Issue 105: Configure and run black and other pre-commit hooks (clean branch) (#1962)

* Configure and run `black` and other pre-commit hooks

Co-authored-by: matt bowen <matthew.r.bowen@omb.eop.gov>

data/data-pipeline/data_pipeline/tests/conftest.py

@@ -3,7 +3,6 @@ from pathlib import Path
 from shutil import copyfile
 
 import pytest
-
 from data_pipeline.config import settings
 from data_pipeline.etl.base import ExtractTransformLoad
 

data/data-pipeline/data_pipeline/tests/score/fixtures.py

@@ -1,8 +1,8 @@
 import pandas as pd
 import pytest
 from data_pipeline.config import settings
-from data_pipeline.score.field_names import GEOID_TRACT_FIELD
 from data_pipeline.etl.score import constants
+from data_pipeline.score.field_names import GEOID_TRACT_FIELD
 
 
 @pytest.fixture(scope="session")

data/data-pipeline/data_pipeline/tests/score/test_calculation.py

@@ -1,9 +1,11 @@
 # flake8: noqa: W0613,W0611,F811
 from dataclasses import dataclass
+
 import pytest
 from data_pipeline.score import field_names
-from data_pipeline.utils import get_module_logger
 from data_pipeline.score.score_narwhal import ScoreNarwhal
+from data_pipeline.utils import get_module_logger
+
 from .fixtures import final_score_df  # pylint: disable=unused-import
 
 logger = get_module_logger(__name__)

data/data-pipeline/data_pipeline/tests/score/test_output.py

@@ -2,36 +2,35 @@
 # pylint: disable=unused-import,too-many-arguments
 from dataclasses import dataclass
 from typing import List
-import pytest
-import pandas as pd
+
 import numpy as np
+import pandas as pd
+import pytest
 from data_pipeline.etl.score import constants
+from data_pipeline.etl.score.constants import TILES_ISLAND_AREA_FIPS_CODES
 from data_pipeline.score import field_names
 from data_pipeline.score.field_names import GEOID_TRACT_FIELD
-from data_pipeline.etl.score.constants import TILES_ISLAND_AREA_FIPS_CODES
-from .fixtures import (
-    final_score_df,
-    ejscreen_df,
-    hud_housing_df,
-    census_acs_df,
-    cdc_places_df,
-    census_acs_median_incomes_df,
-    cdc_life_expectancy_df,
-    doe_energy_burden_df,
-    national_risk_index_df,
-    dot_travel_disadvantage_df,
-    fsf_fire_df,
-    nature_deprived_df,
-    eamlis_df,
-    fuds_df,
-    geocorr_urban_rural_df,
-    census_decennial_df,
-    census_2010_df,
-    hrs_df,
-    national_tract_df,
-    tribal_overlap,
-)
 
+from .fixtures import cdc_life_expectancy_df  # noqa
+from .fixtures import cdc_places_df  # noqa
+from .fixtures import census_2010_df  # noqa
+from .fixtures import census_acs_df  # noqa
+from .fixtures import census_acs_median_incomes_df  # noqa
+from .fixtures import census_decennial_df  # noqa
+from .fixtures import doe_energy_burden_df  # noqa
+from .fixtures import dot_travel_disadvantage_df  # noqa
+from .fixtures import eamlis_df  # noqa
+from .fixtures import ejscreen_df  # noqa
+from .fixtures import final_score_df  # noqa
+from .fixtures import fsf_fire_df  # noqa
+from .fixtures import fuds_df  # noqa
+from .fixtures import geocorr_urban_rural_df  # noqa
+from .fixtures import hrs_df  # noqa
+from .fixtures import hud_housing_df  # noqa
+from .fixtures import national_risk_index_df  # noqa
+from .fixtures import national_tract_df  # noqa
+from .fixtures import nature_deprived_df  # noqa
+from .fixtures import tribal_overlap  # noqa
 
 pytestmark = pytest.mark.smoketest
 UNMATCHED_TRACT_THRESHOLD = 1000

data/data-pipeline/data_pipeline/tests/score/test_score_narwhal_methods.py

@@ -1,10 +1,9 @@
 # pylint: disable=protected-access
-
 import pandas as pd
 import pytest
 from data_pipeline.config import settings
-from data_pipeline.score import field_names
 from data_pipeline.etl.score.etl_score import ScoreETL
+from data_pipeline.score import field_names
 from data_pipeline.utils import get_module_logger
 
 logger = get_module_logger(__name__)

data/data-pipeline/data_pipeline/tests/score/test_tiles_smoketests.py

@@ -1,18 +1,20 @@
 # flake8: noqa: W0613,W0611,F811
 from dataclasses import dataclass
 from typing import Optional
-import pandas as pd
+
 import geopandas as gpd
 import numpy as np
+import pandas as pd
 import pytest
 from data_pipeline.config import settings
 from data_pipeline.etl.score import constants
-from data_pipeline.score import field_names
+from data_pipeline.etl.score.constants import THRESHOLD_COUNT_TO_SHOW_FIELD_NAME
+from data_pipeline.etl.score.constants import TILES_SCORE_COLUMNS
 from data_pipeline.etl.score.constants import (
-    TILES_SCORE_COLUMNS,
-    THRESHOLD_COUNT_TO_SHOW_FIELD_NAME,
     USER_INTERFACE_EXPERIENCE_FIELD_NAME,
 )
+from data_pipeline.score import field_names
+
 from .fixtures import final_score_df  # pylint: disable=unused-import
 
 pytestmark = pytest.mark.smoketest

data/data-pipeline/data_pipeline/tests/score/test_utils/test_adjacency.py

@@ -1,17 +1,17 @@
 # pylint: disable=protected-access
 # flake8: noqa=F841
+from contextlib import contextmanager
+from functools import partial
 from pathlib import Path
 from unittest import mock
-from functools import partial
-from contextlib import contextmanager
 
-import pytest
 import pandas as pd
+import pytest
+from data_pipeline.etl.sources.geo_utils import get_tract_geojson
+from data_pipeline.score import field_names
 from data_pipeline.score.utils import (
     calculate_tract_adjacency_scores as original_calculate_tract_adjacency_score,
 )
-from data_pipeline.etl.sources.geo_utils import get_tract_geojson
-from data_pipeline.score import field_names
 
 
 @contextmanager

data/data-pipeline/data_pipeline/tests/sources/cdc_life_expectancy/test_etl.py

@@ -1,6 +1,7 @@
 # pylint: disable=protected-access
 import pathlib
 from unittest import mock
+
 import requests
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.etl.sources.cdc_life_expectancy.etl import CDCLifeExpectancy

data/data-pipeline/data_pipeline/tests/sources/cdc_places/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.cdc_places.etl import CDCPlacesETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestCDCPlacesETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/doe_energy_burden/test_etl.py

@@ -1,9 +1,7 @@
 # pylint: disable=protected-access
 import pathlib
 
-from data_pipeline.etl.sources.doe_energy_burden.etl import (
-    DOEEnergyBurden,
-)
+from data_pipeline.etl.sources.doe_energy_burden.etl import DOEEnergyBurden
 from data_pipeline.tests.sources.example.test_etl import TestETL
 from data_pipeline.utils import get_module_logger
 

data/data-pipeline/data_pipeline/tests/sources/dot_travel_composite/test_etl.py

@@ -1,9 +1,10 @@
 import pathlib
+
 import geopandas as gpd
-from data_pipeline.tests.sources.example.test_etl import TestETL
 from data_pipeline.etl.sources.dot_travel_composite.etl import (
     TravelCompositeETL,
 )
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestTravelCompositeETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/eamlis/test_etl.py

@@ -1,11 +1,9 @@
 # pylint: disable=protected-access
-from unittest import mock
 import pathlib
-from data_pipeline.etl.base import ValidGeoLevel
+from unittest import mock
 
-from data_pipeline.etl.sources.eamlis.etl import (
-    AbandonedMineETL,
-)
+from data_pipeline.etl.base import ValidGeoLevel
+from data_pipeline.etl.sources.eamlis.etl import AbandonedMineETL
 from data_pipeline.tests.sources.example.test_etl import TestETL
 from data_pipeline.utils import get_module_logger
 

data/data-pipeline/data_pipeline/tests/sources/ejscreen/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.ejscreen.etl import EJSCREENETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestEJSCREENETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/example/etl.py

@@ -1,8 +1,9 @@
 import zipfile
-import pandas as pd
 
+import pandas as pd
 from data_pipeline.config import settings
-from data_pipeline.etl.base import ExtractTransformLoad, ValidGeoLevel
+from data_pipeline.etl.base import ExtractTransformLoad
+from data_pipeline.etl.base import ValidGeoLevel
 from data_pipeline.utils import get_module_logger
 
 logger = get_module_logger(__name__)

data/data-pipeline/data_pipeline/tests/sources/example/test_etl.py

@@ -2,19 +2,18 @@
 import copy
 import os
 import pathlib
-from typing import Type, Optional
+from typing import Optional
+from typing import Type
 from unittest import mock
-import pytest
 
-import requests
 import numpy as np
 import pandas as pd
-
-from data_pipeline.etl.base import ExtractTransformLoad, ValidGeoLevel
-from data_pipeline.etl.score.constants import (
-    TILES_CONTINENTAL_US_FIPS_CODE,
-    TILES_ALASKA_AND_HAWAII_FIPS_CODE,
-)
+import pytest
+import requests
+from data_pipeline.etl.base import ExtractTransformLoad
+from data_pipeline.etl.base import ValidGeoLevel
+from data_pipeline.etl.score.constants import TILES_ALASKA_AND_HAWAII_FIPS_CODE
+from data_pipeline.etl.score.constants import TILES_CONTINENTAL_US_FIPS_CODE
 from data_pipeline.tests.sources.example.etl import ExampleETL
 from data_pipeline.utils import get_module_logger
 

data/data-pipeline/data_pipeline/tests/sources/fsf_flood_risk/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.fsf_flood_risk.etl import FloodRiskETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestFloodRiskETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/fsf_wildfire_risk/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.fsf_wildfire_risk.etl import WildfireRiskETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestWildfireRiskETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/geocorr/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.geocorr.etl import GeoCorrETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestGeoCorrETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/historic_redlining/test_etl.py

@@ -1,10 +1,11 @@
 # pylint: disable=protected-access
 import pathlib
+
 import pandas as pd
-from data_pipeline.tests.sources.example.test_etl import TestETL
 from data_pipeline.etl.sources.historic_redlining.etl import (
     HistoricRedliningETL,
 )
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestHistoricRedliningETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/hud_housing/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.hud_housing.etl import HudHousingETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestHudHousingETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/national_risk_index/test_etl.py

@@ -1,7 +1,7 @@
 # pylint: disable=protected-access
 import pathlib
-from data_pipeline.etl.base import ValidGeoLevel
 
+from data_pipeline.etl.base import ValidGeoLevel
 from data_pipeline.etl.sources.national_risk_index.etl import (
     NationalRiskIndexETL,
 )

data/data-pipeline/data_pipeline/tests/sources/nlcd_nature_deprived/test_etl.py

@@ -1,6 +1,7 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.nlcd_nature_deprived.etl import NatureDeprivedETL
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestNatureDeprivedETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/persistent_poverty/test_etl.py

@@ -1,8 +1,9 @@
 import pathlib
-from data_pipeline.tests.sources.example.test_etl import TestETL
+
 from data_pipeline.etl.sources.persistent_poverty.etl import (
     PersistentPovertyETL,
 )
+from data_pipeline.tests.sources.example.test_etl import TestETL
 
 
 class TestPersistentPovertyETL(TestETL):

data/data-pipeline/data_pipeline/tests/sources/test_geo_utils.py

@@ -1,5 +1,6 @@
-from pathlib import Path
 from collections import namedtuple
+from pathlib import Path
+
 import geopandas as gpd
 from data_pipeline.etl.sources.geo_utils import add_tracts_for_geometries
 

data/data-pipeline/data_pipeline/tests/sources/us_army_fuds/test_etl.py

@@ -1,11 +1,9 @@
 # pylint: disable=protected-access
-from unittest import mock
 import pathlib
-from data_pipeline.etl.base import ValidGeoLevel
+from unittest import mock
 
-from data_pipeline.etl.sources.us_army_fuds.etl import (
-    USArmyFUDS,
-)
+from data_pipeline.etl.base import ValidGeoLevel
+from data_pipeline.etl.sources.us_army_fuds.etl import USArmyFUDS
 from data_pipeline.tests.sources.example.test_etl import TestETL
 from data_pipeline.utils import get_module_logger
 

data/data-pipeline/data_pipeline/tests/test_etl.py

@@ -1,6 +1,7 @@
 # pylint: disable=protected-access
 import pytest
-from data_pipeline.etl import constants, runner
+from data_pipeline.etl import constants
+from data_pipeline.etl import runner
 
 
 def test_get_datasets_to_run():