" , "azure-storage-blob (>=12.1.0)" , "requests (>=2.21.0)" , "gcsfs (>=0.2.0)" , "pyarrow (>=2.0)" , "black (>=19.3b0)" ]
2022-03-30 14:02:06 -04:00
azure = [ "azure-datalake-store (>=0.0.30)" , "azure-storage-blob (>=12.1.0)" , "requests (>=2.21.0)" ]
black = [ "black (>=19.3b0)" ]
2022-08-16 14:44:39 -04:00
dev = [ "boto3" , "botocore" , "codecov" , "coverage" , "google-compute-engine" , "ipython (>=5.0)" , "ipywidgets" , "notebook" , "moto" , "pytest (>=4.1)" , "pytest-cov (>=2.6.1)" , "pytest-mock (>=1.10)" , "pytest-env (>=0.6.2)" , "requests (>=2.21.0)" , "check-manifest" , "attrs (>=17.4.0)" , "pre-commit" , "flake8" , "tox" , "bumpversion" , "recommonmark" , "pip (>=18.1)" , "wheel (>=0.31.0)" , "setuptools (>=38.6.0)" , "twine (>=1.11.0)" , "azure-datalake-store (>=0.0.30)" , "azure-storage-blob (>=12.1.0)" , "gcsfs (>=0.2.0)" , "pyarrow (>=2.0)" , "black (>=19.3b0)" ]
2022-03-30 14:02:06 -04:00
gcs = [ "gcsfs (>=0.2.0)" ]
github = [ "PyGithub (>=1.55)" ]
2022-08-16 14:44:39 -04:00
hdfs = [ "pyarrow (>=2.0)" ]
2022-03-30 14:02:06 -04:00
s3 = [ "boto3" ]
2022-08-16 14:44:39 -04:00
test = [ "boto3" , "botocore" , "codecov" , "coverage" , "google-compute-engine" , "ipython (>=5.0)" , "ipywidgets" , "notebook" , "moto" , "pytest (>=4.1)" , "pytest-cov (>=2.6.1)" , "pytest-mock (>=1.10)" , "pytest-env (>=0.6.2)" , "requests (>=2.21.0)" , "check-manifest" , "attrs (>=17.4.0)" , "pre-commit" , "flake8" , "tox" , "bumpversion" , "recommonmark" , "pip (>=18.1)" , "wheel (>=0.31.0)" , "setuptools (>=38.6.0)" , "twine (>=1.11.0)" , "azure-datalake-store (>=0.0.30)" , "azure-storage-blob (>=12.1.0)" , "gcsfs (>=0.2.0)" , "pyarrow (>=2.0)" , "black (>=19.3b0)" ]
2022-03-30 14:02:06 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "parso"
2022-02-03 17:05:51 -05:00
version = "0.8.3"
2021-06-28 16:16:14 -04:00
description = "A Python Parser"
category = "main"
optional = false
python-versions = ">=3.6"
[ package . extras ]
qa = [ "flake8 (==3.8.3)" , "mypy (==0.782)" ]
testing = [ "docopt" , "pytest (<6.0.0)" ]
[ [ package ] ]
name = "pathspec"
2021-07-21 16:10:32 -04:00
version = "0.9.0"
2021-06-28 16:16:14 -04:00
description = "Utility library for gitignore style pattern matching of file paths."
category = "dev"
optional = false
2021-07-21 16:10:32 -04:00
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pexpect"
version = "4.8.0"
description = "Pexpect allows easy control of interactive console applications."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
ptyprocess = ">=0.5"
[ [ package ] ]
name = "pickleshare"
version = "0.7.5"
description = "Tiny 'shelve'-like database with concurrency support"
category = "main"
optional = false
python-versions = "*"
2021-08-24 15:40:54 -05:00
[ [ package ] ]
name = "pillow"
2022-03-02 16:50:04 -05:00
version = "9.0.1"
2021-08-24 15:40:54 -05:00
description = "Python Imaging Library (Fork)"
category = "main"
optional = false
2022-01-27 18:19:49 -05:00
python-versions = ">=3.7"
2021-08-24 15:40:54 -05:00
2022-08-11 16:34:56 -04:00
[ [ package ] ]
name = "pkgutil-resolve-name"
version = "1.3.10"
description = "Resolve a name to an object."
category = "main"
optional = false
python-versions = ">=3.6"
2021-07-29 14:00:20 -04:00
[ [ package ] ]
name = "platformdirs"
2022-04-18 18:12:18 -04:00
version = "2.5.2"
2021-07-29 14:00:20 -04:00
description = "A small Python module for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
2021-11-09 16:32:46 -05:00
category = "main"
2021-07-29 14:00:20 -04:00
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7"
2021-08-05 15:35:54 -04:00
[ package . extras ]
2022-04-18 18:12:18 -04:00
docs = [ "furo (>=2021.7.5b38)" , "proselint (>=0.10.2)" , "sphinx-autodoc-typehints (>=1.12)" , "sphinx (>=4)" ]
test = [ "appdirs (==1.4.4)" , "pytest-cov (>=2.7)" , "pytest-mock (>=3.6)" , "pytest (>=6)" ]
2021-07-29 14:00:20 -04:00
[ [ package ] ]
name = "pluggy"
2021-09-14 17:28:59 -04:00
version = "1.0.0"
2021-07-29 14:00:20 -04:00
description = "plugin and hook calling mechanisms for python"
category = "dev"
optional = false
2021-09-14 17:28:59 -04:00
python-versions = ">=3.6"
2021-07-29 14:00:20 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
testing = [ "pytest-benchmark" , "pytest" ]
dev = [ "tox" , "pre-commit" ]
2021-07-29 14:00:20 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "prometheus-client"
2022-04-18 18:12:18 -04:00
version = "0.14.1"
2021-06-28 16:16:14 -04:00
description = "Python client for the Prometheus monitoring system."
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
[ package . extras ]
twisted = [ "twisted" ]
[ [ package ] ]
name = "prompt-toolkit"
2022-08-11 16:34:56 -04:00
version = "3.0.30"
2021-06-28 16:16:14 -04:00
description = "Library for building powerful interactive command lines in Python"
category = "main"
optional = false
2021-09-14 17:28:59 -04:00
python-versions = ">=3.6.2"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
wcwidth = "*"
2022-03-17 23:19:23 -04:00
[ [ package ] ]
name = "psutil"
2022-08-11 16:34:56 -04:00
version = "5.9.1"
2022-03-17 23:19:23 -04:00
description = "Cross-platform lib for process and system monitoring in Python."
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
2022-03-17 23:19:23 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "ipaddress" , "mock" , "enum34" , "pywin32" , "wmi" ]
2022-03-17 23:19:23 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "ptyprocess"
version = "0.7.0"
description = "Run a subprocess in a pseudo terminal"
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "py"
2022-02-03 17:05:51 -05:00
version = "1.11.0"
2021-06-28 16:16:14 -04:00
description = "library with cross-python path, ini-parsing, io, code, log facilities"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
2021-06-28 16:16:14 -04:00
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "pycodestyle"
version = "2.7.0"
description = "Python style guide checker"
category = "dev"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pycparser"
2022-02-03 17:05:51 -05:00
version = "2.21"
2021-06-28 16:16:14 -04:00
description = "C parser in Python"
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
2022-04-27 15:59:10 -04:00
[ [ package ] ]
name = "pydantic"
2022-08-16 14:44:39 -04:00
version = "1.9.2"
2022-08-11 16:34:56 -04:00
description = "Data validation and settings management using python type hints"
2022-04-27 15:59:10 -04:00
category = "main"
optional = false
python-versions = ">=3.6.1"
[ package . dependencies ]
typing-extensions = ">=3.7.4.3"
[ package . extras ]
dotenv = [ "python-dotenv (>=0.10.4)" ]
email = [ "email-validator (>=1.0.3)" ]
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "pyflakes"
version = "2.3.1"
description = "passive checker of Python programs"
category = "dev"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pygments"
2022-08-16 14:44:39 -04:00
version = "2.13.0"
2021-06-28 16:16:14 -04:00
description = "Pygments is a syntax highlighting package written in Python."
category = "main"
optional = false
2022-04-27 15:59:10 -04:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
2022-08-16 14:44:39 -04:00
[ package . extras ]
plugins = [ "importlib-metadata" ]
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "pylint"
2022-08-11 16:34:56 -04:00
version = "2.14.5"
2021-08-02 12:16:38 -04:00
description = "python code static checker"
2021-11-09 16:32:46 -05:00
category = "main"
2021-08-02 12:16:38 -04:00
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.7.2"
2021-08-02 12:16:38 -04:00
[ package . dependencies ]
2022-08-11 16:34:56 -04:00
astroid = ">=2.11.6,<=2.12.0-dev0"
colorama = { version = ">=0.4.5" , markers = "sys_platform == \"win32\"" }
2022-03-31 13:56:10 -04:00
dill = ">=0.2"
2021-08-02 12:16:38 -04:00
isort = ">=4.2.5,<6"
2022-03-31 13:56:10 -04:00
mccabe = ">=0.6,<0.8"
2021-09-14 17:28:59 -04:00
platformdirs = ">=2.2.0"
2022-03-31 13:56:10 -04:00
tomli = { version = ">=1.1.0" , markers = "python_version < \"3.11\"" }
2022-08-11 16:34:56 -04:00
tomlkit = ">=0.10.1"
2021-09-22 12:31:03 -04:00
typing-extensions = { version = ">=3.10.0" , markers = "python_version < \"3.10\"" }
2021-08-02 12:16:38 -04:00
2022-03-31 13:56:10 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
spelling = [ "pyenchant (>=3.2,<4.0)" ]
testutils = [ "gitpython (>3)" ]
2022-03-31 13:56:10 -04:00
2021-08-10 15:28:50 -04:00
[ [ package ] ]
name = "pypandoc"
2022-08-11 16:34:56 -04:00
version = "1.8.1"
2021-08-10 15:28:50 -04:00
description = "Thin wrapper for pandoc."
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.6"
2021-08-10 15:28:50 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pyparsing"
2022-08-11 16:34:56 -04:00
version = "3.0.9"
2022-04-18 18:12:18 -04:00
description = "pyparsing module - Classes and methods to define and execute parsing grammars"
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
2022-04-18 18:12:18 -04:00
python-versions = ">=3.6.8"
2022-02-03 17:05:51 -05:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
diagrams = [ "railroad-diagrams" , "jinja2" ]
2021-06-28 16:16:14 -04:00
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "pyproj"
2022-04-27 15:59:10 -04:00
version = "3.3.1"
2021-07-21 16:10:32 -04:00
description = "Python interface to PROJ (cartographic projections and coordinate transformations library)"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.8"
2021-07-21 16:10:32 -04:00
[ package . dependencies ]
certifi = "*"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pyrsistent"
2022-02-03 17:05:51 -05:00
version = "0.18.1"
2021-06-28 16:16:14 -04:00
description = "Persistent/Functional/Immutable data structures"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2021-08-05 15:35:54 -04:00
[ [ package ] ]
name = "pytest"
2021-09-14 17:28:59 -04:00
version = "6.2.5"
2021-08-05 15:35:54 -04:00
description = "pytest: simple powerful testing with Python"
category = "dev"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
atomicwrites = { version = ">=1.0" , markers = "sys_platform == \"win32\"" }
attrs = ">=19.2.0"
colorama = { version = "*" , markers = "sys_platform == \"win32\"" }
iniconfig = "*"
packaging = "*"
2021-09-14 17:28:59 -04:00
pluggy = ">=0.12,<2.0"
2021-08-05 15:35:54 -04:00
py = ">=1.8.2"
toml = "*"
[ package . extras ]
testing = [ "argcomplete" , "hypothesis (>=3.56)" , "mock" , "nose" , "requests" , "xmlschema" ]
2021-09-10 14:17:34 -04:00
[ [ package ] ]
name = "pytest-mock"
2022-08-11 16:34:56 -04:00
version = "3.8.2"
2021-09-10 14:17:34 -04:00
description = "Thin-wrapper around the mock package for easier use with pytest"
category = "dev"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7"
2021-09-10 14:17:34 -04:00
[ package . dependencies ]
pytest = ">=5.0"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
dev = [ "pre-commit" , "tox" , "pytest-asyncio" ]
2021-09-10 14:17:34 -04:00
2022-03-11 21:34:07 -05:00
[ [ package ] ]
name = "pytest-snapshot"
version = "0.8.1"
description = "A plugin for snapshot testing with pytest."
category = "dev"
optional = false
python-versions = ">=3.5"
[ package . dependencies ]
pytest = ">=3.0.0"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "python-dateutil"
2021-07-21 16:10:32 -04:00
version = "2.8.2"
2021-06-28 16:16:14 -04:00
description = "Extensions to the standard Python datetime module"
category = "main"
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
[ package . dependencies ]
six = ">=1.5"
[ [ package ] ]
name = "pytz"
2022-08-16 14:44:39 -04:00
version = "2022.2.1"
2021-06-28 16:16:14 -04:00
description = "World timezone definitions, modern and historical"
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "pywin32"
2022-08-11 16:34:56 -04:00
version = "304"
2021-06-28 16:16:14 -04:00
description = "Python for Window Extensions"
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "pywinpty"
2022-08-11 16:34:56 -04:00
version = "2.0.7"
2021-06-28 16:16:14 -04:00
description = "Pseudo terminal support for Windows from Python."
category = "main"
optional = false
2022-03-08 17:33:11 -05:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pyyaml"
2021-11-01 18:05:05 -04:00
version = "6.0"
2021-06-28 16:16:14 -04:00
description = "YAML parser and emitter for Python"
category = "main"
optional = false
2021-11-01 18:05:05 -04:00
python-versions = ">=3.6"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "pyzmq"
2022-08-16 14:44:39 -04:00
version = "23.2.1"
2021-06-28 16:16:14 -04:00
description = "Python bindings for 0MQ"
category = "main"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
cffi = { version = "*" , markers = "implementation_name == \"pypy\"" }
py = { version = "*" , markers = "implementation_name == \"pypy\"" }
[ [ package ] ]
name = "qtconsole"
2022-08-11 16:34:56 -04:00
version = "5.3.1"
2021-06-28 16:16:14 -04:00
description = "Jupyter Qt console"
category = "main"
optional = false
2022-03-31 13:56:10 -04:00
python-versions = ">= 3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
ipykernel = ">=4.1"
ipython-genutils = "*"
jupyter-client = ">=4.1"
jupyter-core = "*"
pygments = "*"
pyzmq = ">=17.1"
2022-03-31 13:56:10 -04:00
qtpy = ">=2.0.1"
2022-08-11 16:34:56 -04:00
traitlets = "<5.2.1 || >5.2.1,<5.2.2 || >5.2.2"
2021-06-28 16:16:14 -04:00
[ package . extras ]
doc = [ "Sphinx (>=1.3)" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "flaky" , "pytest" , "pytest-qt" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "qtpy"
2022-08-11 16:34:56 -04:00
version = "2.2.0"
2022-02-03 17:05:51 -05:00
description = "Provides an abstraction layer on top of the various Qt bindings (PyQt5/6 and PySide2/6)."
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2022-02-03 17:05:51 -05:00
[ package . dependencies ]
packaging = "*"
[ package . extras ]
2022-08-11 16:34:56 -04:00
test = [ "pytest-qt" , "pytest-cov (>=3.0.0)" , "pytest (>=6,!=7.0.0,!=7.0.1)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "requests"
2022-08-11 16:34:56 -04:00
version = "2.28.1"
2021-06-28 16:16:14 -04:00
description = "Python HTTP for Humans."
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.7, <4"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
certifi = ">=2017.4.17"
2022-08-11 16:34:56 -04:00
charset-normalizer = ">=2,<3"
idna = ">=2.5,<4"
2021-06-28 16:16:14 -04:00
urllib3 = ">=1.21.1,<1.27"
[ package . extras ]
2022-08-16 14:44:39 -04:00
socks = [ "PySocks (>=1.5.6,!=1.5.7)" ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
use_chardet_on_py3 = [ "chardet (>=3.0.2,<6)" ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "rtree"
version = "1.0.0"
description = "R-Tree spatial index for Python GIS"
category = "main"
optional = false
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "safety"
version = "1.10.3"
description = "Checks installed dependencies for known vulnerabilities."
category = "dev"
optional = false
python-versions = ">=3.5"
[ package . dependencies ]
Click = ">=6.0"
dparse = ">=0.5.1"
packaging = "*"
requests = "*"
2022-03-30 14:02:06 -04:00
[ [ package ] ]
name = "scipy"
version = "1.6.1"
description = "SciPy: Scientific Library for Python"
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . dependencies ]
numpy = ">=1.16.5"
[ [ package ] ]
name = "seaborn"
version = "0.11.2"
description = "seaborn: statistical data visualization"
category = "dev"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
matplotlib = ">=2.2"
numpy = ">=1.15"
pandas = ">=0.23"
scipy = ">=1.0"
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "semantic-version"
2022-08-11 16:34:56 -04:00
version = "2.10.0"
2021-08-02 12:16:38 -04:00
description = "A library implementing the 'SemVer' scheme."
category = "dev"
optional = false
2022-03-02 16:50:04 -05:00
python-versions = ">=2.7"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
dev = [ "Django (>=1.11)" , "nose2" , "tox" , "check-manifest" , "coverage" , "flake8" , "wheel" , "zest.releaser" , "readme-renderer (<25.0)" , "colorama (<=0.4.1)" ]
doc = [ "sphinx" , "sphinx-rtd-theme" ]
2021-08-02 12:16:38 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "send2trash"
2021-08-10 15:28:50 -04:00
version = "1.8.0"
2021-06-28 16:16:14 -04:00
description = "Send file to trash natively under Mac OS X, Windows and Linux."
category = "main"
optional = false
python-versions = "*"
[ package . extras ]
2021-08-10 15:28:50 -04:00
nativelib = [ "pyobjc-framework-cocoa" , "pywin32" ]
objc = [ "pyobjc-framework-cocoa" ]
2021-06-28 16:16:14 -04:00
win32 = [ "pywin32" ]
2022-02-03 17:05:51 -05:00
[ [ package ] ]
name = "setuptools-scm"
2022-08-16 14:44:39 -04:00
version = "6.4.2"
2022-02-03 17:05:51 -05:00
description = "the blessed package to manage your versions by scm tags"
category = "main"
optional = false
2022-08-16 14:44:39 -04:00
python-versions = ">=3.6"
2022-02-03 17:05:51 -05:00
[ package . dependencies ]
packaging = ">=20.0"
tomli = ">=1.0.0"
[ package . extras ]
test = [ "pytest (>=6.2)" , "virtualenv (>20)" ]
toml = [ "setuptools (>=42)" ]
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "shapely"
2022-08-11 16:34:56 -04:00
version = "1.8.2"
2021-07-21 16:10:32 -04:00
description = "Geometric objects, predicates, and operations"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.6"
2021-07-21 16:10:32 -04:00
[ package . extras ]
2022-02-03 17:05:51 -05:00
all = [ "pytest" , "pytest-cov" , "numpy" ]
2021-07-21 16:10:32 -04:00
test = [ "pytest" , "pytest-cov" ]
vectorized = [ "numpy" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "six"
version = "1.16.0"
description = "Python 2 and 3 compatibility utilities"
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "sniffio"
version = "1.2.0"
description = "Sniff out which async library your code is running under"
category = "dev"
optional = false
python-versions = ">=3.5"
2022-03-17 23:19:23 -04:00
[ [ package ] ]
name = "soupsieve"
2022-04-18 18:12:18 -04:00
version = "2.3.2.post1"
2022-03-17 23:19:23 -04:00
description = "A modern CSS selector implementation for Beautiful Soup."
category = "main"
optional = false
python-versions = ">=3.6"
2022-03-30 14:02:06 -04:00
[ [ package ] ]
name = "tenacity"
version = "8.0.1"
description = "Retry code until it succeeds"
category = "dev"
optional = false
python-versions = ">=3.6"
[ package . extras ]
doc = [ "reno" , "sphinx" , "tornado (>=4.5)" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "terminado"
2022-08-11 16:34:56 -04:00
version = "0.15.0"
2021-06-28 16:16:14 -04:00
description = "Tornado websocket backend for the Xterm.js Javascript terminal emulator library."
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
[ package . dependencies ]
ptyprocess = { version = "*" , markers = "os_name != \"nt\"" }
pywinpty = { version = ">=1.1.0" , markers = "os_name == \"nt\"" }
2022-08-11 16:34:56 -04:00
tornado = ">=6.1.0"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "pre-commit" , "pytest-timeout" , "pytest (>=6.0)" ]
2021-06-28 16:16:14 -04:00
2022-03-30 14:02:06 -04:00
[ [ package ] ]
name = "textwrap3"
version = "0.9.2"
description = "textwrap from Python 3.6 backport (plus a few tweaks)"
category = "dev"
optional = false
python-versions = "*"
2022-04-18 18:12:18 -04:00
[ [ package ] ]
name = "tinycss2"
version = "1.1.1"
description = "A tiny CSS parser"
category = "main"
optional = false
python-versions = ">=3.6"
[ package . dependencies ]
webencodings = ">=0.4"
[ package . extras ]
doc = [ "sphinx" , "sphinx-rtd-theme" ]
test = [ "pytest" , "pytest-cov" , "pytest-flake8" , "pytest-isort" , "coverage" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "toml"
version = "0.10.2"
description = "Python Library for Tom's Obvious, Minimal Language"
2021-11-09 16:32:46 -05:00
category = "main"
2021-06-28 16:16:14 -04:00
optional = false
python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
2021-07-21 16:10:32 -04:00
[ [ package ] ]
name = "tomli"
2022-02-03 17:05:51 -05:00
version = "1.2.3"
2021-07-21 16:10:32 -04:00
description = "A lil' TOML parser"
2022-02-03 17:05:51 -05:00
category = "main"
2021-07-21 16:10:32 -04:00
optional = false
python-versions = ">=3.6"
2022-08-11 16:34:56 -04:00
[ [ package ] ]
name = "tomlkit"
2022-08-16 14:44:39 -04:00
version = "0.11.4"
2022-08-11 16:34:56 -04:00
description = "Style preserving TOML library"
category = "main"
optional = false
python-versions = ">=3.6,<4.0"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "tornado"
2022-08-11 16:34:56 -04:00
version = "6.2"
2021-06-28 16:16:14 -04:00
description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed."
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">= 3.7"
2021-06-28 16:16:14 -04:00
2021-07-29 14:00:20 -04:00
[ [ package ] ]
name = "tox"
2022-08-11 16:34:56 -04:00
version = "3.25.1"
2021-07-29 14:00:20 -04:00
description = "tox is a generic virtualenv management and test command line tool"
category = "dev"
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
[ package . dependencies ]
colorama = { version = ">=0.4.1" , markers = "platform_system == \"Windows\"" }
filelock = ">=3.0.0"
packaging = ">=14"
pluggy = ">=0.12.0"
py = ">=1.4.17"
six = ">=1.14.0"
toml = ">=0.9.4"
virtualenv = ">=16.0.0,<20.0.0 || >20.0.0,<20.0.1 || >20.0.1,<20.0.2 || >20.0.2,<20.0.3 || >20.0.3,<20.0.4 || >20.0.4,<20.0.5 || >20.0.5,<20.0.6 || >20.0.6,<20.0.7 || >20.0.7"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
docs = [ "pygments-github-lexers (>=0.0.5)" , "sphinx (>=2.0.0)" , "sphinxcontrib-autoprogram (>=0.1.5)" , "towncrier (>=18.5.0)" ]
testing = [ "flaky (>=3.4.0)" , "freezegun (>=0.3.11)" , "pytest (>=4.0.0)" , "pytest-cov (>=2.5.1)" , "pytest-mock (>=1.10.0)" , "pytest-randomly (>=1.0.0)" , "psutil (>=5.6.1)" , "pathlib2 (>=2.3.3)" ]
2021-07-29 14:00:20 -04:00
2022-01-10 16:43:56 -05:00
[ [ package ] ]
name = "tox-poetry"
version = "0.4.1"
description = "Tox poetry plugin"
category = "dev"
optional = false
python-versions = "*"
[ package . dependencies ]
pluggy = "*"
toml = "*"
tox = { version = ">=3.7.0" , markers = "python_version >= \"3\"" }
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "pylint" , "pycodestyle" , "pytest" , "coverage" ]
2022-01-10 16:43:56 -05:00
2021-08-10 15:28:50 -04:00
[ [ package ] ]
name = "tqdm"
version = "4.62.0"
description = "Fast, Extensible Progress Meter"
category = "main"
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
[ package . dependencies ]
colorama = { version = "*" , markers = "platform_system == \"Windows\"" }
[ package . extras ]
dev = [ "py-make (>=0.1.0)" , "twine" , "wheel" ]
notebook = [ "ipywidgets (>=6)" ]
telegram = [ "requests" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "traitlets"
2022-08-11 16:34:56 -04:00
version = "5.3.0"
description = ""
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
python-versions = ">=3.7"
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
test = [ "pre-commit" , "pytest" ]
2021-06-28 16:16:14 -04:00
2021-07-12 15:50:44 -04:00
[ [ package ] ]
2022-02-03 17:05:51 -05:00
name = "types-requests"
2022-08-11 16:34:56 -04:00
version = "2.28.8"
2022-02-03 17:05:51 -05:00
description = "Typing stubs for requests"
2021-11-09 16:32:46 -05:00
category = "main"
2021-07-12 15:50:44 -04:00
optional = false
python-versions = "*"
2022-02-03 17:05:51 -05:00
[ package . dependencies ]
types-urllib3 = "<1.27"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
2022-02-03 17:05:51 -05:00
name = "types-urllib3"
2022-08-11 16:34:56 -04:00
version = "1.26.22"
2022-02-03 17:05:51 -05:00
description = "Typing stubs for urllib3"
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "typing-extensions"
2022-08-11 16:34:56 -04:00
version = "4.3.0"
2022-04-18 18:12:18 -04:00
description = "Backported and Experimental Type Hints for Python 3.7+"
2021-07-12 15:50:44 -04:00
category = "main"
2021-06-28 16:16:14 -04:00
optional = false
2022-04-18 18:12:18 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2022-03-31 13:56:10 -04:00
[ [ package ] ]
name = "typing-inspect"
version = "0.7.1"
description = "Runtime inspection utilities for typing module."
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
mypy-extensions = ">=0.3.0"
typing-extensions = ">=3.7.4"
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "urllib3"
2022-08-11 16:34:56 -04:00
version = "1.26.11"
2021-06-28 16:16:14 -04:00
description = "HTTP library with thread-safe connection pooling, file post, and more."
category = "main"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, <4"
2021-06-28 16:16:14 -04:00
[ package . extras ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
brotli = [ "brotlicffi (>=0.8.0)" , "brotli (>=1.0.9)" , "brotlipy (>=0.6.0)" ]
secure = [ "pyOpenSSL (>=0.14)" , "cryptography (>=1.3.4)" , "idna (>=2.0.0)" , "certifi" , "ipaddress" ]
2021-06-28 16:16:14 -04:00
socks = [ "PySocks (>=1.5.6,!=1.5.7,<2.0)" ]
2021-08-10 15:28:50 -04:00
[ [ package ] ]
name = "us"
version = "2.0.2"
description = "US state meta information and other fun stuff"
category = "main"
optional = false
python-versions = "*"
[ package . dependencies ]
jellyfish = "0.6.1"
2021-07-29 14:00:20 -04:00
[ [ package ] ]
name = "virtualenv"
2022-08-11 16:34:56 -04:00
version = "20.16.3"
2021-07-29 14:00:20 -04:00
description = "Virtual Python Environment builder"
category = "dev"
optional = false
2022-08-11 16:34:56 -04:00
python-versions = ">=3.6"
2021-07-29 14:00:20 -04:00
[ package . dependencies ]
2022-08-11 16:34:56 -04:00
distlib = ">=0.3.5,<1"
filelock = ">=3.4.1,<4"
platformdirs = ">=2.4,<3"
2021-07-29 14:00:20 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
docs = [ "proselint (>=0.13)" , "sphinx (>=5.1.1)" , "sphinx-argparse (>=0.3.1)" , "sphinx-rtd-theme (>=1)" , "towncrier (>=21.9)" ]
testing = [ "coverage (>=6.2)" , "coverage-enable-subprocess (>=1)" , "flaky (>=3.7)" , "packaging (>=21.3)" , "pytest (>=7.0.1)" , "pytest-env (>=0.6.2)" , "pytest-freezegun (>=0.4.2)" , "pytest-mock (>=3.6.1)" , "pytest-randomly (>=3.10.3)" , "pytest-timeout (>=2.1)" ]
2021-07-29 14:00:20 -04:00
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "wcwidth"
version = "0.2.5"
description = "Measures the displayed width of unicode strings in a terminal"
category = "main"
optional = false
python-versions = "*"
[ [ package ] ]
name = "webencodings"
version = "0.5.1"
description = "Character encoding aliases for legacy web content"
category = "main"
optional = false
python-versions = "*"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
[ [ package ] ]
name = "websocket-client"
version = "1.3.3"
description = "WebSocket client for Python with low level API options"
category = "dev"
optional = false
python-versions = ">=3.7"
[ package . extras ]
docs = [ "Sphinx (>=3.4)" , "sphinx-rtd-theme (>=0.5)" ]
optional = [ "python-socks" , "wsaccel" ]
test = [ "websockets" ]
2021-06-28 16:16:14 -04:00
[ [ package ] ]
name = "widgetsnbextension"
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
version = "4.0.2"
description = "Jupyter interactive widgets for Jupyter Notebook"
2021-06-28 16:16:14 -04:00
category = "main"
optional = false
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
python-versions = ">=3.7"
2021-06-28 16:16:14 -04:00
2021-08-02 12:16:38 -04:00
[ [ package ] ]
name = "wrapt"
2022-08-11 16:34:56 -04:00
version = "1.14.1"
2021-08-02 12:16:38 -04:00
description = "Module for decorators, wrappers and monkey patching."
2021-11-09 16:32:46 -05:00
category = "main"
2021-08-02 12:16:38 -04:00
optional = false
2021-11-01 18:05:05 -04:00
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
2021-08-02 12:16:38 -04:00
2021-08-10 15:28:50 -04:00
[ [ package ] ]
name = "xlsxwriter"
version = "2.0.0"
description = "A Python module for creating Excel XLSX files."
category = "main"
optional = false
python-versions = "*"
2021-07-12 15:50:44 -04:00
[ [ package ] ]
name = "zipp"
2022-08-11 16:34:56 -04:00
version = "3.8.1"
2021-07-12 15:50:44 -04:00
description = "Backport of pathlib-compatible object wrapper for zip files"
category = "main"
optional = false
2022-02-03 17:05:51 -05:00
python-versions = ">=3.7"
2021-07-12 15:50:44 -04:00
[ package . extras ]
2022-08-11 16:34:56 -04:00
docs = [ "sphinx" , "jaraco.packaging (>=9)" , "rst.linker (>=1.9)" , "jaraco.tidelift (>=1.4)" ]
testing = [ "pytest (>=6)" , "pytest-checkdocs (>=2.4)" , "pytest-flake8" , "pytest-cov" , "pytest-enabler (>=1.3)" , "jaraco.itertools" , "func-timeout" , "pytest-black (>=0.3.7)" , "pytest-mypy (>=0.9.1)" ]
2021-07-12 15:50:44 -04:00
2021-06-28 16:16:14 -04:00
[ metadata ]
lock-version = "1.1"
2022-03-02 16:50:04 -05:00
python-versions = "^3.8"
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
content-hash = "f3d61a8c4ca54c580ba8d459aa76a9d956e046c2b8339602497ce53393ba9983"
2021-06-28 16:16:14 -04:00
[ metadata . files ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
ansiwrap = [ ]
anyio = [
{ file = "anyio-3.6.1-py3-none-any.whl" , hash = "sha256:cb29b9c70620506a9a8f87a309591713446953302d7d995344d0d7c6c0c9a7be" } ,
{ file = "anyio-3.6.1.tar.gz" , hash = "sha256:413adf95f93886e442aea925f3ee43baa5a765a64a0f52c6081894f9992fdd0b" } ,
2022-03-30 14:02:06 -04:00
]
2021-06-28 16:16:14 -04:00
appnope = [
2022-04-18 18:12:18 -04:00
{ file = "appnope-0.1.3-py2.py3-none-any.whl" , hash = "sha256:265a455292d0bd8a72453494fa24df5a11eb18373a60c7c0430889f22548605e" } ,
{ file = "appnope-0.1.3.tar.gz" , hash = "sha256:02bd91c4de869fbb1e1c50aafc4098827a7a54ab2f39d9dcba6c9547ed920e24" } ,
2021-06-28 16:16:14 -04:00
]
argon2-cffi = [
2022-02-03 17:05:51 -05:00
{ file = "argon2-cffi-21.3.0.tar.gz" , hash = "sha256:d384164d944190a7dd7ef22c6aa3ff197da12962bd04b17f64d4e93d934dba5b" } ,
{ file = "argon2_cffi-21.3.0-py3-none-any.whl" , hash = "sha256:8c976986f2c5c0e5000919e6de187906cfd81fb1c72bf9d88c01177e77da7f80" } ,
]
argon2-cffi-bindings = [
{ file = "argon2-cffi-bindings-21.2.0.tar.gz" , hash = "sha256:bb89ceffa6c791807d1305ceb77dbfacc5aa499891d2c55661c6459651fc39e3" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-macosx_10_9_x86_64.whl" , hash = "sha256:ccb949252cb2ab3a08c02024acb77cfb179492d5701c7cbdbfd776124d4d2367" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:9524464572e12979364b7d600abf96181d3541da11e23ddf565a32e70bd4dc0d" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:b746dba803a79238e925d9046a63aa26bf86ab2a2fe74ce6b009a1c3f5c8f2ae" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:58ed19212051f49a523abb1dbe954337dc82d947fb6e5a0da60f7c8471a8476c" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_aarch64.whl" , hash = "sha256:bd46088725ef7f58b5a1ef7ca06647ebaf0eb4baff7d1d0d177c6cc8744abd86" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_i686.whl" , hash = "sha256:8cd69c07dd875537a824deec19f978e0f2078fdda07fd5c42ac29668dda5f40f" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_x86_64.whl" , hash = "sha256:f1152ac548bd5b8bcecfb0b0371f082037e47128653df2e8ba6e914d384f3c3e" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-win32.whl" , hash = "sha256:603ca0aba86b1349b147cab91ae970c63118a0f30444d4bc80355937c950c082" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp36-abi3-win_amd64.whl" , hash = "sha256:b2ef1c30440dbbcba7a5dc3e319408b59676e2e039e2ae11a8775ecf482b192f" } ,
{ file = "argon2_cffi_bindings-21.2.0-cp38-abi3-macosx_10_9_universal2.whl" , hash = "sha256:e415e3f62c8d124ee16018e491a009937f8cf7ebf5eb430ffc5de21b900dad93" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl" , hash = "sha256:3e385d1c39c520c08b53d63300c3ecc28622f076f4c2b0e6d7e796e9f6502194" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:2c3e3cc67fdb7d82c4718f19b4e7a87123caf8a93fde7e23cf66ac0337d3cb3f" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:6a22ad9800121b71099d0fb0a65323810a15f2e292f2ba450810a7316e128ee5" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:f9f8b450ed0547e3d473fdc8612083fd08dd2120d6ac8f73828df9b7d45bb351" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-win_amd64.whl" , hash = "sha256:93f9bf70084f97245ba10ee36575f0c3f1e7d7724d67d8e5b08e61787c320ed7" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl" , hash = "sha256:3b9ef65804859d335dc6b31582cad2c5166f0c3e7975f324d9ffaa34ee7e6583" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:d4966ef5848d820776f5f562a7d45fdd70c2f330c961d0d745b784034bd9f48d" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:20ef543a89dee4db46a1a6e206cd015360e5a75822f76df533845c3cbaf72670" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:ed2937d286e2ad0cc79a7087d3c272832865f779430e0cc2b4f3718d3159b0cb" } ,
{ file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-win_amd64.whl" , hash = "sha256:5e00316dabdaea0b2dd82d141cc66889ced0cdcbfa599e8b471cf22c620c329a" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-11 16:34:56 -04:00
astroid = [ ]
atomicwrites = [ ]
attrs = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
babel = [
{ file = "Babel-2.10.3-py3-none-any.whl" , hash = "sha256:ff56f4892c1c4bf0d814575ea23471c230d544203c7748e8c68f0089478d48eb" } ,
{ file = "Babel-2.10.3.tar.gz" , hash = "sha256:7614553711ee97490f732126dc077f8d0ae084ebc6a96e23db1482afabdb2c51" } ,
]
2021-06-28 16:16:14 -04:00
backcall = [
{ file = "backcall-0.2.0-py2.py3-none-any.whl" , hash = "sha256:fbbce6a29f263178a1f7915c1940bde0ec2b2a967566fe1c65c1dfb7422bd255" } ,
{ file = "backcall-0.2.0.tar.gz" , hash = "sha256:5cbdbf27be5e7cfadb448baf0aa95508f91f2bbc6c6437cd9cd06e2a4c215e1e" } ,
]
2022-03-17 23:19:23 -04:00
beautifulsoup4 = [
2022-04-18 18:12:18 -04:00
{ file = "beautifulsoup4-4.11.1-py3-none-any.whl" , hash = "sha256:58d5c3d29f5a36ffeb94f02f0d786cd53014cf9b3b3951d42e0080d8a9498d30" } ,
{ file = "beautifulsoup4-4.11.1.tar.gz" , hash = "sha256:ad9aa55b65ef2808eb405f46cf74df7fcb7044d5cbc26487f96eb2ef2e436693" } ,
2022-03-17 23:19:23 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
black = [ ]
bleach = [
{ file = "bleach-5.0.1-py3-none-any.whl" , hash = "sha256:085f7f33c15bd408dd9b17a4ad77c577db66d76203e5984b1bd59baeee948b2a" } ,
{ file = "bleach-5.0.1.tar.gz" , hash = "sha256:0d03255c47eb9bd2f26aa9bb7f2107732e7e8fe195ca2f64709fcf3b0a4a085c" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
censusdata = [ ]
certifi = [
{ file = "certifi-2022.6.15-py3-none-any.whl" , hash = "sha256:fe86415d55e84719d75f8b69414f6438ac3547d2078ab91b67e779ef69378412" } ,
{ file = "certifi-2022.6.15.tar.gz" , hash = "sha256:84c85a9078b11105f04f3036a9482ae10e4621616db313fe045dd24743a0820d" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-11 16:34:56 -04:00
cffi = [ ]
charset-normalizer = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
click = [ ]
click-plugins = [ ]
2021-07-21 16:10:32 -04:00
cligj = [
{ file = "cligj-0.7.2-py3-none-any.whl" , hash = "sha256:c1ca117dbce1fe20a5809dc96f01e1c2840f6dcc939b3ddbb1111bf330ba82df" } ,
{ file = "cligj-0.7.2.tar.gz" , hash = "sha256:a4bc13d623356b373c2c27c53dbd9c68cae5d526270bfa71f6c6fa69669c6b27" } ,
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
colorama = [
{ file = "colorama-0.4.5-py2.py3-none-any.whl" , hash = "sha256:854bf444933e37f5824ae7bfc1e98d5bce2ebe4160d46b5edf346a89358e99da" } ,
{ file = "colorama-0.4.5.tar.gz" , hash = "sha256:e6c6b4334fc50988a639d9b98aa429a0b57da6e17b9a44f0451f930b6967b7a4" } ,
2021-08-24 15:40:54 -05:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
configparser = [ ]
cycler = [ ]
2022-08-11 16:34:56 -04:00
debugpy = [ ]
2021-06-28 16:16:14 -04:00
decorator = [
2022-02-03 17:05:51 -05:00
{ file = "decorator-5.1.1-py3-none-any.whl" , hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186" } ,
{ file = "decorator-5.1.1.tar.gz" , hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330" } ,
2021-06-28 16:16:14 -04:00
]
defusedxml = [
{ file = "defusedxml-0.7.1-py2.py3-none-any.whl" , hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61" } ,
{ file = "defusedxml-0.7.1.tar.gz" , hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69" } ,
]
2022-08-11 16:34:56 -04:00
dill = [ ]
distlib = [ ]
dparse = [ ]
dynaconf = [ ]
2021-06-28 16:16:14 -04:00
entrypoints = [
2022-02-03 17:05:51 -05:00
{ file = "entrypoints-0.4-py3-none-any.whl" , hash = "sha256:f174b5ff827504fd3cd97cc3f8649f3693f51538c7e4bdf3ef002c8429d42f9f" } ,
{ file = "entrypoints-0.4.tar.gz" , hash = "sha256:b706eddaa9218a19ebcd67b56818f05bb27589b1ca9e8d797b74affad4ccacd4" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
et-xmlfile = [ ]
2022-08-11 16:34:56 -04:00
fastjsonschema = [ ]
filelock = [ ]
2021-07-21 16:10:32 -04:00
fiona = [
2022-03-02 16:50:04 -05:00
{ file = "Fiona-1.8.21-cp310-cp310-macosx_10_10_x86_64.whl" , hash = "sha256:39c656421e25b4d0d73d0b6acdcbf9848e71f3d9b74f44c27d2d516d463409ae" } ,
{ file = "Fiona-1.8.21-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:43b1d2e45506e56cf3a9f59ba5d6f7981f3f75f4725d1e6cb9a33ba856371ebd" } ,
{ file = "Fiona-1.8.21-cp36-cp36m-macosx_10_10_x86_64.whl" , hash = "sha256:315e186cb880a8128e110312eb92f5956bbc54d7152af999d3483b463758d6f9" } ,
{ file = "Fiona-1.8.21-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:9fb2407623c4f44732a33b3f056f8c58c54152b51f0324bf8f10945e711eb549" } ,
{ file = "Fiona-1.8.21-cp37-cp37m-macosx_10_10_x86_64.whl" , hash = "sha256:b69054ed810eb7339d7effa88589afca48003206d7627d0b0b149715fc3fde41" } ,
{ file = "Fiona-1.8.21-cp37-cp37m-manylinux2014_x86_64.whl" , hash = "sha256:11532ccfda1073d3f5f558e4bb78d45b268e8680fd6e14993a394c564ddbd069" } ,
{ file = "Fiona-1.8.21-cp38-cp38-macosx_10_10_x86_64.whl" , hash = "sha256:3789523c811809a6e2e170cf9c437631f959f4c7a868f024081612d30afab468" } ,
{ file = "Fiona-1.8.21-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:085f18d943097ac3396f3f9664ac1ae04ad0ff272f54829f03442187f01b6116" } ,
{ file = "Fiona-1.8.21-cp39-cp39-macosx_10_10_x86_64.whl" , hash = "sha256:388acc9fa07ba7858d508dfe826d4b04d813818bced16c4049de19cc7ca322ef" } ,
{ file = "Fiona-1.8.21-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:40b4eaf5b88407421d6c9e707520abd2ff16d7cd43efb59cd398aa41d2de332c" } ,
{ file = "Fiona-1.8.21.tar.gz" , hash = "sha256:3a0edca2a7a070db405d71187214a43d2333a57b4097544a3fcc282066a58bfc" } ,
2021-07-21 16:10:32 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
flake8 = [ ]
2022-08-11 16:34:56 -04:00
fonttools = [ ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
geopandas = [ ]
2021-06-28 16:16:14 -04:00
idna = [
2021-11-01 18:05:05 -04:00
{ file = "idna-3.3-py3-none-any.whl" , hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff" } ,
{ file = "idna-3.3.tar.gz" , hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d" } ,
2021-06-28 16:16:14 -04:00
]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
importlib-metadata = [ ]
2022-08-11 16:34:56 -04:00
importlib-resources = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
iniconfig = [ ]
ipdb = [ ]
2022-08-11 16:34:56 -04:00
ipykernel = [ ]
ipython = [ ]
2021-06-28 16:16:14 -04:00
ipython-genutils = [
{ file = "ipython_genutils-0.2.0-py2.py3-none-any.whl" , hash = "sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8" } ,
{ file = "ipython_genutils-0.2.0.tar.gz" , hash = "sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8" } ,
]
2022-08-11 16:34:56 -04:00
ipywidgets = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
isort = [ ]
2021-06-28 16:16:14 -04:00
jedi = [
2022-02-03 17:05:51 -05:00
{ file = "jedi-0.18.1-py2.py3-none-any.whl" , hash = "sha256:637c9635fcf47945ceb91cd7f320234a7be540ded6f3e99a50cb6febdfd1ba8d" } ,
{ file = "jedi-0.18.1.tar.gz" , hash = "sha256:74137626a64a99c8eb6ae5832d99b3bdd7d29a3850fe2aa80a4126b2a7d949ab" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
jellyfish = [ ]
jinja2 = [
{ file = "Jinja2-3.1.2-py3-none-any.whl" , hash = "sha256:6088930bfe239f0e6710546ab9c19c9ef35e29792895fed6e6e31a023a182a61" } ,
{ file = "Jinja2-3.1.2.tar.gz" , hash = "sha256:31351a702a408a9e7595a8fc6150fc3f43bb6bf7e319770cbc0db9df9437e852" } ,
2021-08-10 15:28:50 -04:00
]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
json5 = [ ]
2022-08-11 16:34:56 -04:00
jsonschema = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
jupyter = [ ]
jupyter-client = [
{ file = "jupyter_client-7.3.4-py3-none-any.whl" , hash = "sha256:17d74b0d0a7b24f1c8c527b24fcf4607c56bee542ffe8e3418e50b21e514b621" } ,
{ file = "jupyter_client-7.3.4.tar.gz" , hash = "sha256:aa9a6c32054b290374f95f73bb0cae91455c58dfb84f65c8591912b8f65e6d56" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-11 16:34:56 -04:00
jupyter-console = [ ]
jupyter-contrib-core = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
jupyter-contrib-nbextensions = [ ]
2022-08-11 16:34:56 -04:00
jupyter-core = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
jupyter-highlight-selected-word = [ ]
jupyter-latex-envs = [ ]
2022-08-11 16:34:56 -04:00
jupyter-nbextensions-configurator = [ ]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
jupyter-server = [ ]
jupyterlab = [ ]
2021-06-28 16:16:14 -04:00
jupyterlab-pygments = [
2022-04-18 18:12:18 -04:00
{ file = "jupyterlab_pygments-0.2.2-py2.py3-none-any.whl" , hash = "sha256:2405800db07c9f770863bcf8049a529c3dd4d3e28536638bd7c1c01d2748309f" } ,
{ file = "jupyterlab_pygments-0.2.2.tar.gz" , hash = "sha256:7405d7fde60819d905a9fa8ce89e4cd830e318cdad22a0030f7a901da705585d" } ,
2021-06-28 16:16:14 -04:00
]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
jupyterlab-server = [ ]
2022-08-11 16:34:56 -04:00
jupyterlab-widgets = [ ]
kiwisolver = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
lazy-object-proxy = [ ]
liccheck = [ ]
2022-08-11 16:34:56 -04:00
lxml = [ ]
2021-06-28 16:16:14 -04:00
markupsafe = [
2022-03-17 23:19:23 -04:00
{ file = "MarkupSafe-2.1.1-cp310-cp310-macosx_10_9_universal2.whl" , hash = "sha256:86b1f75c4e7c2ac2ccdaec2b9022845dbb81880ca318bb7a0a01fbf7813e3812" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-macosx_10_9_x86_64.whl" , hash = "sha256:f121a1420d4e173a5d96e47e9a0c0dcff965afdf1626d28de1460815f7c4ee7a" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:a49907dd8420c5685cfa064a1335b6754b74541bbb3706c259c02ed65b644b3e" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:10c1bfff05d95783da83491be968e8fe789263689c02724e0c691933c52994f5" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:b7bd98b796e2b6553da7225aeb61f447f80a1ca64f41d83612e6139ca5213aa4" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-musllinux_1_1_aarch64.whl" , hash = "sha256:b09bf97215625a311f669476f44b8b318b075847b49316d3e28c08e41a7a573f" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-musllinux_1_1_i686.whl" , hash = "sha256:694deca8d702d5db21ec83983ce0bb4b26a578e71fbdbd4fdcd387daa90e4d5e" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-musllinux_1_1_x86_64.whl" , hash = "sha256:efc1913fd2ca4f334418481c7e595c00aad186563bbc1ec76067848c7ca0a933" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-win32.whl" , hash = "sha256:4a33dea2b688b3190ee12bd7cfa29d39c9ed176bda40bfa11099a3ce5d3a7ac6" } ,
{ file = "MarkupSafe-2.1.1-cp310-cp310-win_amd64.whl" , hash = "sha256:dda30ba7e87fbbb7eab1ec9f58678558fd9a6b8b853530e176eabd064da81417" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-macosx_10_9_x86_64.whl" , hash = "sha256:671cd1187ed5e62818414afe79ed29da836dde67166a9fac6d435873c44fdd02" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:3799351e2336dc91ea70b034983ee71cf2f9533cdff7c14c90ea126bfd95d65a" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:e72591e9ecd94d7feb70c1cbd7be7b3ebea3f548870aa91e2732960fa4d57a37" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:6fbf47b5d3728c6aea2abb0589b5d30459e369baa772e0f37a0320185e87c980" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-musllinux_1_1_aarch64.whl" , hash = "sha256:d5ee4f386140395a2c818d149221149c54849dfcfcb9f1debfe07a8b8bd63f9a" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-musllinux_1_1_i686.whl" , hash = "sha256:bcb3ed405ed3222f9904899563d6fc492ff75cce56cba05e32eff40e6acbeaa3" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-musllinux_1_1_x86_64.whl" , hash = "sha256:e1c0b87e09fa55a220f058d1d49d3fb8df88fbfab58558f1198e08c1e1de842a" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-win32.whl" , hash = "sha256:8dc1c72a69aa7e082593c4a203dcf94ddb74bb5c8a731e4e1eb68d031e8498ff" } ,
{ file = "MarkupSafe-2.1.1-cp37-cp37m-win_amd64.whl" , hash = "sha256:97a68e6ada378df82bc9f16b800ab77cbf4b2fada0081794318520138c088e4a" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-macosx_10_9_universal2.whl" , hash = "sha256:e8c843bbcda3a2f1e3c2ab25913c80a3c5376cd00c6e8c4a86a89a28c8dc5452" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-macosx_10_9_x86_64.whl" , hash = "sha256:0212a68688482dc52b2d45013df70d169f542b7394fc744c02a57374a4207003" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:8e576a51ad59e4bfaac456023a78f6b5e6e7651dcd383bcc3e18d06f9b55d6d1" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:4b9fe39a2ccc108a4accc2676e77da025ce383c108593d65cc909add5c3bd601" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:96e37a3dc86e80bf81758c152fe66dbf60ed5eca3d26305edf01892257049925" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-musllinux_1_1_aarch64.whl" , hash = "sha256:6d0072fea50feec76a4c418096652f2c3238eaa014b2f94aeb1d56a66b41403f" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-musllinux_1_1_i686.whl" , hash = "sha256:089cf3dbf0cd6c100f02945abeb18484bd1ee57a079aefd52cffd17fba910b88" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-musllinux_1_1_x86_64.whl" , hash = "sha256:6a074d34ee7a5ce3effbc526b7083ec9731bb3cbf921bbe1d3005d4d2bdb3a63" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-win32.whl" , hash = "sha256:421be9fbf0ffe9ffd7a378aafebbf6f4602d564d34be190fc19a193232fd12b1" } ,
{ file = "MarkupSafe-2.1.1-cp38-cp38-win_amd64.whl" , hash = "sha256:fc7b548b17d238737688817ab67deebb30e8073c95749d55538ed473130ec0c7" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-macosx_10_9_universal2.whl" , hash = "sha256:e04e26803c9c3851c931eac40c695602c6295b8d432cbe78609649ad9bd2da8a" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-macosx_10_9_x86_64.whl" , hash = "sha256:b87db4360013327109564f0e591bd2a3b318547bcef31b468a92ee504d07ae4f" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:99a2a507ed3ac881b975a2976d59f38c19386d128e7a9a18b7df6fff1fd4c1d6" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:56442863ed2b06d19c37f94d999035e15ee982988920e12a5b4ba29b62ad1f77" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:3ce11ee3f23f79dbd06fb3d63e2f6af7b12db1d46932fe7bd8afa259a5996603" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-musllinux_1_1_aarch64.whl" , hash = "sha256:33b74d289bd2f5e527beadcaa3f401e0df0a89927c1559c8566c066fa4248ab7" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-musllinux_1_1_i686.whl" , hash = "sha256:43093fb83d8343aac0b1baa75516da6092f58f41200907ef92448ecab8825135" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-musllinux_1_1_x86_64.whl" , hash = "sha256:8e3dcf21f367459434c18e71b2a9532d96547aef8a871872a5bd69a715c15f96" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-win32.whl" , hash = "sha256:d4306c36ca495956b6d568d276ac11fdd9c30a36f1b6eb928070dc5360b22e1c" } ,
{ file = "MarkupSafe-2.1.1-cp39-cp39-win_amd64.whl" , hash = "sha256:46d00d6cfecdde84d40e572d63735ef81423ad31184100411e6e3388d405e247" } ,
{ file = "MarkupSafe-2.1.1.tar.gz" , hash = "sha256:7f91197cc9e48f989d12e4e6fbc46495c446636dfc81b9ccf50bb0ec74b91d4b" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-11 16:34:56 -04:00
marshmallow = [ ]
marshmallow-dataclass = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
marshmallow-enum = [ ]
2022-08-11 16:34:56 -04:00
matplotlib = [ ]
2021-06-28 16:16:14 -04:00
matplotlib-inline = [
2021-09-14 17:28:59 -04:00
{ file = "matplotlib-inline-0.1.3.tar.gz" , hash = "sha256:a04bfba22e0d1395479f866853ec1ee28eea1485c1d69a6faf00dc3e24ff34ee" } ,
{ file = "matplotlib_inline-0.1.3-py3-none-any.whl" , hash = "sha256:aed605ba3b72462d64d475a21a9296f400a19c4f74a31b59103d2a99ffd5aa5c" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
mccabe = [ ]
2021-06-28 16:16:14 -04:00
mistune = [
{ file = "mistune-0.8.4-py2.py3-none-any.whl" , hash = "sha256:88a1051873018da288eee8538d476dffe1262495144b33ecb586c4ab266bb8d4" } ,
{ file = "mistune-0.8.4.tar.gz" , hash = "sha256:59a3429db53c50b5c6bcc8a07f8848cb00d7dc8bdb431a4ab41920d201d4756e" } ,
]
2021-07-21 16:10:32 -04:00
munch = [
{ file = "munch-2.5.0-py2.py3-none-any.whl" , hash = "sha256:6f44af89a2ce4ed04ff8de41f70b226b984db10a91dcc7b9ac2efc1c77022fdd" } ,
{ file = "munch-2.5.0.tar.gz" , hash = "sha256:2d735f6f24d4dba3417fa448cae40c6e896ec1fdab6cdb5e6510999758a4dbd2" } ,
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
mypy = [ ]
2021-06-28 16:16:14 -04:00
mypy-extensions = [
{ file = "mypy_extensions-0.4.3-py2.py3-none-any.whl" , hash = "sha256:090fedd75945a69ae91ce1303b5824f428daf5a028d2f6ab8a299250a846f15d" } ,
{ file = "mypy_extensions-0.4.3.tar.gz" , hash = "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8" } ,
]
2022-03-02 16:50:04 -05:00
nb-black = [
{ file = "nb_black-1.0.7.tar.gz" , hash = "sha256:1ca52e3a46675f6a0a6d79ac73a1f8f951bef60f919eced56173e76ab1b6d62b" } ,
]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
nbclassic = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
nbclient = [
{ file = "nbclient-0.6.6-py3-none-any.whl" , hash = "sha256:09bae4ea2df79fa6bc50aeb8278d8b79d2036792824337fa6eee834afae17312" } ,
{ file = "nbclient-0.6.6.tar.gz" , hash = "sha256:0df76a7961d99a681b4796c74a1f2553b9f998851acc01896dce064ad19a9027" } ,
]
2022-08-11 16:34:56 -04:00
nbconvert = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
nbformat = [
{ file = "nbformat-5.4.0-py3-none-any.whl" , hash = "sha256:0d6072aaec95dddc39735c144ee8bbc6589c383fb462e4058abc855348152dad" } ,
{ file = "nbformat-5.4.0.tar.gz" , hash = "sha256:44ba5ca6acb80c5d5a500f1e5b83ede8cbe364d5a495c4c8cf60aaf1ba656501" } ,
]
2021-06-28 16:16:14 -04:00
nest-asyncio = [
2022-04-18 18:12:18 -04:00
{ file = "nest_asyncio-1.5.5-py3-none-any.whl" , hash = "sha256:b98e3ec1b246135e4642eceffa5a6c23a3ab12c82ff816a92c612d68205813b2" } ,
{ file = "nest_asyncio-1.5.5.tar.gz" , hash = "sha256:e442291cd942698be619823a17a86a5759eabe1f8613084790de189fe9e16d65" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
notebook = [
{ file = "notebook-6.4.12-py3-none-any.whl" , hash = "sha256:8c07a3bb7640e371f8a609bdbb2366a1976c6a2589da8ef917f761a61e3ad8b1" } ,
{ file = "notebook-6.4.12.tar.gz" , hash = "sha256:6268c9ec9048cff7a45405c990c29ac9ca40b0bc3ec29263d218c5e01f2b4e86" } ,
]
notebook-shim = [
{ file = "notebook_shim-0.1.0-py3-none-any.whl" , hash = "sha256:02432d55a01139ac16e2100888aa2b56c614720cec73a27e71f40a5387e45324" } ,
{ file = "notebook_shim-0.1.0.tar.gz" , hash = "sha256:7897e47a36d92248925a2143e3596f19c60597708f7bef50d81fcd31d7263e85" } ,
]
2022-08-11 16:34:56 -04:00
numpy = [ ]
openpyxl = [ ]
2021-06-28 16:16:14 -04:00
packaging = [
2022-02-03 17:05:51 -05:00
{ file = "packaging-21.3-py3-none-any.whl" , hash = "sha256:ef103e05f519cdc783ae24ea4e2e0f508a9c99b2d4969652eed6a2e1ea5bd522" } ,
{ file = "packaging-21.3.tar.gz" , hash = "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pandas = [
{ file = "pandas-1.4.3-cp310-cp310-macosx_10_9_universal2.whl" , hash = "sha256:d51674ed8e2551ef7773820ef5dab9322be0828629f2cbf8d1fc31a0c4fed640" } ,
{ file = "pandas-1.4.3-cp310-cp310-macosx_10_9_x86_64.whl" , hash = "sha256:16ad23db55efcc93fa878f7837267973b61ea85d244fc5ff0ccbcfa5638706c5" } ,
{ file = "pandas-1.4.3-cp310-cp310-macosx_11_0_arm64.whl" , hash = "sha256:958a0588149190c22cdebbc0797e01972950c927a11a900fe6c2296f207b1d6f" } ,
{ file = "pandas-1.4.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:e48fbb64165cda451c06a0f9e4c7a16b534fcabd32546d531b3c240ce2844112" } ,
{ file = "pandas-1.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:6f803320c9da732cc79210d7e8cc5c8019aad512589c910c66529eb1b1818230" } ,
{ file = "pandas-1.4.3-cp310-cp310-win_amd64.whl" , hash = "sha256:2893e923472a5e090c2d5e8db83e8f907364ec048572084c7d10ef93546be6d1" } ,
{ file = "pandas-1.4.3-cp38-cp38-macosx_10_9_universal2.whl" , hash = "sha256:24ea75f47bbd5574675dae21d51779a4948715416413b30614c1e8b480909f81" } ,
{ file = "pandas-1.4.3-cp38-cp38-macosx_10_9_x86_64.whl" , hash = "sha256:d5ebc990bd34f4ac3c73a2724c2dcc9ee7bf1ce6cf08e87bb25c6ad33507e318" } ,
{ file = "pandas-1.4.3-cp38-cp38-macosx_11_0_arm64.whl" , hash = "sha256:d6c0106415ff1a10c326c49bc5dd9ea8b9897a6ca0c8688eb9c30ddec49535ef" } ,
{ file = "pandas-1.4.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:78b00429161ccb0da252229bcda8010b445c4bf924e721265bec5a6e96a92e92" } ,
{ file = "pandas-1.4.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:6dfbf16b1ea4f4d0ee11084d9c026340514d1d30270eaa82a9f1297b6c8ecbf0" } ,
{ file = "pandas-1.4.3-cp38-cp38-win32.whl" , hash = "sha256:48350592665ea3cbcd07efc8c12ff12d89be09cd47231c7925e3b8afada9d50d" } ,
{ file = "pandas-1.4.3-cp38-cp38-win_amd64.whl" , hash = "sha256:605d572126eb4ab2eadf5c59d5d69f0608df2bf7bcad5c5880a47a20a0699e3e" } ,
{ file = "pandas-1.4.3-cp39-cp39-macosx_10_9_universal2.whl" , hash = "sha256:a3924692160e3d847e18702bb048dc38e0e13411d2b503fecb1adf0fcf950ba4" } ,
{ file = "pandas-1.4.3-cp39-cp39-macosx_10_9_x86_64.whl" , hash = "sha256:07238a58d7cbc8a004855ade7b75bbd22c0db4b0ffccc721556bab8a095515f6" } ,
{ file = "pandas-1.4.3-cp39-cp39-macosx_11_0_arm64.whl" , hash = "sha256:755679c49460bd0d2f837ab99f0a26948e68fa0718b7e42afbabd074d945bf84" } ,
{ file = "pandas-1.4.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:41fc406e374590a3d492325b889a2686b31e7a7780bec83db2512988550dadbf" } ,
{ file = "pandas-1.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:1d9382f72a4f0e93909feece6fef5500e838ce1c355a581b3d8f259839f2ea76" } ,
{ file = "pandas-1.4.3-cp39-cp39-win32.whl" , hash = "sha256:0daf876dba6c622154b2e6741f29e87161f844e64f84801554f879d27ba63c0d" } ,
{ file = "pandas-1.4.3-cp39-cp39-win_amd64.whl" , hash = "sha256:721a3dd2f06ef942f83a819c0f3f6a648b2830b191a72bbe9451bcd49c3bd42e" } ,
{ file = "pandas-1.4.3.tar.gz" , hash = "sha256:2ff7788468e75917574f080cd4681b27e1a7bf36461fe968b49a87b5a54d007c" } ,
]
pandas-vet = [ ]
2021-06-28 16:16:14 -04:00
pandocfilters = [
2021-09-14 17:28:59 -04:00
{ file = "pandocfilters-1.5.0-py2.py3-none-any.whl" , hash = "sha256:33aae3f25fd1a026079f5d27bdd52496f0e0803b3469282162bafdcbdf6ef14f" } ,
{ file = "pandocfilters-1.5.0.tar.gz" , hash = "sha256:0b679503337d233b4339a817bfc8c50064e2eff681314376a47cb582305a7a38" } ,
2021-06-28 16:16:14 -04:00
]
Add FUDS ETL (#1817)
* Add spatial join method (#1871)
Since we'll need to figure out the tracts for a large number of points
in future tickets, add a utility to handle grabbing the tract geometries
and adding tract data to a point dataset.
* Add FUDS, also jupyter lab (#1871)
* Add YAML configs for FUDS (#1871)
* Allow input geoid to be optional (#1871)
* Add FUDS ETL, tests, test-datae noteobook (#1871)
This adds the ETL class for Formerly Used Defense Sites (FUDS). This is
different from most other ETLs since these FUDS are not provided by
tract, but instead by geographic point, so we need to assign FUDS to
tracts and then do calculations from there.
* Floats -> Ints, as I intended (#1871)
* Floats -> Ints, as I intended (#1871)
* Formatting fixes (#1871)
* Add test false positive GEOIDs (#1871)
* Add gdal binaries (#1871)
* Refactor pandas code to be more idiomatic (#1871)
Per Emma, the more pandas-y way of doing my counts is using np.where to
add the values i need, then groupby and size. It is definitely more
compact, and also I think more correct!
* Update configs per Emma suggestions (#1871)
* Type fixed! (#1871)
* Remove spurious import from vscode (#1871)
* Snapshot update after changing col name (#1871)
* Move up GDAL (#1871)
* Adjust geojson strategy (#1871)
* Try running census separately first (#1871)
* Fix import order (#1871)
* Cleanup cache strategy (#1871)
* Download census data from S3 instead of re-calculating (#1871)
* Clarify pandas code per Emma (#1871)
2022-08-16 13:28:39 -04:00
papermill = [ ]
2021-06-28 16:16:14 -04:00
parso = [
2022-02-03 17:05:51 -05:00
{ file = "parso-0.8.3-py2.py3-none-any.whl" , hash = "sha256:c001d4636cd3aecdaf33cbb40aebb59b094be2a74c556778ef5576c175e19e75" } ,
{ file = "parso-0.8.3.tar.gz" , hash = "sha256:8c07be290bb59f03588915921e29e8a50002acaf2cdc5fa0e0114f91709fafa0" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pathspec = [ ]
2021-06-28 16:16:14 -04:00
pexpect = [
{ file = "pexpect-4.8.0-py2.py3-none-any.whl" , hash = "sha256:0b48a55dcb3c05f3329815901ea4fc1537514d6ba867a152b581d69ae3710937" } ,
{ file = "pexpect-4.8.0.tar.gz" , hash = "sha256:fc65a43959d153d0114afe13997d439c22823a27cefceb5ff35c2178c6784c0c" } ,
]
pickleshare = [
{ file = "pickleshare-0.7.5-py2.py3-none-any.whl" , hash = "sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56" } ,
{ file = "pickleshare-0.7.5.tar.gz" , hash = "sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca" } ,
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pillow = [ ]
2022-08-11 16:34:56 -04:00
pkgutil-resolve-name = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
platformdirs = [ ]
pluggy = [ ]
2021-06-28 16:16:14 -04:00
prometheus-client = [
2022-04-18 18:12:18 -04:00
{ file = "prometheus_client-0.14.1-py3-none-any.whl" , hash = "sha256:522fded625282822a89e2773452f42df14b5a8e84a86433e3f8a189c1d54dc01" } ,
{ file = "prometheus_client-0.14.1.tar.gz" , hash = "sha256:5459c427624961076277fdc6dc50540e2bacb98eebde99886e59ec55ed92093a" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-11 16:34:56 -04:00
prompt-toolkit = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
psutil = [
{ file = "psutil-5.9.1-cp27-cp27m-manylinux2010_i686.whl" , hash = "sha256:799759d809c31aab5fe4579e50addf84565e71c1dc9f1c31258f159ff70d3f87" } ,
{ file = "psutil-5.9.1-cp27-cp27m-manylinux2010_x86_64.whl" , hash = "sha256:9272167b5f5fbfe16945be3db475b3ce8d792386907e673a209da686176552af" } ,
{ file = "psutil-5.9.1-cp27-cp27m-win32.whl" , hash = "sha256:0904727e0b0a038830b019551cf3204dd48ef5c6868adc776e06e93d615fc5fc" } ,
{ file = "psutil-5.9.1-cp27-cp27m-win_amd64.whl" , hash = "sha256:e7e10454cb1ab62cc6ce776e1c135a64045a11ec4c6d254d3f7689c16eb3efd2" } ,
{ file = "psutil-5.9.1-cp27-cp27mu-manylinux2010_i686.whl" , hash = "sha256:56960b9e8edcca1456f8c86a196f0c3d8e3e361320071c93378d41445ffd28b0" } ,
{ file = "psutil-5.9.1-cp27-cp27mu-manylinux2010_x86_64.whl" , hash = "sha256:44d1826150d49ffd62035785a9e2c56afcea66e55b43b8b630d7706276e87f22" } ,
{ file = "psutil-5.9.1-cp310-cp310-macosx_10_9_x86_64.whl" , hash = "sha256:c7be9d7f5b0d206f0bbc3794b8e16fb7dbc53ec9e40bbe8787c6f2d38efcf6c9" } ,
{ file = "psutil-5.9.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:abd9246e4cdd5b554a2ddd97c157e292ac11ef3e7af25ac56b08b455c829dca8" } ,
{ file = "psutil-5.9.1-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:29a442e25fab1f4d05e2655bb1b8ab6887981838d22effa2396d584b740194de" } ,
{ file = "psutil-5.9.1-cp310-cp310-win32.whl" , hash = "sha256:20b27771b077dcaa0de1de3ad52d22538fe101f9946d6dc7869e6f694f079329" } ,
{ file = "psutil-5.9.1-cp310-cp310-win_amd64.whl" , hash = "sha256:58678bbadae12e0db55186dc58f2888839228ac9f41cc7848853539b70490021" } ,
{ file = "psutil-5.9.1-cp36-cp36m-macosx_10_9_x86_64.whl" , hash = "sha256:3a76ad658641172d9c6e593de6fe248ddde825b5866464c3b2ee26c35da9d237" } ,
{ file = "psutil-5.9.1-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:a6a11e48cb93a5fa606306493f439b4aa7c56cb03fc9ace7f6bfa21aaf07c453" } ,
{ file = "psutil-5.9.1-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:068935df39055bf27a29824b95c801c7a5130f118b806eee663cad28dca97685" } ,
{ file = "psutil-5.9.1-cp36-cp36m-win32.whl" , hash = "sha256:0f15a19a05f39a09327345bc279c1ba4a8cfb0172cc0d3c7f7d16c813b2e7d36" } ,
{ file = "psutil-5.9.1-cp36-cp36m-win_amd64.whl" , hash = "sha256:db417f0865f90bdc07fa30e1aadc69b6f4cad7f86324b02aa842034efe8d8c4d" } ,
{ file = "psutil-5.9.1-cp37-cp37m-macosx_10_9_x86_64.whl" , hash = "sha256:91c7ff2a40c373d0cc9121d54bc5f31c4fa09c346528e6a08d1845bce5771ffc" } ,
{ file = "psutil-5.9.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:fea896b54f3a4ae6f790ac1d017101252c93f6fe075d0e7571543510f11d2676" } ,
{ file = "psutil-5.9.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:3054e923204b8e9c23a55b23b6df73a8089ae1d075cb0bf711d3e9da1724ded4" } ,
{ file = "psutil-5.9.1-cp37-cp37m-win32.whl" , hash = "sha256:d2d006286fbcb60f0b391741f520862e9b69f4019b4d738a2a45728c7e952f1b" } ,
{ file = "psutil-5.9.1-cp37-cp37m-win_amd64.whl" , hash = "sha256:b14ee12da9338f5e5b3a3ef7ca58b3cba30f5b66f7662159762932e6d0b8f680" } ,
{ file = "psutil-5.9.1-cp38-cp38-macosx_10_9_x86_64.whl" , hash = "sha256:19f36c16012ba9cfc742604df189f2f28d2720e23ff7d1e81602dbe066be9fd1" } ,
{ file = "psutil-5.9.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:944c4b4b82dc4a1b805329c980f270f170fdc9945464223f2ec8e57563139cf4" } ,
{ file = "psutil-5.9.1-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:4b6750a73a9c4a4e689490ccb862d53c7b976a2a35c4e1846d049dcc3f17d83b" } ,
{ file = "psutil-5.9.1-cp38-cp38-win32.whl" , hash = "sha256:a8746bfe4e8f659528c5c7e9af5090c5a7d252f32b2e859c584ef7d8efb1e689" } ,
{ file = "psutil-5.9.1-cp38-cp38-win_amd64.whl" , hash = "sha256:79c9108d9aa7fa6fba6e668b61b82facc067a6b81517cab34d07a84aa89f3df0" } ,
{ file = "psutil-5.9.1-cp39-cp39-macosx_10_9_x86_64.whl" , hash = "sha256:28976df6c64ddd6320d281128817f32c29b539a52bdae5e192537bc338a9ec81" } ,
{ file = "psutil-5.9.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:b88f75005586131276634027f4219d06e0561292be8bd6bc7f2f00bdabd63c4e" } ,
{ file = "psutil-5.9.1-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:645bd4f7bb5b8633803e0b6746ff1628724668681a434482546887d22c7a9537" } ,
{ file = "psutil-5.9.1-cp39-cp39-win32.whl" , hash = "sha256:32c52611756096ae91f5d1499fe6c53b86f4a9ada147ee42db4991ba1520e574" } ,
{ file = "psutil-5.9.1-cp39-cp39-win_amd64.whl" , hash = "sha256:f65f9a46d984b8cd9b3750c2bdb419b2996895b005aefa6cbaba9a143b1ce2c5" } ,
{ file = "psutil-5.9.1.tar.gz" , hash = "sha256:57f1819b5d9e95cdfb0c881a8a5b7d542ed0b7c522d575706a80bedc848c8954" } ,
]
2021-06-28 16:16:14 -04:00
ptyprocess = [
{ file = "ptyprocess-0.7.0-py2.py3-none-any.whl" , hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35" } ,
{ file = "ptyprocess-0.7.0.tar.gz" , hash = "sha256:5c5d0a3b48ceee0b48485e0c26037c0acd7d29765ca3fbb5cb3831d347423220" } ,
]
py = [
2022-02-03 17:05:51 -05:00
{ file = "py-1.11.0-py2.py3-none-any.whl" , hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378" } ,
{ file = "py-1.11.0.tar.gz" , hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pycodestyle = [ ]
2021-06-28 16:16:14 -04:00
pycparser = [
2022-02-03 17:05:51 -05:00
{ file = "pycparser-2.21-py2.py3-none-any.whl" , hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9" } ,
{ file = "pycparser-2.21.tar.gz" , hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-11 16:34:56 -04:00
pydantic = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pyflakes = [ ]
2022-08-16 14:44:39 -04:00
pygments = [ ]
2022-08-11 16:34:56 -04:00
pylint = [ ]
pypandoc = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pyparsing = [
{ file = "pyparsing-3.0.9-py3-none-any.whl" , hash = "sha256:5026bae9a10eeaefb61dab2f09052b9f4307d44aee4eda64b309723d8d206bbc" } ,
{ file = "pyparsing-3.0.9.tar.gz" , hash = "sha256:2b020ecf7d21b687f219b71ecad3631f644a47f01403fa1d1036b0c6416d70fb" } ,
]
2021-07-21 16:10:32 -04:00
pyproj = [
2022-04-27 15:59:10 -04:00
{ file = "pyproj-3.3.1-cp310-cp310-macosx_10_9_x86_64.whl" , hash = "sha256:473961faef7a9fd723c5d432f65220ea6ab3854e606bf84b4d409a75a4261c78" } ,
{ file = "pyproj-3.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:2fef9c1e339f25c57f6ae0558b5ab1bbdf7994529a30d8d7504fc6302ea51c03" } ,
{ file = "pyproj-3.3.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:140fa649fedd04f680a39f8ad339799a55cb1c49f6a84e1b32b97e49646647aa" } ,
{ file = "pyproj-3.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:b59c08aea13ee428cf8a919212d55c036cc94784805ed77c8f31a4d1f541058c" } ,
{ file = "pyproj-3.3.1-cp310-cp310-win32.whl" , hash = "sha256:1adc9ccd1bf04998493b6a2e87e60656c75ab790653b36cfe351e9ef214828ed" } ,
{ file = "pyproj-3.3.1-cp310-cp310-win_amd64.whl" , hash = "sha256:42eea10afc750fccd1c5c4ba56de29ab791ab4d83c1f7db72705566282ac5396" } ,
{ file = "pyproj-3.3.1-cp38-cp38-macosx_10_9_x86_64.whl" , hash = "sha256:531ea36519fa7b581466d4b6ab32f66ae4dadd9499d726352f71ee5e19c3d1c5" } ,
{ file = "pyproj-3.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:67025e37598a6bbed2c9c6c9e4c911f6dd39315d3e1148ead935a5c4d64309d5" } ,
{ file = "pyproj-3.3.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:aed1a3c0cd4182425f91b48d5db39f459bc2fe0d88017ead6425a1bc85faee33" } ,
{ file = "pyproj-3.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:3cc4771403db54494e1e55bca8e6d33cde322f8cf0ed39f1557ff109c66d2cd1" } ,
{ file = "pyproj-3.3.1-cp38-cp38-win32.whl" , hash = "sha256:c99f7b5757a28040a2dd4a28c9805fdf13eef79a796f4a566ab5cb362d10630d" } ,
{ file = "pyproj-3.3.1-cp38-cp38-win_amd64.whl" , hash = "sha256:5dac03d4338a4c8bd0f69144c527474f517b4cbd7d2d8c532cd8937799723248" } ,
{ file = "pyproj-3.3.1-cp39-cp39-macosx_10_9_x86_64.whl" , hash = "sha256:56b0f9ee2c5b2520b18db30a393a7b86130cf527ddbb8c96e7f3c837474a9d79" } ,
{ file = "pyproj-3.3.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:5f92d8f6514516124abb714dce912b20867831162cfff9fae2678ef07b6fcf0f" } ,
{ file = "pyproj-3.3.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:1ef1bfbe2dcc558c7a98e2f1836abdcd630390f3160724a6f4f5c818b2be0ad5" } ,
{ file = "pyproj-3.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:5ca5f32b56210429b367ca4f9a57ffe67975c487af82e179a24370879a3daf68" } ,
{ file = "pyproj-3.3.1-cp39-cp39-win32.whl" , hash = "sha256:aba199704c824fb84ab64927e7bc9ef71e603e483130ec0f7e09e97259b8f61f" } ,
{ file = "pyproj-3.3.1-cp39-cp39-win_amd64.whl" , hash = "sha256:120d45ed73144c65e9677dc73ba8a531c495d179dd9f9f0471ac5acc02d7ac4b" } ,
{ file = "pyproj-3.3.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl" , hash = "sha256:52efb681647dfac185cc655a709bc0caaf910031a0390f816f5fc8ce150cbedc" } ,
{ file = "pyproj-3.3.1-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:5ab0d6e38fda7c13726afacaf62e9f9dd858089d67910471758afd9cb24e0ecd" } ,
{ file = "pyproj-3.3.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:45487942c19c5a8b09c91964ea3201f4e094518e34743cae373889a36e3d9260" } ,
{ file = "pyproj-3.3.1-pp38-pypy38_pp73-win_amd64.whl" , hash = "sha256:797ad5655d484feac14b0fbb4a4efeaac0cf780a223046e2465494c767fd1c3b" } ,
{ file = "pyproj-3.3.1.tar.gz" , hash = "sha256:b3d8e14d91cc95fb3dbc03a9d0588ac58326803eefa5bbb0978d109de3304fbe" } ,
2021-07-21 16:10:32 -04:00
]
2021-06-28 16:16:14 -04:00
pyrsistent = [
2022-02-03 17:05:51 -05:00
{ file = "pyrsistent-0.18.1-cp310-cp310-macosx_10_9_universal2.whl" , hash = "sha256:df46c854f490f81210870e509818b729db4488e1f30f2a1ce1698b2295a878d1" } ,
{ file = "pyrsistent-0.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:5d45866ececf4a5fff8742c25722da6d4c9e180daa7b405dc0a2a2790d668c26" } ,
{ file = "pyrsistent-0.18.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:4ed6784ceac462a7d6fcb7e9b663e93b9a6fb373b7f43594f9ff68875788e01e" } ,
{ file = "pyrsistent-0.18.1-cp310-cp310-win32.whl" , hash = "sha256:e4f3149fd5eb9b285d6bfb54d2e5173f6a116fe19172686797c056672689daf6" } ,
{ file = "pyrsistent-0.18.1-cp310-cp310-win_amd64.whl" , hash = "sha256:636ce2dc235046ccd3d8c56a7ad54e99d5c1cd0ef07d9ae847306c91d11b5fec" } ,
{ file = "pyrsistent-0.18.1-cp37-cp37m-macosx_10_9_x86_64.whl" , hash = "sha256:e92a52c166426efbe0d1ec1332ee9119b6d32fc1f0bbfd55d5c1088070e7fc1b" } ,
{ file = "pyrsistent-0.18.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:d7a096646eab884bf8bed965bad63ea327e0d0c38989fc83c5ea7b8a87037bfc" } ,
{ file = "pyrsistent-0.18.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:cdfd2c361b8a8e5d9499b9082b501c452ade8bbf42aef97ea04854f4a3f43b22" } ,
{ file = "pyrsistent-0.18.1-cp37-cp37m-win32.whl" , hash = "sha256:7ec335fc998faa4febe75cc5268a9eac0478b3f681602c1f27befaf2a1abe1d8" } ,
{ file = "pyrsistent-0.18.1-cp37-cp37m-win_amd64.whl" , hash = "sha256:6455fc599df93d1f60e1c5c4fe471499f08d190d57eca040c0ea182301321286" } ,
{ file = "pyrsistent-0.18.1-cp38-cp38-macosx_10_9_universal2.whl" , hash = "sha256:fd8da6d0124efa2f67d86fa70c851022f87c98e205f0594e1fae044e7119a5a6" } ,
{ file = "pyrsistent-0.18.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:7bfe2388663fd18bd8ce7db2c91c7400bf3e1a9e8bd7d63bf7e77d39051b85ec" } ,
{ file = "pyrsistent-0.18.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:0e3e1fcc45199df76053026a51cc59ab2ea3fc7c094c6627e93b7b44cdae2c8c" } ,
{ file = "pyrsistent-0.18.1-cp38-cp38-win32.whl" , hash = "sha256:b568f35ad53a7b07ed9b1b2bae09eb15cdd671a5ba5d2c66caee40dbf91c68ca" } ,
{ file = "pyrsistent-0.18.1-cp38-cp38-win_amd64.whl" , hash = "sha256:d1b96547410f76078eaf66d282ddca2e4baae8964364abb4f4dcdde855cd123a" } ,
{ file = "pyrsistent-0.18.1-cp39-cp39-macosx_10_9_universal2.whl" , hash = "sha256:f87cc2863ef33c709e237d4b5f4502a62a00fab450c9e020892e8e2ede5847f5" } ,
{ file = "pyrsistent-0.18.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:6bc66318fb7ee012071b2792024564973ecc80e9522842eb4e17743604b5e045" } ,
{ file = "pyrsistent-0.18.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:914474c9f1d93080338ace89cb2acee74f4f666fb0424896fcfb8d86058bf17c" } ,
{ file = "pyrsistent-0.18.1-cp39-cp39-win32.whl" , hash = "sha256:1b34eedd6812bf4d33814fca1b66005805d3640ce53140ab8bbb1e2651b0d9bc" } ,
{ file = "pyrsistent-0.18.1-cp39-cp39-win_amd64.whl" , hash = "sha256:e24a828f57e0c337c8d8bb9f6b12f09dfdf0273da25fda9e314f0b684b415a07" } ,
{ file = "pyrsistent-0.18.1.tar.gz" , hash = "sha256:d4d61f8b993a7255ba714df3aca52700f8125289f84f704cf80916517c46eb96" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pytest = [ ]
2022-08-11 16:34:56 -04:00
pytest-mock = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pytest-snapshot = [ ]
2021-06-28 16:16:14 -04:00
python-dateutil = [
2021-07-21 16:10:32 -04:00
{ file = "python-dateutil-2.8.2.tar.gz" , hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86" } ,
{ file = "python_dateutil-2.8.2-py2.py3-none-any.whl" , hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9" } ,
2021-06-28 16:16:14 -04:00
]
2022-08-16 14:44:39 -04:00
pytz = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pywin32 = [
{ file = "pywin32-304-cp310-cp310-win32.whl" , hash = "sha256:3c7bacf5e24298c86314f03fa20e16558a4e4138fc34615d7de4070c23e65af3" } ,
{ file = "pywin32-304-cp310-cp310-win_amd64.whl" , hash = "sha256:4f32145913a2447736dad62495199a8e280a77a0ca662daa2332acf849f0be48" } ,
{ file = "pywin32-304-cp310-cp310-win_arm64.whl" , hash = "sha256:d3ee45adff48e0551d1aa60d2ec066fec006083b791f5c3527c40cd8aefac71f" } ,
{ file = "pywin32-304-cp311-cp311-win32.whl" , hash = "sha256:30c53d6ce44c12a316a06c153ea74152d3b1342610f1b99d40ba2795e5af0269" } ,
{ file = "pywin32-304-cp311-cp311-win_amd64.whl" , hash = "sha256:7ffa0c0fa4ae4077e8b8aa73800540ef8c24530057768c3ac57c609f99a14fd4" } ,
{ file = "pywin32-304-cp311-cp311-win_arm64.whl" , hash = "sha256:cbbe34dad39bdbaa2889a424d28752f1b4971939b14b1bb48cbf0182a3bcfc43" } ,
{ file = "pywin32-304-cp36-cp36m-win32.whl" , hash = "sha256:be253e7b14bc601718f014d2832e4c18a5b023cbe72db826da63df76b77507a1" } ,
{ file = "pywin32-304-cp36-cp36m-win_amd64.whl" , hash = "sha256:de9827c23321dcf43d2f288f09f3b6d772fee11e809015bdae9e69fe13213988" } ,
{ file = "pywin32-304-cp37-cp37m-win32.whl" , hash = "sha256:f64c0377cf01b61bd5e76c25e1480ca8ab3b73f0c4add50538d332afdf8f69c5" } ,
{ file = "pywin32-304-cp37-cp37m-win_amd64.whl" , hash = "sha256:bb2ea2aa81e96eee6a6b79d87e1d1648d3f8b87f9a64499e0b92b30d141e76df" } ,
{ file = "pywin32-304-cp38-cp38-win32.whl" , hash = "sha256:94037b5259701988954931333aafd39cf897e990852115656b014ce72e052e96" } ,
{ file = "pywin32-304-cp38-cp38-win_amd64.whl" , hash = "sha256:ead865a2e179b30fb717831f73cf4373401fc62fbc3455a0889a7ddac848f83e" } ,
{ file = "pywin32-304-cp39-cp39-win32.whl" , hash = "sha256:25746d841201fd9f96b648a248f731c1dec851c9a08b8e33da8b56148e4c65cc" } ,
{ file = "pywin32-304-cp39-cp39-win_amd64.whl" , hash = "sha256:d24a3382f013b21aa24a5cfbfad5a2cd9926610c0affde3e8ab5b3d7dbcf4ac9" } ,
2022-08-16 14:44:39 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
pywinpty = [ ]
pyyaml = [ ]
2022-08-16 14:44:39 -04:00
pyzmq = [ ]
2022-08-11 16:34:56 -04:00
qtconsole = [ ]
qtpy = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
requests = [
{ file = "requests-2.28.1-py3-none-any.whl" , hash = "sha256:8fefa2a1a1365bf5520aac41836fbee479da67864514bdb821f31ce07ce65349" } ,
{ file = "requests-2.28.1.tar.gz" , hash = "sha256:7c5599b102feddaa661c826c56ab4fee28bfd17f5abca1ebbe3e7f19d7c97983" } ,
]
rtree = [
{ file = "Rtree-1.0.0-cp310-cp310-macosx_10_9_x86_64.whl" , hash = "sha256:757bbf9ca38c241e34812a646f16ffda2cabd535bcd815041b83fe091df7a85c" } ,
{ file = "Rtree-1.0.0-cp310-cp310-macosx_11_0_arm64.whl" , hash = "sha256:fe3954a51d691d3938cbac42ac97f4acacbea8ea622a375df901318a5c4ab0e9" } ,
{ file = "Rtree-1.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl" , hash = "sha256:24185f39b277aaca0566284858de02edc80dc7b120233be38fcf3b4c7d2e72dc" } ,
{ file = "Rtree-1.0.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:b2110fb8675bf809bba431a1876ba76ca5dde829a4de40aa7851941452a01278" } ,
{ file = "Rtree-1.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:b0256ed9c27037892bcb7167e7f5c469ee7c5de38c5a895145e33c320584babe" } ,
{ file = "Rtree-1.0.0-cp310-cp310-musllinux_1_1_aarch64.whl" , hash = "sha256:7f2c0bd3e7d4b68cc27ab605b18487440427d5febba5f4b747b694f9de601c6f" } ,
{ file = "Rtree-1.0.0-cp310-cp310-musllinux_1_1_i686.whl" , hash = "sha256:c2b14f7603576b73a5e0fd2e35394db08c5ca3cfa41e4c8530128d91e5e43dd3" } ,
{ file = "Rtree-1.0.0-cp310-cp310-musllinux_1_1_x86_64.whl" , hash = "sha256:973ce22ee8bafa44b3df24c6bf78012e534e1f36103e0bbfbb193ec48e9be22a" } ,
{ file = "Rtree-1.0.0-cp310-cp310-win_amd64.whl" , hash = "sha256:55b771e62b1e391a44776ef9f906944796213cc3cb48ffd6b22493684c68a859" } ,
{ file = "Rtree-1.0.0-cp37-cp37m-macosx_10_9_x86_64.whl" , hash = "sha256:0475b2e7fe813c427ceb21e57c22f8b4b7fee6e5966db8a200688163d4853f14" } ,
{ file = "Rtree-1.0.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:e436d8da7527655fd0512dd6a5218f604a3806849f3981ec0ca64930dc19b7f2" } ,
{ file = "Rtree-1.0.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:8d18efe4e69f6b7daee9aaced21e0218786209d55235c909c78dbc5c12368790" } ,
{ file = "Rtree-1.0.0-cp37-cp37m-musllinux_1_1_i686.whl" , hash = "sha256:728cf9b774ed6f120f2ed072082431c14af8243d477656b5b7dc1ff855fe7786" } ,
{ file = "Rtree-1.0.0-cp37-cp37m-musllinux_1_1_x86_64.whl" , hash = "sha256:3e28303d84f8b5509e26db7c2aa533692a6112a430cc955a7a7e6d899c9d5996" } ,
{ file = "Rtree-1.0.0-cp37-cp37m-win_amd64.whl" , hash = "sha256:062439d3a33d95281445960af76b6189b987cda0803fdc1818e31b68bce989d1" } ,
{ file = "Rtree-1.0.0-cp38-cp38-macosx_10_9_x86_64.whl" , hash = "sha256:0ab0dccff665389329f8d2e623131a1af3ab82b6de570f8c494a429c129f3e65" } ,
{ file = "Rtree-1.0.0-cp38-cp38-macosx_11_0_arm64.whl" , hash = "sha256:44df5adc12841b94adcbc4e5aaada248e98a4dc2017c8c7060f9a782ef63e050" } ,
{ file = "Rtree-1.0.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:29a1a4452e334eaf3299c8b95f137a2ccafbccfd856041f612ec933eeafb2cf5" } ,
{ file = "Rtree-1.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:efdaf7137303af7a85ddd224bacdb27f9f7ece99e0dec627c900e12f22cdefd0" } ,
{ file = "Rtree-1.0.0-cp38-cp38-musllinux_1_1_i686.whl" , hash = "sha256:264e3b255a1fc6aaa2ddbcedfc15ac40578433f6b35a0c7aaba026215d91d8c3" } ,
{ file = "Rtree-1.0.0-cp38-cp38-musllinux_1_1_x86_64.whl" , hash = "sha256:26b2275ebc738cb6a0473c15d80fdfe820ef319015009f8f0789e586552cf411" } ,
{ file = "Rtree-1.0.0-cp38-cp38-win_amd64.whl" , hash = "sha256:825c1f74a84e9857657c04503c4c50b9f170114183fa2db9211a5d8650cf1ffa" } ,
{ file = "Rtree-1.0.0-cp39-cp39-macosx_10_9_x86_64.whl" , hash = "sha256:a91d7b514210ae93029c2a7ed83b2595ca73de5e08a9d87fcdf3a784a7b3ef54" } ,
{ file = "Rtree-1.0.0-cp39-cp39-macosx_11_0_arm64.whl" , hash = "sha256:0ffaa03d1f7e8291de7cd8a11f92e10579f145dc3a08cd46a9eea65cc7b42173" } ,
{ file = "Rtree-1.0.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl" , hash = "sha256:4f2f93c997de551a1a0fa4065e713270ad9a509aeeb143c5b46f332c0759f314" } ,
{ file = "Rtree-1.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl" , hash = "sha256:a48f46dbb6ab0cb135a43d90529e1fa09a6dd80149a34844f2adf8414b4ab71a" } ,
{ file = "Rtree-1.0.0-cp39-cp39-musllinux_1_1_i686.whl" , hash = "sha256:171aa361b3542bf1e47bdee54c611644bb33d35502e2ceea57ac89cf35330554" } ,
{ file = "Rtree-1.0.0-cp39-cp39-musllinux_1_1_x86_64.whl" , hash = "sha256:bc18d4df3edb3b889b177ba39238770afdb5787fb803677c3aadea42a6931485" } ,
{ file = "Rtree-1.0.0-cp39-cp39-win_amd64.whl" , hash = "sha256:bc6e7384684a260eb2f04fcac64ca5ffe28876132a11d1a883db2a5db8becb64" } ,
{ file = "Rtree-1.0.0.tar.gz" , hash = "sha256:d0483482121346b093b9a42518d40f921adf445915b7aea307eb26768c839682" } ,
]
safety = [ ]
scipy = [ ]
seaborn = [ ]
2022-08-11 16:34:56 -04:00
semantic-version = [ ]
2021-06-28 16:16:14 -04:00
send2trash = [
2021-08-10 15:28:50 -04:00
{ file = "Send2Trash-1.8.0-py3-none-any.whl" , hash = "sha256:f20eaadfdb517eaca5ce077640cb261c7d2698385a6a0f072a4a5447fd49fa08" } ,
{ file = "Send2Trash-1.8.0.tar.gz" , hash = "sha256:d2c24762fd3759860a0aff155e45871447ea58d2be6bdd39b5c8f966a0c99c2d" } ,
2021-06-28 16:16:14 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
setuptools-scm = [ ]
2022-08-11 16:34:56 -04:00
shapely = [ ]
2021-06-28 16:16:14 -04:00
six = [
{ file = "six-1.16.0-py2.py3-none-any.whl" , hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254" } ,
{ file = "six-1.16.0.tar.gz" , hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926" } ,
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
sniffio = [
{ file = "sniffio-1.2.0-py3-none-any.whl" , hash = "sha256:471b71698eac1c2112a40ce2752bb2f4a4814c22a54a3eed3676bc0f5ca9f663" } ,
{ file = "sniffio-1.2.0.tar.gz" , hash = "sha256:c4666eecec1d3f50960c6bdf61ab7bc350648da6c126e3cf6898d8cd4ddcd3de" } ,
]
2022-03-17 23:19:23 -04:00
soupsieve = [
2022-04-18 18:12:18 -04:00
{ file = "soupsieve-2.3.2.post1-py3-none-any.whl" , hash = "sha256:3b2503d3c7084a42b1ebd08116e5f81aadfaea95863628c80a3b774a11b7c759" } ,
{ file = "soupsieve-2.3.2.post1.tar.gz" , hash = "sha256:fc53893b3da2c33de295667a0e19f078c14bf86544af307354de5fcf12a3f30d" } ,
2022-03-17 23:19:23 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
tenacity = [ ]
terminado = [
{ file = "terminado-0.15.0-py3-none-any.whl" , hash = "sha256:0d5f126fbfdb5887b25ae7d9d07b0d716b1cc0ccaacc71c1f3c14d228e065197" } ,
{ file = "terminado-0.15.0.tar.gz" , hash = "sha256:ab4eeedccfcc1e6134bfee86106af90852c69d602884ea3a1e8ca6d4486e9bfe" } ,
2022-03-30 14:02:06 -04:00
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
textwrap3 = [ ]
2022-04-18 18:12:18 -04:00
tinycss2 = [
{ file = "tinycss2-1.1.1-py3-none-any.whl" , hash = "sha256:fe794ceaadfe3cf3e686b22155d0da5780dd0e273471a51846d0a02bc204fec8" } ,
{ file = "tinycss2-1.1.1.tar.gz" , hash = "sha256:b2e44dd8883c360c35dd0d1b5aad0b610e5156c2cb3b33434634e539ead9d8bf" } ,
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
toml = [ ]
tomli = [ ]
2022-08-11 16:34:56 -04:00
tomlkit = [ ]
tornado = [ ]
tox = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
tox-poetry = [ ]
tqdm = [ ]
traitlets = [
{ file = "traitlets-5.3.0-py3-none-any.whl" , hash = "sha256:65fa18961659635933100db8ca120ef6220555286949774b9cfc106f941d1c7a" } ,
{ file = "traitlets-5.3.0.tar.gz" , hash = "sha256:0bb9f1f9f017aa8ec187d8b1b2a7a6626a2a1d877116baba52a129bfa124f8e2" } ,
2022-08-16 14:44:39 -04:00
]
2022-08-11 16:34:56 -04:00
types-requests = [ ]
types-urllib3 = [ ]
typing-extensions = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
typing-inspect = [ ]
2022-08-11 16:34:56 -04:00
urllib3 = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
us = [ ]
2022-08-11 16:34:56 -04:00
virtualenv = [ ]
2021-06-28 16:16:14 -04:00
wcwidth = [
{ file = "wcwidth-0.2.5-py2.py3-none-any.whl" , hash = "sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784" } ,
{ file = "wcwidth-0.2.5.tar.gz" , hash = "sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83" } ,
]
webencodings = [
{ file = "webencodings-0.5.1-py2.py3-none-any.whl" , hash = "sha256:a0af1213f3c2226497a97e2b3aa01a7e4bee4f403f95be16fc9acd2947514a78" } ,
{ file = "webencodings-0.5.1.tar.gz" , hash = "sha256:b36a1c245f2d304965eb4e0a82848379241dc04b865afcc4aab16748587e1923" } ,
]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
websocket-client = [
{ file = "websocket-client-1.3.3.tar.gz" , hash = "sha256:d58c5f284d6a9bf8379dab423259fe8f85b70d5fa5d2916d5791a84594b122b1" } ,
{ file = "websocket_client-1.3.3-py3-none-any.whl" , hash = "sha256:5d55652dc1d0b3c734f044337d929aaf83f4f9138816ec680c1aefefb4dc4877" } ,
]
2022-08-11 16:34:56 -04:00
widgetsnbextension = [ ]
wrapt = [ ]
Pipeline tile tests (#1864)
* temp update
* updating with fips check
* adding check on pfs
* updating with pfs test
* Update test_tiles_smoketests.py
* Fix lint errors (#1848)
* Add column names test (#1848)
* Mark tests as smoketests (#1848)
* Move to other score-related tests (#1848)
* Recast Total threshold criteria exceeded to int (#1848)
In writing tests to verify the output of the tiles csv matches the final
score CSV, I noticed TC/Total threshold criteria exceeded was getting
cast from an int64 to a float64 in the process of PostScoreETL. I
tracked it down to the line where we merge the score dataframe with
constants.DATA_CENSUS_CSV_FILE_PATH --- there where > 100 tracts in the
national census CSV that don't exist in the score, so those ended up
with a Total threshhold count of np.nan, which is a float, and thereby
cast those columns to float. For the moment I just cast it back.
* No need for low memeory (#1848)
* Add additional tests of tiles.csv (#1848)
* Drop pre-2010 rows before computing score (#1848)
Note this is probably NOT the optimal place for this change; it might
make more sense for each source to filter its own tracts down to the
acceptable tract list. However, that would be a pretty invasive change,
where this is central and plenty of other things are happening in score
transform that could be moved to sources, so for today, here's where the
change will live.
* Fix typo (#1848)
* Switch from filter to inner join (#1848)
* Remove no-op lines from tiles (#1848)
* Apply feedback from review, linter (#1848)
* Check the values oeverything in the frame (#1848)
* Refactor checker class (#1848)
* Add test for state names (#1848)
* cleanup from reviewing my own code (#1848)
* Fix lint error (#1858)
* Apply Emma's feedback from review (#1848)
* Remove refs to national_df (#1848)
* Account for new, fake nullable bools in tiles (#1848)
To handle a geojson limitation, Emma converted some nullable boolean
colunms to float64 in the tiles export with the values {0.0, 1.0, nan},
giving us the same expressiveness. Sadly, this broke my assumption that
all columns between the score and tiles csvs would have the same dtypes,
so I need to account for these new, fake bools in my test.
* Use equals instead of my worse version (#1848)
* Missed a spot where we called _create_score_data (#1848)
* Update per safety (#1848)
Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>
2022-09-01 13:07:14 -04:00
xlsxwriter = [ ]
2022-08-11 16:34:56 -04:00
zipp = [ ]