fixing merge conflicts

data/data-pipeline/data_pipeline/etl/score/config/datasets.yml

@@ -81,7 +81,7 @@ datasets:
     load_fields:
       - short_name: "he_heat"
         df_field_name: "EXTREME_HEAT_FIELD"
-        long_name: "Summer days above 90F" 
+        long_name: "Summer days above 90F"
         field_type: float
         include_in_downloadable_files: true
         include_in_tiles: true
@@ -92,7 +92,7 @@ datasets:
         include_in_downloadable_files: true
         include_in_tiles: true
       - short_name: "he_green"
-        long_name: "Percent impenetrable surface areas" 
+        long_name: "Percent impenetrable surface areas"
         df_field_name: "IMPENETRABLE_SURFACES_FIELD"
         field_type: float
         include_in_downloadable_files: true
@@ -110,7 +110,7 @@ datasets:
     load_fields:
       - short_name: "EBP_PFS"
         df_field_name: "REVISED_ENERGY_BURDEN_FIELD_NAME"
-        long_name: "Energy burden" 
+        long_name: "Energy burden"
         field_type: float
         include_in_downloadable_files: true
         include_in_tiles: true
@@ -121,7 +121,7 @@ datasets:
       - short_name: "fuds_count"
         df_field_name: "ELIGIBLE_FUDS_COUNT_FIELD_NAME"
         long_name: "Count of eligible Formerly Used Defense Site (FUDS) properties centroids"
-        description_short: 
+        description_short:
           "The number of FUDS marked as Eligible and Has Project in the tract."
         field_type: int64
         include_in_tiles: false
@@ -129,7 +129,7 @@ datasets:
       - short_name: "not_fuds_ct"
         df_field_name: "INELIGIBLE_FUDS_COUNT_FIELD_NAME"
         long_name: "Count of ineligible Formerly Used Defense Site (FUDS) properties centroids"
-        description_short: 
+        description_short:
           "The number of FUDS marked as Ineligible or Project in the tract."
         field_type: int64
         include_in_tiles: false
@@ -137,7 +137,7 @@ datasets:
       - short_name: "has_fuds"
         df_field_name: "ELIGIBLE_FUDS_BINARY_FIELD_NAME"
         long_name: "Is there at least one Formerly Used Defense Site (FUDS) in the tract?"
-        description_short: 
+        description_short:
           "Whether the tract has a FUDS"
         field_type: bool
         include_in_tiles: false
@@ -149,7 +149,7 @@ datasets:
       - short_name: "has_aml"
         df_field_name: "AML_BOOLEAN"
         long_name: "Is there at least one abandoned mine in this census tract?"
-        description_short: 
+        description_short:
           "Whether the tract has an abandoned mine"
         field_type: bool
         include_in_tiles: true
@@ -161,7 +161,7 @@ datasets:
     load_fields:
       - short_name: "EXAMPLE_FIELD"
         df_field_name: "Input Field 1"
-        long_name: "Example Field 1" 
+        long_name: "Example Field 1"
         field_type: float
         include_in_tiles: true
         include_in_downloadable_files: true
@@ -172,35 +172,35 @@ datasets:
     load_fields:
       - short_name: "flood_eligible_properties"
         df_field_name: "COUNT_PROPERTIES"
-        long_name: "Count of properties eligible for flood risk calculation within tract (floor of 250)" 
+        long_name: "Count of properties eligible for flood risk calculation within tract (floor of 250)"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "flood_risk_properties_today"
         df_field_name: "PROPERTIES_AT_RISK_FROM_FLOODING_TODAY"
-        long_name: "Count of properties at risk of flood today" 
+        long_name: "Count of properties at risk of flood today"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "flood_risk_properties_30yrs"
         df_field_name: "PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS"
-        long_name: "Count of properties at risk of flood in 30 years" 
+        long_name: "Count of properties at risk of flood in 30 years"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "flood_risk_share_today"
         df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_TODAY"
-        long_name: "Share of properties at risk of flood today" 
+        long_name: "Share of properties at risk of flood today"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: true
       - short_name: "flood_risk_share_30yrs"
         df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS"
-        long_name: "Share of properties at risk of flood in 30 years" 
+        long_name: "Share of properties at risk of flood in 30 years"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
@@ -212,35 +212,35 @@ datasets:
     load_fields:
       - short_name: "fire_eligible_properties"
         df_field_name: "COUNT_PROPERTIES"
-        long_name: "Count of properties eligible for wildfire risk calculation within tract (floor of 250)" 
+        long_name: "Count of properties eligible for wildfire risk calculation within tract (floor of 250)"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "fire_risk_properties_today"
         df_field_name: "PROPERTIES_AT_RISK_FROM_FIRE_TODAY"
-        long_name: "Count of properties at risk of wildfire today" 
+        long_name: "Count of properties at risk of wildfire today"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "fire_risk_properties_30yrs"
         df_field_name: "PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS"
-        long_name: "Count of properties at risk of wildfire in 30 years" 
+        long_name: "Count of properties at risk of wildfire in 30 years"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "fire_risk_share_today"
         df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_TODAY"
-        long_name: "Share of properties at risk of fire today" 
+        long_name: "Share of properties at risk of fire today"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
         create_percentile: true
       - short_name: "fire_risk_share_30yrs"
         df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS"
-        long_name: "Share of properties at risk of fire in 30 years" 
+        long_name: "Share of properties at risk of fire in 30 years"
         field_type: float
         include_in_tiles: false
         include_in_downloadable_files: true
@@ -252,7 +252,7 @@ datasets:
     load_fields:
       - short_name: "travel_burden"
         df_field_name: "TRAVEL_BURDEN_FIELD_NAME"
-        long_name: "DOT Travel Barriers Score" 
+        long_name: "DOT Travel Barriers Score"
         field_type: float
         include_in_tiles: true
         include_in_downloadable_files: true
@@ -264,28 +264,28 @@ datasets:
     load_fields:
       - short_name: "ncld_eligible"
         df_field_name: "ELIGIBLE_FOR_NATURE_DEPRIVED_FIELD_NAME"
-        long_name: "Does the tract have at least 35 acres in it?" 
+        long_name: "Does the tract have at least 35 acres in it?"
         field_type: bool
         include_in_tiles: true
         include_in_downloadable_files: true
         create_percentile: false
       - short_name: "percent_impervious"
         df_field_name: "TRACT_PERCENT_IMPERVIOUS_FIELD_NAME"
-        long_name: "Share of the tract's land area that is covered by impervious surface as a percent" 
+        long_name: "Share of the tract's land area that is covered by impervious surface as a percent"
         field_type: percentage
         include_in_tiles: true
         include_in_downloadable_files: true
         create_percentile: true
       - short_name: "percent_nonnatural"
         df_field_name: "TRACT_PERCENT_NON_NATURAL_FIELD_NAME"
-        long_name: "Share of the tract's land area that is covered by impervious surface or cropland as a percent" 
+        long_name: "Share of the tract's land area that is covered by impervious surface or cropland as a percent"
         field_type: percentage
         include_in_tiles: true
         include_in_downloadable_files: true
         create_percentile: true
       - short_name: "percent_cropland"
         df_field_name: "TRACT_PERCENT_CROPLAND_FIELD_NAME"
-        long_name: "Share of the tract's land area that is covered by cropland as a percent" 
+        long_name: "Share of the tract's land area that is covered by cropland as a percent"
         field_type: percentage
         include_in_tiles: true
         include_in_downloadable_files: true
@@ -328,4 +328,4 @@ datasets:
        include_in_tiles: false
        include_in_downloadable_files: true
        create_percentile: false
-       create_reverse_percentile: true
+       create_reverse_percentile: true

data/data-pipeline/data_pipeline/etl/score/constants.py

@@ -1,8 +1,7 @@
-from pathlib import Path
 import datetime
+from pathlib import Path
 
 from data_pipeline.config import settings
-
 from data_pipeline.score import field_names
 
 ## note: to keep map porting "right" fields, keeping descriptors the same.

data/data-pipeline/data_pipeline/etl/score/etl_score.py

@@ -1,31 +1,28 @@
 import functools
-from typing import List
-
 from dataclasses import dataclass
+from typing import List
 
 import numpy as np
 import pandas as pd
-
 from data_pipeline.etl.base import ExtractTransformLoad
+from data_pipeline.etl.score import constants
 from data_pipeline.etl.sources.census_acs.etl import CensusACSETL
-from data_pipeline.etl.sources.national_risk_index.etl import (
-    NationalRiskIndexETL,
-)
 from data_pipeline.etl.sources.dot_travel_composite.etl import (
     TravelCompositeETL,
 )
+from data_pipeline.etl.sources.eamlis.etl import AbandonedMineETL
 from data_pipeline.etl.sources.fsf_flood_risk.etl import (
     FloodRiskETL,
 )
-from data_pipeline.etl.sources.eamlis.etl import AbandonedMineETL
+from data_pipeline.etl.sources.fsf_wildfire_risk.etl import WildfireRiskETL
+from data_pipeline.etl.sources.national_risk_index.etl import (
+    NationalRiskIndexETL,
+)
+from data_pipeline.etl.sources.nlcd_nature_deprived.etl import NatureDeprivedETL
 from data_pipeline.etl.sources.tribal_overlap.etl import TribalOverlapETL
 from data_pipeline.etl.sources.us_army_fuds.etl import USArmyFUDS
-from data_pipeline.etl.sources.nlcd_nature_deprived.etl import NatureDeprivedETL
-from data_pipeline.etl.sources.fsf_wildfire_risk.etl import WildfireRiskETL
-from data_pipeline.score.score_runner import ScoreRunner
 from data_pipeline.score import field_names
-from data_pipeline.etl.score import constants
-
+from data_pipeline.score.score_runner import ScoreRunner
 from data_pipeline.utils import get_module_logger
 
 logger = get_module_logger(__name__)

data/data-pipeline/data_pipeline/etl/score/etl_score_geo.py

@@ -1,24 +1,22 @@
 import concurrent.futures
 import math
 import os
+
+import geopandas as gpd
 import numpy as np
 import pandas as pd
-import geopandas as gpd
-
+from data_pipeline.content.schemas.download_schemas import CSVConfig
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.etl.score import constants
+from data_pipeline.etl.score.etl_utils import check_score_data_source
 from data_pipeline.etl.sources.census.etl_utils import (
     check_census_data_source,
 )
-from data_pipeline.etl.score.etl_utils import check_score_data_source
 from data_pipeline.score import field_names
-from data_pipeline.content.schemas.download_schemas import CSVConfig
-from data_pipeline.utils import (
-    get_module_logger,
-    zip_files,
-    load_yaml_dict_from_file,
-    load_dict_from_yaml_object_fields,
-)
+from data_pipeline.utils import get_module_logger
+from data_pipeline.utils import load_dict_from_yaml_object_fields
+from data_pipeline.utils import load_yaml_dict_from_file
+from data_pipeline.utils import zip_files
 
 logger = get_module_logger(__name__)
 

data/data-pipeline/data_pipeline/etl/score/etl_score_post.py

@@ -1,29 +1,25 @@
-from pathlib import Path
 import json
-from numpy import float64
+from pathlib import Path
+
 import numpy as np
 import pandas as pd
-from data_pipeline.content.schemas.download_schemas import (
-    CSVConfig,
-    CodebookConfig,
-    ExcelConfig,
-)
-
+from data_pipeline.content.schemas.download_schemas import CodebookConfig
+from data_pipeline.content.schemas.download_schemas import CSVConfig
+from data_pipeline.content.schemas.download_schemas import ExcelConfig
 from data_pipeline.etl.base import ExtractTransformLoad
-from data_pipeline.etl.score.etl_utils import floor_series, create_codebook
-from data_pipeline.utils import (
-    get_module_logger,
-    zip_files,
-    load_yaml_dict_from_file,
-    column_list_from_yaml_object_fields,
-    load_dict_from_yaml_object_fields,
-)
-from data_pipeline.score import field_names
-
-
+from data_pipeline.etl.score.etl_utils import create_codebook
+from data_pipeline.etl.score.etl_utils import floor_series
 from data_pipeline.etl.sources.census.etl_utils import (
     check_census_data_source,
 )
+from data_pipeline.score import field_names
+from data_pipeline.utils import column_list_from_yaml_object_fields
+from data_pipeline.utils import get_module_logger
+from data_pipeline.utils import load_dict_from_yaml_object_fields
+from data_pipeline.utils import load_yaml_dict_from_file
+from data_pipeline.utils import zip_files
+from numpy import float64
+
 from . import constants
 
 logger = get_module_logger(__name__)

data/data-pipeline/data_pipeline/etl/score/etl_utils.py

@@ -1,24 +1,21 @@
 import os
 import sys
 import typing
-from pathlib import Path
 from collections import namedtuple
+from pathlib import Path
+
 import numpy as np
 import pandas as pd
-
 from data_pipeline.config import settings
-from data_pipeline.etl.score.constants import (
-    TILES_ISLAND_AREA_FIPS_CODES,
-    TILES_PUERTO_RICO_FIPS_CODE,
-    TILES_CONTINENTAL_US_FIPS_CODE,
-    TILES_ALASKA_AND_HAWAII_FIPS_CODE,
-)
+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.etl.score.constants import TILES_ISLAND_AREA_FIPS_CODES
+from data_pipeline.etl.score.constants import TILES_PUERTO_RICO_FIPS_CODE
 from data_pipeline.etl.sources.census.etl_utils import get_state_fips_codes
-from data_pipeline.utils import (
-    download_file_from_url,
-    get_module_logger,
-)
 from data_pipeline.score import field_names
+from data_pipeline.utils import download_file_from_url
+from data_pipeline.utils import get_module_logger
+
 from . import constants
 
 logger = get_module_logger(__name__)
@@ -99,7 +96,7 @@ def floor_series(series: pd.Series, number_of_decimals: int) -> pd.Series:
     if series.isin(unacceptable_values).any():
         series.replace(mapping, regex=False, inplace=True)
 
-    multiplication_factor = 10 ** number_of_decimals
+    multiplication_factor = 10**number_of_decimals
 
     # In order to safely cast NaNs
     # First coerce series to float type: series.astype(float)

data/data-pipeline/data_pipeline/etl/score/schemas/datasets.py

@@ -1,6 +1,8 @@
-from dataclasses import dataclass, field
+from dataclasses import dataclass
+from dataclasses import field
 from enum import Enum
-from typing import List, Optional
+from typing import List
+from typing import Optional
 
 
 class FieldType(Enum):

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

@@ -5,7 +5,8 @@ from pathlib import Path
 import pandas as pd
 import pytest
 from data_pipeline import config
-from data_pipeline.etl.score import etl_score_post, tests
+from data_pipeline.etl.score import etl_score_post
+from data_pipeline.etl.score import tests
 from data_pipeline.etl.score.etl_score_post import PostScoreETL
 
 

data/data-pipeline/data_pipeline/etl/score/tests/sample_data/state_data_initial.csv

@@ -1,4 +1,4 @@
 fips,state_name,state_abbreviation,region,division
 01,Alabama,AL,South,East South Central
 02,Alaska,AK,West,Pacific
-04,Arizona,AZ,West,Mountain
+04,Arizona,AZ,West,Mountain

data/data-pipeline/data_pipeline/etl/score/tests/test_etl_utils.py

@@ -1,11 +1,10 @@
-import pandas as pd
 import numpy as np
+import pandas as pd
 import pytest
-
 from data_pipeline.etl.score.etl_utils import (
-    floor_series,
     compare_to_list_of_expected_state_fips_codes,
 )
+from data_pipeline.etl.score.etl_utils import floor_series
 
 
 def test_floor_series():

data/data-pipeline/data_pipeline/etl/score/tests/test_score_post.py

@@ -1,14 +1,13 @@
 # pylint: disable=W0212
 ## 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.content.schemas.download_schemas import (
     CSVConfig,
 )
-
 from data_pipeline.etl.score import constants
 from data_pipeline.utils import load_yaml_dict_from_file