publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-08-03 02:14:18 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Issue 308 python linting (#443)

Browse source 
* Adds flake8, pylint, liccheck, flake8 to dependencies for data-pipeline

* Sets up and runs black autoformatting

* Adds flake8 to tox linting

* Fixes flake8 error F541 f string missing placeholders

* Fixes flake8 E501 line too long

* Fixes flake8 F401 imported but not used

* Adds pylint to tox and disables the following pylint errors:
- C0114: module docstrings
- R0201: method could have been a function
- R0903: too few public methods
- C0103: name case styling
- W0511: fix me
- W1203: f-string interpolation in logging

* Adds utils.py to tox.ini linting, runs black on utils.py

* Fixes import related pylint errors: C0411 and C0412

* Fixes or ignores remaining pylint errors (for discussion later)

* Adds safety and liccheck to tox.ini
This commit is contained in:
Billy Daly 2021-08-02 12:16:38 -04:00 • committed by GitHub
commit 5504528fdf
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
22 changed files with 709 additions and 228 deletions
Download patch file Download diff file Expand all files Collapse all files

11
data/data-pipeline/etl/sources/hud_recap/etl.py
View file

@ -9,7 +9,8 @@ logger = get_module_logger(__name__)
class HudRecapETL(ExtractTransformLoad):
def __init__(self):
self.HUD_RECAP_CSV_URL = "https://opendata.arcgis.com/api/v3/datasets/56de4edea8264fe5a344da9811ef5d6e_0/downloads/data?format=csv&spatialRefId=4326"
# pylint: disable=line-too-long
self.HUD_RECAP_CSV_URL = "https://opendata.arcgis.com/api/v3/datasets/56de4edea8264fe5a344da9811ef5d6e_0/downloads/data?format=csv&spatialRefId=4326" # noqa: E501
self.HUD_RECAP_CSV = (
self.TMP_PATH
/ "Racially_or_Ethnically_Concentrated_Areas_of_Poverty__R_ECAPs_.csv"
@ -22,7 +23,7 @@ class HudRecapETL(ExtractTransformLoad):
self.df: pd.DataFrame
def extract(self) -> None:
logger.info(f"Downloading HUD Recap Data")
logger.info("Downloading HUD Recap Data")
download = requests.get(self.HUD_RECAP_CSV_URL, verify=None)
file_contents = download.content
csv_file = open(self.HUD_RECAP_CSV, "wb")
@ -30,7 +31,7 @@ class HudRecapETL(ExtractTransformLoad):
csv_file.close()
def transform(self) -> None:
logger.info(f"Transforming HUD Recap Data")
logger.info("Transforming HUD Recap Data")
# Load comparison index (CalEnviroScreen 4)
self.df = pd.read_csv(self.HUD_RECAP_CSV, dtype={"GEOID": "string"})
@ -57,7 +58,7 @@ class HudRecapETL(ExtractTransformLoad):
self.df.sort_values(by=self.GEOID_TRACT_FIELD_NAME, inplace=True)
def load(self) -> None:
logger.info(f"Saving HUD Recap CSV")
logger.info("Saving HUD Recap CSV")
# write nationwide csv
self.CSV_PATH.mkdir(parents=True, exist_ok=True)
self.df.to_csv(self.CSV_PATH / f"usa.csv", index=False)
self.df.to_csv(self.CSV_PATH / "usa.csv", index=False)