Merge branch 'main' into justice40-tool-iss-719

2025-02-23 01:54:18 -08:00 · 2021-09-22 15:00:13 -04:00 · 2021-09-22 15:00:13 -04:00 · 28600d3e03
commit 28600d3e03
parent a5652e65d2 d1ced6d584
18 changed files with 115 additions and 67 deletions
--- a/data/data-pipeline/README.md
+++ b/data/data-pipeline/README.md
@ -283,7 +283,7 @@ In a bit more detail:
 If you update the input our output to various methods, it is necessary to create new pickles so that data is validated correctly. To do this:

 1. Drop a breakpoint just before the dataframe will otherwise be written to / read from disk. If you're using VSCode, use one of the named run targets within `data-pipeline` such as `Score Full Run` , and put a breakpoint in the margin just before the actionable step. More on using breakpoints in VSCode [here](https://code.visualstudio.com/docs/editor/debugging#_breakpoints). If you are not using VSCode, you can put the line `breakpoint()` in your code and it will stop where you have placed the line in whatever calling context you are using.
-1. In your editor/terminal, run `df.to_pickle("data_pipeline/etl/score/tests/snapshots/YOUR_OUT_PATH_HERE.pkl")` to write the pickle to the appropriate location on disk.
+1. In your editor/terminal, run `df.to_pickle("data_pipeline/etl/score/tests/snapshots/YOUR_OUT_PATH_HERE.pkl", protocol=4)` to write the pickle to the appropriate location on disk.
 1. Be sure to do this for all inputs/outputs that have changed as a result of your modification. It is often necessary to do this several times for cascading operations.
 1. To inspect your pickle, open a python interpreter, then run `pickle.load( open( "data_pipeline/etl/score/tests/snapshots/YOUR_OUT_PATH_HERE.pkl", "rb" ) )` to get file contents.

--- a/data/data-pipeline/data_pipeline/etl/base.py
+++ b/data/data-pipeline/data_pipeline/etl/base.py
@ -19,6 +19,7 @@ class ExtractTransformLoad:

    DATA_PATH: Path = settings.APP_ROOT / "data"
    TMP_PATH: Path = DATA_PATH / "tmp"
+    FILES_PATH: Path = settings.APP_ROOT / "files"
    GEOID_FIELD_NAME: str = "GEOID10"
    GEOID_TRACT_FIELD_NAME: str = "GEOID10_TRACT"
    # TODO: investigate. Census says there are only 217,740 CBGs in the US.
--- a/data/data-pipeline/data_pipeline/etl/score/constants.py
+++ b/data/data-pipeline/data_pipeline/etl/score/constants.py
@ -43,7 +43,8 @@ DATA_SCORE_TILES_DIR = DATA_SCORE_DIR / "tiles"
 SCORE_DOWNLOADABLE_DIR = DATA_SCORE_DIR / "downloadable"
 SCORE_DOWNLOADABLE_CSV_FILE_PATH = SCORE_DOWNLOADABLE_DIR / "usa.csv"
 SCORE_DOWNLOADABLE_EXCEL_FILE_PATH = SCORE_DOWNLOADABLE_DIR / "usa.xlsx"
-SCORE_DOWNLOADABLE_PDF_FILE_PATH = FILES_PATH / "Draft_Communities_List.pdf"
+SCORE_DOWNLOADABLE_PDF_FILE_NAME = "Draft_Communities_List.pdf"
+SCORE_DOWNLOADABLE_PDF_FILE_PATH = FILES_PATH / SCORE_DOWNLOADABLE_PDF_FILE_NAME
 SCORE_DOWNLOADABLE_ZIP_FILE_PATH = (
    SCORE_DOWNLOADABLE_DIR / "Screening_Tool_Data.zip"
 )
--- a/data/data-pipeline/data_pipeline/etl/score/tests/conftest.py
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/conftest.py
@ -41,6 +41,7 @@ def etl(monkeypatch, root):
    etl = PostScoreETL()
    monkeypatch.setattr(etl, "DATA_PATH", root)
    monkeypatch.setattr(etl, "TMP_PATH", tmp_path)
+
    return etl


@ -65,6 +66,11 @@ def score_data_initial(sample_data_dir):
    return sample_data_dir / "score_data_initial.csv"


+@pytest.fixture()
+def score_pdf_initial(sample_data_dir):
+    return sample_data_dir / "Draft_Communities_List.pdf"
+
+
@pytest.fixture()
 def counties_transformed_expected():
    return pd.DataFrame.from_dict(
--- a/data/data-pipeline/data_pipeline/etl/score/tests/sample_data/score_data_initial.csv
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/sample_data/score_data_initial.csv
--- a/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/downloadable_data_expected.pkl
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/downloadable_data_expected.pkl
--- a/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/score_data_expected.pkl
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/score_data_expected.pkl
--- a/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/score_transformed_expected.pkl
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/score_transformed_expected.pkl
--- a/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/tile_data_expected.pkl
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/snapshots/tile_data_expected.pkl
--- a/data/data-pipeline/data_pipeline/etl/score/tests/test_score_post.py
+++ b/data/data-pipeline/data_pipeline/etl/score/tests/test_score_post.py
@ -2,9 +2,10 @@
 ## Above disables warning about access to underscore-prefixed methods

 from importlib import reload
-
+from pathlib import Path
 import pandas.api.types as ptypes
 import pandas.testing as pdt
+
 from data_pipeline.etl.score import constants

 # See conftest.py for all fixtures used in these tests
@ -117,8 +118,17 @@ def test_load_tile_csv(etl, tile_data_expected):
    assert constants.DATA_SCORE_CSV_TILES_FILE_PATH.is_file()


-def test_load_downloadable_zip(etl, downloadable_data_expected):
+def test_load_downloadable_zip(etl, monkeypatch, downloadable_data_expected):
    reload(constants)
+    STATIC_FILES_PATH = (
+        Path.cwd() / "data_pipeline" / "files"
+    )  # need to monkeypatch to real dir
+    monkeypatch.setattr(constants, "FILES_PATH", STATIC_FILES_PATH)
+    monkeypatch.setattr(
+        constants,
+        "SCORE_DOWNLOADABLE_PDF_FILE_PATH",
+        STATIC_FILES_PATH / constants.SCORE_DOWNLOADABLE_PDF_FILE_NAME,
+    )
    etl._load_downloadable_zip(
        downloadable_data_expected, constants.SCORE_DOWNLOADABLE_DIR
    )
--- a/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/input.csv
+++ b/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/input.csv
@ -1,6 +1,6 @@
-TRACT,TRACTFIPS,RISK_SCORE,RISK_RATNG,RISK_NPCTL
-40300,05007040300,10.492015,Very Low,15.3494
-20100,05001020100,14.705854,Relatively Low,36.725828
-40500,15007040500,10.234981,Very Low,13.997993
-21010,15001021010,21.537231,Relatively Moderate,59.488033
-21101,15001021101,19.434585,Relatively Low,53.392265
+TRACT,TRACTFIPS,RISK_SCORE,RISK_RATNG,RISK_NPCTL,EAL_SCORE
+40300,05007040300,10.492015,Very Low,15.3494,11.5
+20100,05001020100,14.705854,Relatively Low,36.725828,12.5
+40500,15007040500,10.234981,Very Low,13.997993,13.5
+21010,15001021010,21.537231,Relatively Moderate,59.488033,14.5
+21101,15001021101,19.434585,Relatively Low,53.392265,15.5
--- a/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/output.csv
+++ b/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/output.csv
@ -1,11 +1,11 @@
-GEOID10,GEOID10_TRACT,TRACT,RISK_SCORE,RISK_RATNG,RISK_NPCTL
-050070403001,05007040300,40300,10.492015,Very Low,15.3494
-050070403002,05007040300,40300,10.492015,Very Low,15.3494
-050010201001,05001020100,20100,14.705854,Relatively Low,36.725828
-050010201002,05001020100,20100,14.705854,Relatively Low,36.725828
-150070405001,15007040500,40500,10.234981,Very Low,13.997993
-150070405002,15007040500,40500,10.234981,Very Low,13.997993
-150010210101,15001021010,21010,21.537231,Relatively Moderate,59.488033
-150010210102,15001021010,21010,21.537231,Relatively Moderate,59.488033
-150010211011,15001021101,21101,19.434585,Relatively Low,53.392265
-150010211012,15001021101,21101,19.434585,Relatively Low,53.392265
+GEOID10,FEMA Risk Index Expected Annual Loss Score
+050070403001,11.5
+050070403002,11.5
+050010201001,12.5
+050010201002,12.5
+150070405001,13.5
+150070405002,13.5
+150010210101,14.5
+150010210102,14.5
+150010211011,15.5
+150010211012,15.5
--- a/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/transform.csv
+++ b/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/transform.csv
@ -0,0 +1,11 @@
+GEOID10,GEOID10_TRACT,FEMA Risk Index Expected Annual Loss Score
+050070403001,05007040300,11.5
+050070403002,05007040300,11.5
+050010201001,05001020100,12.5
+050010201002,05001020100,12.5
+150070405001,15007040500,13.5
+150070405002,15007040500,13.5
+150010210101,15001021010,14.5
+150010210102,15001021010,14.5
+150010211011,15001021101,15.5
+150010211012,15001021101,15.5
--- a/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/test_etl.py
+++ b/data/data-pipeline/data_pipeline/tests/sources/national_risk_index/test_etl.py
@ -73,13 +73,13 @@ class TestNationalRiskIndexETL:
        TRACT_COL = etl.GEOID_TRACT_FIELD_NAME
        BLOCK_COL = etl.GEOID_FIELD_NAME
        expected = pd.read_csv(
-            DATA_DIR / "output.csv",
+            DATA_DIR / "transform.csv",
            dtype={BLOCK_COL: "string", TRACT_COL: "string"},
        )
        # execution
        etl.transform()
        # validation
-        assert etl.df.shape == (10, 6)
+        assert etl.df.shape == (10, 3)
        assert etl.df.equals(expected)

    def test_load(self, mock_etl):
@ -90,21 +90,23 @@ class TestNationalRiskIndexETL:
          self.OUTPUT_DIR
        - The content of the file that's written matches the data in self.df
        """
-        # setup
+        # setup - input variables
        etl = NationalRiskIndexETL()
-        output_path = etl.OUTPUT_DIR / "usa.csv"
        TRACT_COL = etl.GEOID_TRACT_FIELD_NAME
        BLOCK_COL = etl.GEOID_FIELD_NAME
-        expected = pd.read_csv(
-            DATA_DIR / "output.csv",
-            dtype={BLOCK_COL: str, TRACT_COL: str},
+        output_path = etl.OUTPUT_DIR / "usa.csv"
+        # setup - mock transform step
+        df_transform = pd.read_csv(
+            DATA_DIR / "transform.csv",
+            dtype={BLOCK_COL: "string", TRACT_COL: "string"},
        )
-        etl.df = expected
+        etl.df = df_transform
+        # setup - load expected output
+        expected = pd.read_csv(DATA_DIR / "output.csv", dtype={BLOCK_COL: str})
        # execution
        etl.load()
-        output = pd.read_csv(
-            output_path, dtype={BLOCK_COL: str, TRACT_COL: str}
-        )
+        output = pd.read_csv(output_path, dtype={BLOCK_COL: str})
        # validation
        assert output_path.exists()
+        assert output.shape == (10, 2)
        assert output.equals(expected)
--- a/data/data-pipeline/poetry.lock
+++ b/data/data-pipeline/poetry.lock
@ -997,7 +997,7 @@ version = "3.0.9"
 description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
 category = "dev"
 optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.6,"

 [package.dependencies]
 et-xmlfile = "*"
@ -2040,8 +2040,6 @@ lxml = [
    {file = "lxml-4.6.3-cp27-cp27m-win_amd64.whl", hash = "sha256:8157dadbb09a34a6bd95a50690595e1fa0af1a99445e2744110e3dca7831c4ee"},
    {file = "lxml-4.6.3-cp27-cp27mu-manylinux1_i686.whl", hash = "sha256:7728e05c35412ba36d3e9795ae8995e3c86958179c9770e65558ec3fdfd3724f"},
    {file = "lxml-4.6.3-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:4bff24dfeea62f2e56f5bab929b4428ae6caba2d1eea0c2d6eb618e30a71e6d4"},
-    {file = "lxml-4.6.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:64812391546a18896adaa86c77c59a4998f33c24788cadc35789e55b727a37f4"},
-    {file = "lxml-4.6.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:c1a40c06fd5ba37ad39caa0b3144eb3772e813b5fb5b084198a985431c2f1e8d"},
    {file = "lxml-4.6.3-cp35-cp35m-manylinux1_i686.whl", hash = "sha256:74f7d8d439b18fa4c385f3f5dfd11144bb87c1da034a466c5b5577d23a1d9b51"},
    {file = "lxml-4.6.3-cp35-cp35m-manylinux1_x86_64.whl", hash = "sha256:f90ba11136bfdd25cae3951af8da2e95121c9b9b93727b1b896e3fa105b2f586"},
    {file = "lxml-4.6.3-cp35-cp35m-manylinux2010_i686.whl", hash = "sha256:4c61b3a0db43a1607d6264166b230438f85bfed02e8cff20c22e564d0faff354"},
@ -2083,22 +2081,12 @@ lxml = [
    {file = "lxml-4.6.3.tar.gz", hash = "sha256:39b78571b3b30645ac77b95f7c69d1bffc4cf8c3b157c435a34da72e78c82468"},
 ]
 markupsafe = [
-    {file = "MarkupSafe-2.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d8446c54dc28c01e5a2dbac5a25f071f6653e6e40f3a8818e8b45d790fe6ef53"},
-    {file = "MarkupSafe-2.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:36bc903cbb393720fad60fc28c10de6acf10dc6cc883f3e24ee4012371399a38"},
-    {file = "MarkupSafe-2.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2d7d807855b419fc2ed3e631034685db6079889a1f01d5d9dac950f764da3dad"},
-    {file = "MarkupSafe-2.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:add36cb2dbb8b736611303cd3bfcee00afd96471b09cda130da3581cbdc56a6d"},
-    {file = "MarkupSafe-2.0.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:168cd0a3642de83558a5153c8bd34f175a9a6e7f6dc6384b9655d2697312a646"},
-    {file = "MarkupSafe-2.0.1-cp310-cp310-win32.whl", hash = "sha256:99df47edb6bda1249d3e80fdabb1dab8c08ef3975f69aed437cb69d0a5de1e28"},
-    {file = "MarkupSafe-2.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:e0f138900af21926a02425cf736db95be9f4af72ba1bb21453432a07f6082134"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:f9081981fe268bd86831e5c75f7de206ef275defcb82bc70740ae6dc507aee51"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:0955295dd5eec6cb6cc2fe1698f4c6d84af2e92de33fbcac4111913cd100a6ff"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:0446679737af14f45767963a1a9ef7620189912317d095f2d9ffa183a4d25d2b"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux2010_i686.whl", hash = "sha256:f826e31d18b516f653fe296d967d700fddad5901ae07c622bb3705955e1faa94"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:fa130dd50c57d53368c9d59395cb5526eda596d3ffe36666cd81a44d56e48872"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux2014_aarch64.whl", hash = "sha256:905fec760bd2fa1388bb5b489ee8ee5f7291d692638ea5f67982d968366bef9f"},
-    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bf5d821ffabf0ef3533c39c518f3357b171a1651c1ff6827325e4489b0e46c3c"},
-    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0d4b31cc67ab36e3392bbf3862cfbadac3db12bdd8b02a2731f509ed5b829724"},
-    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:baa1a4e8f868845af802979fcdbf0bb11f94f1cb7ced4c4b8a351bb60d108145"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-win32.whl", hash = "sha256:6c4ca60fa24e85fe25b912b01e62cb969d69a23a5d5867682dd3e80b5b02581d"},
    {file = "MarkupSafe-2.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:b2f4bf27480f5e5e8ce285a8c8fd176c0b03e93dcc6646477d4630e83440c6a9"},
    {file = "MarkupSafe-2.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:0717a7390a68be14b8c793ba258e075c6f4ca819f15edfc2a3a027c823718567"},
@ -2107,21 +2095,14 @@ markupsafe = [
    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux2010_i686.whl", hash = "sha256:d7f9850398e85aba693bb640262d3611788b1f29a79f0c93c565694658f4071f"},
    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:6a7fae0dd14cf60ad5ff42baa2e95727c3d81ded453457771d02b7d2b3f9c0c2"},
    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:b7f2d075102dc8c794cbde1947378051c4e5180d52d276987b8d28a3bd58c17d"},
-    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e9936f0b261d4df76ad22f8fee3ae83b60d7c3e871292cd42f40b81b70afae85"},
-    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:2a7d351cbd8cfeb19ca00de495e224dea7e7d919659c2841bbb7f420ad03e2d6"},
-    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:60bf42e36abfaf9aff1f50f52644b336d4f0a3fd6d8a60ca0d054ac9f713a864"},
    {file = "MarkupSafe-2.0.1-cp37-cp37m-win32.whl", hash = "sha256:a30e67a65b53ea0a5e62fe23682cfe22712e01f453b95233b25502f7c61cb415"},
    {file = "MarkupSafe-2.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:611d1ad9a4288cf3e3c16014564df047fe08410e628f89805e475368bd304914"},
-    {file = "MarkupSafe-2.0.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5bb28c636d87e840583ee3adeb78172efc47c8b26127267f54a9c0ec251d41a9"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:be98f628055368795d818ebf93da628541e10b75b41c559fdf36d104c5787066"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux1_i686.whl", hash = "sha256:1d609f577dc6e1aa17d746f8bd3c31aa4d258f4070d61b2aa5c4166c1539de35"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:7d91275b0245b1da4d4cfa07e0faedd5b0812efc15b702576d103293e252af1b"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux2010_i686.whl", hash = "sha256:01a9b8ea66f1658938f65b93a85ebe8bc016e6769611be228d797c9d998dd298"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:47ab1e7b91c098ab893b828deafa1203de86d0bc6ab587b160f78fe6c4011f75"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:97383d78eb34da7e1fa37dd273c20ad4320929af65d156e35a5e2d89566d9dfb"},
-    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6fcf051089389abe060c9cd7caa212c707e58153afa2c649f00346ce6d260f1b"},
-    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:5855f8438a7d1d458206a2466bf82b0f104a3724bf96a1c781ab731e4201731a"},
-    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:3dd007d54ee88b46be476e293f48c85048603f5f516008bee124ddd891398ed6"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-win32.whl", hash = "sha256:023cb26ec21ece8dc3907c0e8320058b2e0cb3c55cf9564da612bc325bed5e64"},
    {file = "MarkupSafe-2.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:984d76483eb32f1bcb536dc27e4ad56bba4baa70be32fa87152832cdd9db0833"},
    {file = "MarkupSafe-2.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:2ef54abee730b502252bcdf31b10dacb0a416229b72c18b19e24a4509f273d26"},
@ -2131,9 +2112,6 @@ markupsafe = [
    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux2010_i686.whl", hash = "sha256:4efca8f86c54b22348a5467704e3fec767b2db12fc39c6d963168ab1d3fc9135"},
    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:ab3ef638ace319fa26553db0624c4699e31a28bb2a835c5faca8f8acf6a5a902"},
    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:f8ba0e8349a38d3001fae7eadded3f6606f0da5d748ee53cc1dab1d6527b9509"},
-    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c47adbc92fc1bb2b3274c4b3a43ae0e4573d9fbff4f54cd484555edbf030baf1"},
-    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:37205cac2a79194e3750b0af2a5720d95f786a55ce7df90c3af697bfa100eaac"},
-    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:1f2ade76b9903f39aa442b4aadd2177decb66525062db244b35d71d0ee8599b6"},
    {file = "MarkupSafe-2.0.1-cp39-cp39-win32.whl", hash = "sha256:10f82115e21dc0dfec9ab5c0223652f7197feb168c940f3ef61563fc2d6beb74"},
    {file = "MarkupSafe-2.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:693ce3f9e70a6cf7d2fb9e6c9d8b204b6b39897a2c4a1aa65728d5ac97dcc1d8"},
    {file = "MarkupSafe-2.0.1.tar.gz", hash = "sha256:594c67807fb16238b30c44bdf74f36c02cdf22d1c8cda91ef8a0ed8dabf5620a"},
--- a/data/data-pipeline/requirements.txt
+++ b/data/data-pipeline/requirements.txt
@ -1,8 +1,12 @@
 appnope==0.1.2; sys_platform == "darwin" and python_version >= "3.7" and platform_system == "Darwin"
 argcomplete==1.12.3; python_version < "3.8.0" and python_version >= "3.7"
 argon2-cffi==21.1.0; python_version >= "3.6"
+astroid==2.8.0; python_version >= "3.6" and python_version < "4.0"
+atomicwrites==1.4.0; python_version >= "3.6" and python_full_version < "3.0.0" and sys_platform == "win32" or sys_platform == "win32" and python_version >= "3.6" and python_full_version >= "3.4.0"
 attrs==21.2.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
 backcall==0.2.0; python_version >= "3.7"
+backports.entry-points-selectable==1.1.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "2.7"
+black==21.9b0; python_full_version >= "3.6.2"
 bleach==4.1.0; python_version >= "3.7"
 censusdata==1.15; python_version >= "2.7"
 certifi==2021.5.30; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.7"
@ -11,21 +15,29 @@ charset-normalizer==2.0.6; python_full_version >= "3.6.0" and python_version >=
 click-plugins==1.1.1; python_version >= "3.6"
 click==8.0.1; python_version >= "3.6"
 cligj==0.7.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version < "4" and python_version >= "3.6"
-colorama==0.4.4; python_version >= "3.7" and python_full_version < "3.0.0" and platform_system == "Windows" and sys_platform == "win32" or platform_system == "Windows" and python_version >= "3.7" and python_full_version >= "3.5.0" and sys_platform == "win32"
+colorama==0.4.4; platform_system == "Windows" and python_version >= "3.7" and python_full_version >= "3.6.2" and sys_platform == "win32" and python_version < "4.0" and (python_version >= "3.6" and python_full_version < "3.0.0" and sys_platform == "win32" or sys_platform == "win32" and python_version >= "3.6" and python_full_version >= "3.5.0") and (python_version >= "3.7" and python_full_version < "3.0.0" and sys_platform == "win32" or sys_platform == "win32" and python_version >= "3.7" and python_full_version >= "3.5.0")
+configparser==5.0.2; python_version >= "3.6"
 cycler==0.10.0; python_version >= "3.7"
 debugpy==1.4.3; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
 decorator==5.1.0; python_version >= "3.7"
 defusedxml==0.7.1; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
+distlib==0.3.2; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
+dparse==0.5.1; python_version >= "3.5"
 dynaconf==3.1.7; python_version >= "3.7"
 entrypoints==0.3; python_full_version >= "3.6.1" and python_version >= "3.7"
+et-xmlfile==1.1.0; python_version >= "3.6"
+filelock==3.0.12; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 fiona==1.8.20; python_version >= "3.6"
+flake8==3.9.2; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
 geopandas==0.9.0; python_version >= "3.6"
 idna==3.2; python_version >= "3.5" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.5"
-importlib-metadata==4.8.1; python_version == "3.7"
+importlib-metadata==4.8.1; python_version == "3.7" and (python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.5.0" and python_version < "3.8" and python_version >= "3.6") and python_full_version >= "3.6.2"
+iniconfig==1.1.1; python_version >= "3.6"
 ipykernel==6.4.1; python_version >= "3.7"
 ipython-genutils==0.2.0; python_version >= "3.7"
 ipython==7.27.0; python_version >= "3.7"
 ipywidgets==7.6.5
+isort==5.9.3; python_full_version >= "3.6.1" and python_version < "4.0" and python_version >= "3.6"
 jedi==0.18.0; python_version >= "3.7"
 jellyfish==0.6.1
 jinja2==3.0.1; python_version >= "3.7"
@ -42,35 +54,49 @@ jupyter==1.0.0
 jupyterlab-pygments==0.1.2; python_version >= "3.7"
 jupyterlab-widgets==1.0.2; python_version >= "3.6"
 kiwisolver==1.3.2; python_version >= "3.7"
+lazy-object-proxy==1.6.0; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4.0" or python_version >= "3.6" and python_version < "4.0" and python_full_version >= "3.6.0"
+liccheck==0.6.2; python_version >= "2.7"
 lxml==4.6.3; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 markupsafe==2.0.1; python_version >= "3.7"
 matplotlib-inline==0.1.3; python_version >= "3.7"
 matplotlib==3.4.3; python_version >= "3.7"
+mccabe==0.6.1; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4.0" or python_version >= "3.6" and python_version < "4.0" and python_full_version >= "3.5.0"
 mistune==0.8.4; python_version >= "3.7"
 munch==2.5.0; python_version >= "3.6"
+mypy-extensions==0.4.3; python_full_version >= "3.6.2" and python_version >= "3.5"
+mypy==0.910; python_version >= "3.5"
 nbclient==0.5.4; python_full_version >= "3.6.1" and python_version >= "3.7"
 nbconvert==6.1.0; python_version >= "3.7"
 nbformat==5.1.3; python_full_version >= "3.6.1" and python_version >= "3.7"
 nest-asyncio==1.5.1; python_full_version >= "3.6.1" and python_version >= "3.7"
 notebook==6.4.4; python_version >= "3.6"
 numpy==1.21.1; python_version >= "3.7"
-packaging==21.0; python_version >= "3.7"
+openpyxl==3.0.7; python_version >= "3.6"
+packaging==21.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
 pandas==1.3.3; python_full_version >= "3.7.1"
 pandocfilters==1.5.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.7"
 parso==0.8.2; python_version >= "3.7"
+pathspec==0.9.0; python_full_version >= "3.6.2"
 pexpect==4.8.0; sys_platform != "win32" and python_version >= "3.7"
 pickleshare==0.7.5; python_version >= "3.7"
 pillow==8.3.2; python_version >= "3.7"
+platformdirs==2.3.0; python_version >= "3.6" and python_full_version >= "3.6.2" and python_version < "4.0" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6")
+pluggy==1.0.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
 prometheus-client==0.11.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
 prompt-toolkit==3.0.20; python_full_version >= "3.6.2" and python_version >= "3.7"
 ptyprocess==0.7.0; sys_platform != "win32" and python_version >= "3.7" and os_name != "nt"
-py==1.10.0; python_version >= "3.6" and python_full_version < "3.0.0" and implementation_name == "pypy" or implementation_name == "pypy" and python_version >= "3.6" and python_full_version >= "3.4.0"
+py==1.10.0; python_version >= "3.6" and python_full_version < "3.0.0" and implementation_name == "pypy" or python_full_version >= "3.5.0" and python_version >= "3.6" and implementation_name == "pypy"
+pycodestyle==2.7.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 pycparser==2.20; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
+pyflakes==2.3.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 pygments==2.10.0; python_version >= "3.7"
+pylint==2.11.1; python_version >= "3.6" and python_version < "4.0"
 pypandoc==1.6.4
 pyparsing==2.4.7; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.7"
 pyproj==3.2.1; python_version >= "3.7"
 pyrsistent==0.18.0; python_version >= "3.6"
+pytest-mock==3.6.1; python_version >= "3.6"
+pytest==6.2.5; python_version >= "3.6"
 python-dateutil==2.8.2; python_full_version >= "3.7.1" and python_version >= "3.7"
 pytz==2021.1; python_full_version >= "3.7.1" and python_version >= "2.7"
 pywin32==301; sys_platform == "win32" and platform_python_implementation != "PyPy" and python_version >= "3.6"
@ -79,21 +105,29 @@ pyyaml==5.4.1; python_version >= "2.7" and python_full_version < "3.0.0" or pyth
 pyzmq==22.3.0; python_full_version >= "3.6.1" and python_version >= "3.7"
 qtconsole==5.1.1; python_version >= "3.6"
 qtpy==1.11.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
+regex==2021.8.28; python_full_version >= "3.6.2"
 requests==2.26.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0")
+safety==1.10.3; python_version >= "3.5"
+semantic-version==2.8.5; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "2.7"
 send2trash==1.8.0; python_version >= "3.6"
 shapely==1.7.1; python_version >= "3.6"
-six==1.16.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.7"
+six==1.16.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
 terminado==0.12.1; python_version >= "3.6"
 testpath==0.5.0; python_version >= "3.7"
+toml==0.10.2; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4.0" or python_full_version >= "3.5.0" and python_version >= "3.6" and python_version < "4.0"
+tomli==1.2.1; python_version >= "3.6" and python_full_version >= "3.6.2"
 tornado==6.1; python_full_version >= "3.6.1" and python_version >= "3.7"
+tox==3.24.4; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
 tqdm==4.62.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.4.0")
 traitlets==5.1.0; python_full_version >= "3.6.1" and python_version >= "3.7"
 types-requests==2.25.8
 typing-extensions==3.10.0.2; python_version < "3.8" and python_version >= "3.6"
 urllib3==1.26.6; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version < "4" and python_version >= "2.7"
 us==2.0.2
+virtualenv==20.8.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 wcwidth==0.2.5; python_full_version >= "3.6.2" and python_version >= "3.7"
 webencodings==0.5.1; python_version >= "3.7"
 widgetsnbextension==3.5.1
+wrapt==1.12.1; python_version >= "3.6" and python_version < "4.0"
 xlsxwriter==2.0.0
 zipp==3.5.0; python_version < "3.8" and python_version >= "3.6"
--- a/data/data-pipeline/tox.ini
+++ b/data/data-pipeline/tox.ini
@ -1,7 +1,7 @@
 [tox]
 # required because we use pyproject.toml
 isolated_build = true
-envlist = py37, py38, py39, lint, checkdeps
+envlist = py37, py38, py39, lint, checkdeps, pytest
 # only checks python versions installed locally
 skip_missing_interpreters = true

@ -18,3 +18,8 @@ commands = black data_pipeline
 deps = -rrequirements.txt
 commands = safety check
           liccheck
+
+[testenv:pytest]
+# Run tests
+deps = pytest
+commands = pytest
--- a/infrastructure/functions/detect-changes-for-worker/package-lock.json
+++ b/infrastructure/functions/detect-changes-for-worker/package-lock.json
@ -97,9 +97,9 @@
      "dev": true
    },
    "ansi-regex": {
-      "version": "5.0.0",
-      "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.0.tgz",
-      "integrity": "sha512-bY6fj56OUQ0hU1KjFNDQuJFezqKdrAyFdIevADiqrWHwSlbmBNMHp5ak2f40Pm8JTFyM2mqxkG6ngkHO11f/lg==",
+      "version": "5.0.1",
+      "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.1.tgz",
+      "integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==",
      "dev": true
    },
    "ansi-styles": {