Issue 308 python linting (#443)

* 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

data/data-pipeline/etl/base.py

@@ -1,11 +1,10 @@
 from pathlib import Path
-import pathlib
 
 from config import settings
 from utils import unzip_file_from_url, remove_all_from_dir
 
 
-class ExtractTransformLoad(object):
+class ExtractTransformLoad:
     """
     A class used to instantiate an ETL object to retrieve and process data from
     datasets.
@@ -34,9 +33,7 @@ class ExtractTransformLoad(object):
 
         pass
 
-    def extract(
-        self, source_url: str = None, extract_path: Path = None
-    ) -> None:
+    def extract(self, source_url: str = None, extract_path: Path = None) -> None:
         """Extract the data from
         a remote source. By default it provides code to get the file from a source url,
         unzips it and stores it on an extract_path."""

data/data-pipeline/etl/runner.py

@@ -67,9 +67,7 @@ def etl_runner(dataset_to_run: str = None) -> None:
 
     # Run the ETLs for the dataset_list
     for dataset in dataset_list:
-        etl_module = importlib.import_module(
-            f"etl.sources.{dataset['module_dir']}.etl"
-        )
+        etl_module = importlib.import_module(f"etl.sources.{dataset['module_dir']}.etl")
         etl_class = getattr(etl_module, dataset["class_name"])
         etl_instance = etl_class()
 

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

@@ -4,7 +4,6 @@ import pandas as pd
 
 from etl.base import ExtractTransformLoad
 from utils import get_module_logger
-from etl.sources.census.etl_utils import get_state_fips_codes
 
 logger = get_module_logger(__name__)
 
@@ -28,10 +27,10 @@ class ScoreETL(ExtractTransformLoad):
         self.UNEMPLOYED_FIELD_NAME = "Unemployed civilians (percent)"
         self.LINGUISTIC_ISOLATION_FIELD_NAME = "Linguistic isolation (percent)"
         self.HOUSING_BURDEN_FIELD_NAME = "Housing burden (percent)"
-        self.POVERTY_FIELD_NAME = (
-            "Poverty (Less than 200% of federal poverty line)"
+        self.POVERTY_FIELD_NAME = "Poverty (Less than 200% of federal poverty line)"
+        self.HIGH_SCHOOL_FIELD_NAME = (
+            "Percent individuals age 25 or over with less than high school degree"
         )
-        self.HIGH_SCHOOL_FIELD_NAME = "Percent individuals age 25 or over with less than high school degree"
 
         # There's another aggregation level (a second level of "buckets").
         self.AGGREGATION_POLLUTION = "Pollution Burden"
@@ -55,9 +54,7 @@ class ScoreETL(ExtractTransformLoad):
         self.ejscreen_df = pd.read_csv(
             ejscreen_csv, dtype={"ID": "string"}, low_memory=False
         )
-        self.ejscreen_df.rename(
-            columns={"ID": self.GEOID_FIELD_NAME}, inplace=True
-        )
+        self.ejscreen_df.rename(columns={"ID": self.GEOID_FIELD_NAME}, inplace=True)
 
         # Load census data
         census_csv = self.DATA_PATH / "dataset" / "census_acs_2019" / "usa.csv"
@@ -69,10 +66,7 @@ class ScoreETL(ExtractTransformLoad):
 
         # Load housing and transportation data
         housing_and_transportation_index_csv = (
-            self.DATA_PATH
-            / "dataset"
-            / "housing_and_transportation_index"
-            / "usa.csv"
+            self.DATA_PATH / "dataset" / "housing_and_transportation_index" / "usa.csv"
         )
         self.housing_and_transportation_df = pd.read_csv(
             housing_and_transportation_index_csv,
@@ -89,7 +83,7 @@ class ScoreETL(ExtractTransformLoad):
         )
 
     def transform(self) -> None:
-        logger.info(f"Transforming Score Data")
+        logger.info("Transforming Score Data")
 
         # Join all the data sources that use census block groups
         census_block_group_dfs = [
@@ -106,10 +100,7 @@ class ScoreETL(ExtractTransformLoad):
         )
 
         # Sanity check the join.
-        if (
-            len(census_block_group_df[self.GEOID_FIELD_NAME].str.len().unique())
-            != 1
-        ):
+        if len(census_block_group_df[self.GEOID_FIELD_NAME].str.len().unique()) != 1:
             raise ValueError(
                 f"One of the input CSVs uses {self.GEOID_FIELD_NAME} with a different length."
             )
@@ -119,9 +110,9 @@ class ScoreETL(ExtractTransformLoad):
         census_tract_df = self.hud_housing_df
 
         # Calculate the tract for the CBG data.
-        census_block_group_df[
-            self.GEOID_TRACT_FIELD_NAME
-        ] = census_block_group_df[self.GEOID_FIELD_NAME].str[0:11]
+        census_block_group_df[self.GEOID_TRACT_FIELD_NAME] = census_block_group_df[
+            self.GEOID_FIELD_NAME
+        ].str[0:11]
 
         self.df = census_block_group_df.merge(
             census_tract_df, on=self.GEOID_TRACT_FIELD_NAME
@@ -254,8 +245,7 @@ class ScoreETL(ExtractTransformLoad):
 
         # Rename columns:
         renaming_dict = {
-            data_set.input_field: data_set.renamed_field
-            for data_set in data_sets
+            data_set.input_field: data_set.renamed_field for data_set in data_sets
         }
 
         self.df.rename(
@@ -310,7 +300,7 @@ class ScoreETL(ExtractTransformLoad):
             ) / (max_value - min_value)
 
             # Graph distributions and correlations.
-            min_max_fields = [
+            min_max_fields = [  # noqa: F841
                 f"{data_set.renamed_field}{self.MIN_MAX_FIELD_SUFFIX}"
                 for data_set in data_sets
                 if data_set.renamed_field != self.GEOID_FIELD_NAME
@@ -324,9 +314,7 @@ class ScoreETL(ExtractTransformLoad):
             ]
         ].mean(axis=1)
         self.df["Score B"] = (
-            self.df[
-                "Poverty (Less than 200% of federal poverty line) (percentile)"
-            ]
+            self.df["Poverty (Less than 200% of federal poverty line) (percentile)"]
             * self.df[
                 "Percent individuals age 25 or over with less than high school degree (percentile)"
             ]
@@ -342,21 +330,26 @@ class ScoreETL(ExtractTransformLoad):
             ]
             self.df[f"{bucket}"] = self.df[fields_in_bucket].mean(axis=1)
 
-        # Combine the score from the two Exposures and Environmental Effects buckets into a single score called "Pollution Burden". The math for this score is: (1.0 * Exposures Score + 0.5 * Environment Effects score) / 1.5.
+        # Combine the score from the two Exposures and Environmental Effects buckets
+        # into a single score called "Pollution Burden".
+        # The math for this score is:
+        # (1.0 * Exposures Score + 0.5 * Environment Effects score) / 1.5.
         self.df[self.AGGREGATION_POLLUTION] = (
             1.0 * self.df[f"{self.BUCKET_EXPOSURES}"]
             + 0.5 * self.df[f"{self.BUCKET_ENVIRONMENTAL}"]
         ) / 1.5
 
-        # Average the score from the two Sensitive populations and Socioeconomic factors buckets into a single score called "Population Characteristics".
+        # Average the score from the two Sensitive populations and
+        # Socioeconomic factors buckets into a single score called
+        # "Population Characteristics".
         self.df[self.AGGREGATION_POPULATION] = self.df[
             [f"{self.BUCKET_SENSITIVE}", f"{self.BUCKET_SOCIOECONOMIC}"]
         ].mean(axis=1)
 
-        # Multiply the "Pollution Burden" score and the "Population Characteristics" together to produce the cumulative impact score.
+        # Multiply the "Pollution Burden" score and the "Population Characteristics"
+        # together to produce the cumulative impact score.
         self.df["Score C"] = (
-            self.df[self.AGGREGATION_POLLUTION]
-            * self.df[self.AGGREGATION_POPULATION]
+            self.df[self.AGGREGATION_POLLUTION] * self.df[self.AGGREGATION_POPULATION]
         )
 
         if len(census_block_group_df) > 220333:
@@ -371,12 +364,10 @@ class ScoreETL(ExtractTransformLoad):
         ]
 
         fields_min_max = [
-            f"{field}{self.MIN_MAX_FIELD_SUFFIX}"
-            for field in fields_to_use_in_score
+            f"{field}{self.MIN_MAX_FIELD_SUFFIX}" for field in fields_to_use_in_score
         ]
         fields_percentile = [
-            f"{field}{self.PERCENTILE_FIELD_SUFFIX}"
-            for field in fields_to_use_in_score
+            f"{field}{self.PERCENTILE_FIELD_SUFFIX}" for field in fields_to_use_in_score
         ]
 
         # Calculate "Score D", which uses min-max normalization
@@ -396,17 +387,22 @@ class ScoreETL(ExtractTransformLoad):
             "Score E",
             "Poverty (Less than 200% of federal poverty line)",
         ]:
-            self.df[f"{score_field}{self.PERCENTILE_FIELD_SUFFIX}"] = self.df[score_field].rank(pct=True)
+            self.df[f"{score_field}{self.PERCENTILE_FIELD_SUFFIX}"] = self.df[
+                score_field
+            ].rank(pct=True)
 
             for threshold in [0.25, 0.3, 0.35, 0.4]:
                 fraction_converted_to_percent = int(100 * threshold)
-                self.df[f"{score_field} (top {fraction_converted_to_percent}th percentile)"] = (
-                        self.df[f"{score_field}{self.PERCENTILE_FIELD_SUFFIX}"] >= 1 - threshold
+                self.df[
+                    f"{score_field} (top {fraction_converted_to_percent}th percentile)"
+                ] = (
+                    self.df[f"{score_field}{self.PERCENTILE_FIELD_SUFFIX}"]
+                    >= 1 - threshold
                 )
 
     def load(self) -> None:
-        logger.info(f"Saving Score CSV")
+        logger.info("Saving Score CSV")
 
         # write nationwide csv
         self.SCORE_CSV_PATH.mkdir(parents=True, exist_ok=True)
-        self.df.to_csv(self.SCORE_CSV_PATH / f"usa.csv", index=False)
+        self.df.to_csv(self.SCORE_CSV_PATH / "usa.csv", index=False)

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

@@ -1,6 +1,7 @@
+import math
+
 import pandas as pd
 import geopandas as gpd
-import math
 
 from etl.base import ExtractTransformLoad
 from utils import get_module_logger
@@ -21,9 +22,7 @@ class GeoScoreETL(ExtractTransformLoad):
         self.SCORE_CSV_PATH = self.DATA_PATH / "score" / "csv"
         self.TILE_SCORE_CSV = self.SCORE_CSV_PATH / "tiles" / "usa.csv"
 
-        self.CENSUS_USA_GEOJSON = (
-            self.DATA_PATH / "census" / "geojson" / "us.json"
-        )
+        self.CENSUS_USA_GEOJSON = self.DATA_PATH / "census" / "geojson" / "us.json"
 
         self.TARGET_SCORE_NAME = "Score E (percentile)"
         self.TARGET_SCORE_RENAME_TO = "E_SCORE"
@@ -36,7 +35,7 @@ class GeoScoreETL(ExtractTransformLoad):
         self.geojson_score_usa_low: gpd.GeoDataFrame
 
     def extract(self) -> None:
-        logger.info(f"Reading US GeoJSON (~6 minutes)")
+        logger.info("Reading US GeoJSON (~6 minutes)")
         self.geojson_usa_df = gpd.read_file(
             self.CENSUS_USA_GEOJSON,
             dtype={"GEOID10": "string"},
@@ -45,7 +44,7 @@ class GeoScoreETL(ExtractTransformLoad):
         )
         self.geojson_usa_df.head()
 
-        logger.info(f"Reading score CSV")
+        logger.info("Reading score CSV")
         self.score_usa_df = pd.read_csv(
             self.TILE_SCORE_CSV,
             dtype={"GEOID10": "string"},
@@ -53,11 +52,11 @@ class GeoScoreETL(ExtractTransformLoad):
         )
 
     def transform(self) -> None:
-        logger.info(f"Pruning Census GeoJSON")
+        logger.info("Pruning Census GeoJSON")
         fields = ["GEOID10", "geometry"]
         self.geojson_usa_df = self.geojson_usa_df[fields]
 
-        logger.info(f"Merging and compressing score CSV with USA GeoJSON")
+        logger.info("Merging and compressing score CSV with USA GeoJSON")
         self.geojson_score_usa_high = self.score_usa_df.merge(
             self.geojson_usa_df, on="GEOID10", how="left"
         )
@@ -75,7 +74,7 @@ class GeoScoreETL(ExtractTransformLoad):
             inplace=True,
         )
 
-        logger.info(f"Aggregating into tracts (~5 minutes)")
+        logger.info("Aggregating into tracts (~5 minutes)")
         usa_tracts = self._aggregate_to_tracts(usa_simplified)
 
         usa_tracts = gpd.GeoDataFrame(
@@ -84,17 +83,15 @@ class GeoScoreETL(ExtractTransformLoad):
             crs="EPSG:4326",
         )
 
-        logger.info(f"Creating buckets from tracts")
+        logger.info("Creating buckets from tracts")
         usa_bucketed = self._create_buckets_from_tracts(
             usa_tracts, self.NUMBER_OF_BUCKETS
         )
 
-        logger.info(f"Aggregating buckets")
+        logger.info("Aggregating buckets")
         usa_aggregated = self._aggregate_buckets(usa_bucketed, agg_func="mean")
 
-        compressed = self._breakup_multipolygons(
-            usa_aggregated, self.NUMBER_OF_BUCKETS
-        )
+        compressed = self._breakup_multipolygons(usa_aggregated, self.NUMBER_OF_BUCKETS)
 
         self.geojson_score_usa_low = gpd.GeoDataFrame(
             compressed,
@@ -118,9 +115,7 @@ class GeoScoreETL(ExtractTransformLoad):
         # assign tracts to buckets by D_SCORE
         state_tracts.sort_values(self.TARGET_SCORE_RENAME_TO, inplace=True)
         SCORE_bucket = []
-        bucket_size = math.ceil(
-            len(state_tracts.index) / self.NUMBER_OF_BUCKETS
-        )
+        bucket_size = math.ceil(len(state_tracts.index) / self.NUMBER_OF_BUCKETS)
         for i in range(len(state_tracts.index)):
             SCORE_bucket.extend([math.floor(i / bucket_size)])
         state_tracts[f"{self.TARGET_SCORE_RENAME_TO}_bucket"] = SCORE_bucket
@@ -155,14 +150,10 @@ class GeoScoreETL(ExtractTransformLoad):
         return compressed
 
     def load(self) -> None:
-        logger.info(f"Writing usa-high (~9 minutes)")
-        self.geojson_score_usa_high.to_file(
-            self.SCORE_HIGH_GEOJSON, driver="GeoJSON"
-        )
-        logger.info(f"Completed writing usa-high")
+        logger.info("Writing usa-high (~9 minutes)")
+        self.geojson_score_usa_high.to_file(self.SCORE_HIGH_GEOJSON, driver="GeoJSON")
+        logger.info("Completed writing usa-high")
 
-        logger.info(f"Writing usa-low (~9 minutes)")
-        self.geojson_score_usa_low.to_file(
-            self.SCORE_LOW_GEOJSON, driver="GeoJSON"
-        )
-        logger.info(f"Completed writing usa-low")
+        logger.info("Writing usa-low (~9 minutes)")
+        self.geojson_score_usa_low.to_file(self.SCORE_LOW_GEOJSON, driver="GeoJSON")
+        logger.info("Completed writing usa-low")

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

@@ -19,9 +19,7 @@ class PostScoreETL(ExtractTransformLoad):
         self.CENSUS_USA_CSV = self.DATA_PATH / "census" / "csv" / "us.csv"
         self.SCORE_CSV_PATH = self.DATA_PATH / "score" / "csv"
 
-        self.STATE_CSV = (
-            self.DATA_PATH / "census" / "csv" / "fips_states_2010.csv"
-        )
+        self.STATE_CSV = self.DATA_PATH / "census" / "csv" / "fips_states_2010.csv"
 
         self.FULL_SCORE_CSV = self.SCORE_CSV_PATH / "full" / "usa.csv"
         self.TILR_SCORE_CSV = self.SCORE_CSV_PATH / "tile" / "usa.csv"
@@ -49,7 +47,7 @@ class PostScoreETL(ExtractTransformLoad):
             self.TMP_PATH,
         )
 
-        logger.info(f"Reading Counties CSV")
+        logger.info("Reading Counties CSV")
         self.counties_df = pd.read_csv(
             self.CENSUS_COUNTIES_TXT,
             sep="\t",
@@ -58,16 +56,14 @@ class PostScoreETL(ExtractTransformLoad):
             encoding="latin-1",
         )
 
-        logger.info(f"Reading States CSV")
+        logger.info("Reading States CSV")
         self.states_df = pd.read_csv(
             self.STATE_CSV, dtype={"fips": "string", "state_code": "string"}
         )
-        self.score_df = pd.read_csv(
-            self.FULL_SCORE_CSV, dtype={"GEOID10": "string"}
-        )
+        self.score_df = pd.read_csv(self.FULL_SCORE_CSV, dtype={"GEOID10": "string"})
 
     def transform(self) -> None:
-        logger.info(f"Transforming data sources for Score + County CSV")
+        logger.info("Transforming data sources for Score + County CSV")
 
         # rename some of the columns to prepare for merge
         self.counties_df = self.counties_df[["USPS", "GEOID", "NAME"]]
@@ -101,7 +97,7 @@ class PostScoreETL(ExtractTransformLoad):
         )
 
         # check if there are census cbgs without score
-        logger.info(f"Removing CBG rows without score")
+        logger.info("Removing CBG rows without score")
 
         ## load cbgs
         cbg_usa_df = pd.read_csv(
@@ -121,19 +117,19 @@ class PostScoreETL(ExtractTransformLoad):
         null_cbg_df = merged_df[merged_df["Score E (percentile)"].isnull()]
 
         # subsctract data sets
-        removed_df = pd.concat(
-            [merged_df, null_cbg_df, null_cbg_df]
-        ).drop_duplicates(keep=False)
+        removed_df = pd.concat([merged_df, null_cbg_df, null_cbg_df]).drop_duplicates(
+            keep=False
+        )
 
         # set the score to the new df
         self.score_county_state_merged = removed_df
 
     def load(self) -> None:
-        logger.info(f"Saving Full Score CSV with County Information")
+        logger.info("Saving Full Score CSV with County Information")
         self.SCORE_CSV_PATH.mkdir(parents=True, exist_ok=True)
         self.score_county_state_merged.to_csv(self.FULL_SCORE_CSV, index=False)
 
-        logger.info(f"Saving Tile Score CSV")
+        logger.info("Saving Tile Score CSV")
         # TODO: check which are the columns we'll use
         # Related to: https://github.com/usds/justice40-tool/issues/302
         score_tiles = self.score_county_state_merged[self.TILES_SCORE_COLUMNS]

data/data-pipeline/etl/sources/calenviroscreen/etl.py

@@ -9,16 +9,12 @@ logger = get_module_logger(__name__)
 class CalEnviroScreenETL(ExtractTransformLoad):
     def __init__(self):
         self.CALENVIROSCREEN_FTP_URL = "https://justice40-data.s3.amazonaws.com/data-sources/CalEnviroScreen_4.0_2021.zip"
-        self.CALENVIROSCREEN_CSV = (
-            self.TMP_PATH / "CalEnviroScreen_4.0_2021.csv"
-        )
+        self.CALENVIROSCREEN_CSV = self.TMP_PATH / "CalEnviroScreen_4.0_2021.csv"
         self.CSV_PATH = self.DATA_PATH / "dataset" / "calenviroscreen4"
 
         # Definining some variable names
         self.CALENVIROSCREEN_SCORE_FIELD_NAME = "calenviroscreen_score"
-        self.CALENVIROSCREEN_PERCENTILE_FIELD_NAME = (
-            "calenviroscreen_percentile"
-        )
+        self.CALENVIROSCREEN_PERCENTILE_FIELD_NAME = "calenviroscreen_percentile"
         self.CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD_NAME = (
             "calenviroscreen_priority_community"
         )
@@ -30,14 +26,14 @@ class CalEnviroScreenETL(ExtractTransformLoad):
         self.df: pd.DataFrame
 
     def extract(self) -> None:
-        logger.info(f"Downloading CalEnviroScreen Data")
+        logger.info("Downloading CalEnviroScreen Data")
         super().extract(
             self.CALENVIROSCREEN_FTP_URL,
             self.TMP_PATH,
         )
 
     def transform(self) -> None:
-        logger.info(f"Transforming CalEnviroScreen Data")
+        logger.info("Transforming CalEnviroScreen Data")
 
         # Data from https://calenviroscreen-oehha.hub.arcgis.com/#Data, specifically:
         # https://oehha.ca.gov/media/downloads/calenviroscreen/document/calenviroscreen40resultsdatadictionaryd12021.zip
@@ -67,7 +63,7 @@ class CalEnviroScreenETL(ExtractTransformLoad):
         )
 
     def load(self) -> None:
-        logger.info(f"Saving CalEnviroScreen CSV")
+        logger.info("Saving CalEnviroScreen CSV")
         # write nationwide csv
         self.CSV_PATH.mkdir(parents=True, exist_ok=True)
-        self.df.to_csv(self.CSV_PATH / f"data06.csv", index=False)
+        self.df.to_csv(self.CSV_PATH / "data06.csv", index=False)

data/data-pipeline/etl/sources/census/etl.py

@@ -1,11 +1,12 @@
-import csv
 import os
+import csv
 import json
 from pathlib import Path
+
 import geopandas as gpd
 
-from .etl_utils import get_state_fips_codes
 from utils import unzip_file_from_url, get_module_logger
+from .etl_utils import get_state_fips_codes
 
 logger = get_module_logger(__name__)
 
@@ -29,9 +30,7 @@ def download_census_csvs(data_path: Path) -> None:
 
     for fips in state_fips_codes:
         # check if file exists
-        shp_file_path = (
-            data_path / "census" / "shp" / fips / f"tl_2010_{fips}_bg10.shp"
-        )
+        shp_file_path = data_path / "census" / "shp" / fips / f"tl_2010_{fips}_bg10.shp"
 
         logger.info(f"Checking if {fips} file exists")
         if not os.path.isfile(shp_file_path):
@@ -110,7 +109,7 @@ def download_census_csvs(data_path: Path) -> None:
             )
 
     ## create national geojson
-    logger.info(f"Generating national geojson file")
+    logger.info("Generating national geojson file")
     usa_df = gpd.GeoDataFrame()
 
     for file_name in geojson_dir_path.rglob("*.json"):
@@ -119,7 +118,7 @@ def download_census_csvs(data_path: Path) -> None:
         usa_df = usa_df.append(state_gdf)
 
     usa_df = usa_df.to_crs("+proj=longlat +ellps=WGS84 +datum=WGS84 +no_defs")
-    logger.info(f"Writing national geojson file")
+    logger.info("Writing national geojson file")
     usa_df.to_file(geojson_dir_path / "us.json", driver="GeoJSON")
 
     logger.info("Census block groups downloading complete")

data/data-pipeline/etl/sources/census/etl_utils.py

@@ -1,7 +1,8 @@
-from pathlib import Path
-import csv
-import pandas as pd
 import os
+import csv
+
+from pathlib import Path
+import pandas as pd
 from config import settings
 
 from utils import (
@@ -35,7 +36,7 @@ def get_state_fips_codes(data_path: Path) -> list:
 
     # check if file exists
     if not os.path.isfile(fips_csv_path):
-        logger.info(f"Downloading fips from S3 repository")
+        logger.info("Downloading fips from S3 repository")
         unzip_file_from_url(
             settings.AWS_JUSTICE40_DATA_URL + "/Census/fips_states_2010.zip",
             data_path / "tmp",

data/data-pipeline/etl/sources/census_acs/etl.py

@@ -11,14 +11,10 @@ logger = get_module_logger(__name__)
 class CensusACSETL(ExtractTransformLoad):
     def __init__(self):
         self.ACS_YEAR = 2019
-        self.OUTPUT_PATH = (
-            self.DATA_PATH / "dataset" / f"census_acs_{self.ACS_YEAR}"
-        )
+        self.OUTPUT_PATH = self.DATA_PATH / "dataset" / f"census_acs_{self.ACS_YEAR}"
         self.UNEMPLOYED_FIELD_NAME = "Unemployed civilians (percent)"
         self.LINGUISTIC_ISOLATION_FIELD_NAME = "Linguistic isolation (percent)"
-        self.LINGUISTIC_ISOLATION_TOTAL_FIELD_NAME = (
-            "Linguistic isolation (total)"
-        )
+        self.LINGUISTIC_ISOLATION_TOTAL_FIELD_NAME = "Linguistic isolation (total)"
         self.LINGUISTIC_ISOLATION_FIELDS = [
             "C16002_001E",
             "C16002_004E",
@@ -28,9 +24,7 @@ class CensusACSETL(ExtractTransformLoad):
         ]
         self.df: pd.DataFrame
 
-    def _fips_from_censusdata_censusgeo(
-        self, censusgeo: censusdata.censusgeo
-    ) -> str:
+    def _fips_from_censusdata_censusgeo(self, censusgeo: censusdata.censusgeo) -> str:
         """Create a FIPS code from the proprietary censusgeo index."""
         fips = "".join([value for (key, value) in censusgeo.params()])
         return fips
@@ -38,9 +32,7 @@ class CensusACSETL(ExtractTransformLoad):
     def extract(self) -> None:
         dfs = []
         for fips in get_state_fips_codes(self.DATA_PATH):
-            logger.info(
-                f"Downloading data for state/territory with FIPS code {fips}"
-            )
+            logger.info(f"Downloading data for state/territory with FIPS code {fips}")
 
             dfs.append(
                 censusdata.download(
@@ -65,13 +57,11 @@ class CensusACSETL(ExtractTransformLoad):
         )
 
     def transform(self) -> None:
-        logger.info(f"Starting Census ACS Transform")
+        logger.info("Starting Census ACS Transform")
 
         # Calculate percent unemployment.
         # TODO: remove small-sample data that should be `None` instead of a high-variance fraction.
-        self.df[self.UNEMPLOYED_FIELD_NAME] = (
-            self.df.B23025_005E / self.df.B23025_003E
-        )
+        self.df[self.UNEMPLOYED_FIELD_NAME] = self.df.B23025_005E / self.df.B23025_003E
 
         # Calculate linguistic isolation.
         individual_limited_english_fields = [
@@ -92,7 +82,7 @@ class CensusACSETL(ExtractTransformLoad):
         self.df[self.LINGUISTIC_ISOLATION_FIELD_NAME].describe()
 
     def load(self) -> None:
-        logger.info(f"Saving Census ACS Data")
+        logger.info("Saving Census ACS Data")
 
         # mkdir census
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
@@ -108,6 +98,6 @@ class CensusACSETL(ExtractTransformLoad):
         )
 
     def validate(self) -> None:
-        logger.info(f"Validating Census ACS Data")
+        logger.info("Validating Census ACS Data")
 
         pass

data/data-pipeline/etl/sources/ejscreen/etl.py

@@ -8,20 +8,22 @@ logger = get_module_logger(__name__)
 
 class EJScreenETL(ExtractTransformLoad):
     def __init__(self):
-        self.EJSCREEN_FTP_URL = "https://gaftp.epa.gov/EJSCREEN/2019/EJSCREEN_2019_StatePctile.csv.zip"
+        self.EJSCREEN_FTP_URL = (
+            "https://gaftp.epa.gov/EJSCREEN/2019/EJSCREEN_2019_StatePctile.csv.zip"
+        )
         self.EJSCREEN_CSV = self.TMP_PATH / "EJSCREEN_2019_StatePctiles.csv"
         self.CSV_PATH = self.DATA_PATH / "dataset" / "ejscreen_2019"
         self.df: pd.DataFrame
 
     def extract(self) -> None:
-        logger.info(f"Downloading EJScreen Data")
+        logger.info("Downloading EJScreen Data")
         super().extract(
             self.EJSCREEN_FTP_URL,
             self.TMP_PATH,
         )
 
     def transform(self) -> None:
-        logger.info(f"Transforming EJScreen Data")
+        logger.info("Transforming EJScreen Data")
         self.df = pd.read_csv(
             self.EJSCREEN_CSV,
             dtype={"ID": "string"},
@@ -31,7 +33,7 @@ class EJScreenETL(ExtractTransformLoad):
         )
 
     def load(self) -> None:
-        logger.info(f"Saving EJScreen CSV")
+        logger.info("Saving EJScreen 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)

data/data-pipeline/etl/sources/housing_and_transportation/etl.py

@@ -35,9 +35,7 @@ class HousingTransportationETL(ExtractTransformLoad):
             )
 
             # New file name:
-            tmp_csv_file_path = (
-                zip_file_dir / f"htaindex_data_blkgrps_{fips}.csv"
-            )
+            tmp_csv_file_path = zip_file_dir / f"htaindex_data_blkgrps_{fips}.csv"
             tmp_df = pd.read_csv(filepath_or_buffer=tmp_csv_file_path)
 
             dfs.append(tmp_df)
@@ -45,16 +43,16 @@ class HousingTransportationETL(ExtractTransformLoad):
         self.df = pd.concat(dfs)
 
     def transform(self) -> None:
-        logger.info(f"Transforming Housing and Transportation Data")
+        logger.info("Transforming Housing and Transportation Data")
 
         # Rename and reformat block group ID
         self.df.rename(columns={"blkgrp": self.GEOID_FIELD_NAME}, inplace=True)
-        self.df[self.GEOID_FIELD_NAME] = self.df[
-            self.GEOID_FIELD_NAME
-        ].str.replace('"', "")
+        self.df[self.GEOID_FIELD_NAME] = self.df[self.GEOID_FIELD_NAME].str.replace(
+            '"', ""
+        )
 
     def load(self) -> None:
-        logger.info(f"Saving Housing and Transportation Data")
+        logger.info("Saving Housing and Transportation Data")
 
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
         self.df.to_csv(path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False)

data/data-pipeline/etl/sources/hud_housing/etl.py

@@ -1,8 +1,7 @@
 import pandas as pd
 
 from etl.base import ExtractTransformLoad
-from etl.sources.census.etl_utils import get_state_fips_codes
-from utils import get_module_logger, unzip_file_from_url, remove_all_from_dir
+from utils import get_module_logger
 
 logger = get_module_logger(__name__)
 
@@ -11,33 +10,37 @@ class HudHousingETL(ExtractTransformLoad):
     def __init__(self):
         self.OUTPUT_PATH = self.DATA_PATH / "dataset" / "hud_housing"
         self.GEOID_TRACT_FIELD_NAME = "GEOID10_TRACT"
-        self.HOUSING_FTP_URL = "https://www.huduser.gov/portal/datasets/cp/2012thru2016-140-csv.zip"
+        self.HOUSING_FTP_URL = (
+            "https://www.huduser.gov/portal/datasets/cp/2012thru2016-140-csv.zip"
+        )
         self.HOUSING_ZIP_FILE_DIR = self.TMP_PATH / "hud_housing"
 
         # We measure households earning less than 80% of HUD Area Median Family Income by county
         # and paying greater than 30% of their income to housing costs.
         self.HOUSING_BURDEN_FIELD_NAME = "Housing burden (percent)"
         self.HOUSING_BURDEN_NUMERATOR_FIELD_NAME = "HOUSING_BURDEN_NUMERATOR"
-        self.HOUSING_BURDEN_DENOMINATOR_FIELD_NAME = (
-            "HOUSING_BURDEN_DENOMINATOR"
-        )
+        self.HOUSING_BURDEN_DENOMINATOR_FIELD_NAME = "HOUSING_BURDEN_DENOMINATOR"
 
         # Note: some variable definitions.
         # HUD-adjusted median family income (HAMFI).
-        # The four housing problems are: incomplete kitchen facilities, incomplete plumbing facilities, more than 1 person per room, and cost burden greater than 30%.
+        # The four housing problems are:
+        #   - incomplete kitchen facilities,
+        #   - incomplete plumbing facilities,
+        #   - more than 1 person per room,
+        #   - cost burden greater than 30%.
         # Table 8 is the desired table.
 
         self.df: pd.DataFrame
 
     def extract(self) -> None:
-        logger.info(f"Extracting HUD Housing Data")
+        logger.info("Extracting HUD Housing Data")
         super().extract(
             self.HOUSING_FTP_URL,
             self.HOUSING_ZIP_FILE_DIR,
         )
 
     def transform(self) -> None:
-        logger.info(f"Transforming HUD Housing Data")
+        logger.info("Transforming HUD Housing Data")
 
         # New file name:
         tmp_csv_file_path = (
@@ -53,9 +56,7 @@ class HudHousingETL(ExtractTransformLoad):
         )
 
         # Rename and reformat block group ID
-        self.df.rename(
-            columns={"geoid": self.GEOID_TRACT_FIELD_NAME}, inplace=True
-        )
+        self.df.rename(columns={"geoid": self.GEOID_TRACT_FIELD_NAME}, inplace=True)
 
         # The CHAS data has census tract ids such as `14000US01001020100`
         # Whereas the rest of our data uses, for the same tract, `01001020100`.
@@ -70,69 +71,177 @@ class HudHousingETL(ExtractTransformLoad):
 
         # Owner occupied numerator fields
         OWNER_OCCUPIED_NUMERATOR_FIELDS = [
-            # Key: Column Name	Line_Type	Tenure	Household income	Cost burden	Facilities
-            # T8_est7	Subtotal	Owner occupied	less than or equal to 30% of HAMFI	greater than 30% but less than or equal to 50%	All
+            # Column Name
+            #   Line_Type
+            #   Tenure
+            #   Household income
+            #   Cost burden
+            #   Facilities
             "T8_est7",
-            # T8_est10	Subtotal	Owner occupied	less than or equal to 30% of HAMFI	greater than 50%	All
+            #   Subtotal
+            #   Owner occupied
+            #   less than or equal to 30% of HAMFI
+            #   greater than 30% but less than or equal to 50%
+            #   All
             "T8_est10",
-            # T8_est20	Subtotal	Owner occupied	greater than 30% but less than or equal to 50% of HAMFI	greater than 30% but less than or equal to 50%	All
+            #   Subtotal
+            #   Owner occupied
+            #   less than or equal to 30% of HAMFI
+            #   greater than 50%
+            #   All
             "T8_est20",
-            # T8_est23	Subtotal	Owner occupied	greater than 30% but less than or equal to 50% of HAMFI	greater than 50%	All
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 30% but less than or equal to 50% of HAMFI
+            #   greater than 30% but less than or equal to 50%
+            #   All
             "T8_est23",
-            # T8_est33	Subtotal	Owner occupied	greater than 50% but less than or equal to 80% of HAMFI	greater than 30% but less than or equal to 50%	All
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 30% but less than or equal to 50% of HAMFI
+            #   greater than 50%
+            #   All
             "T8_est33",
-            # T8_est36	Subtotal	Owner occupied	greater than 50% but less than or equal to 80% of HAMFI	greater than 50%	All
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 50% but less than or equal to 80% of HAMFI
+            #   greater than 30% but less than or equal to 50%
+            #   All
             "T8_est36",
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 50% but less than or equal to 80% of HAMFI
+            #   greater than 50%
+            #   All
         ]
 
         # These rows have the values where HAMFI was not computed, b/c of no or negative income.
         OWNER_OCCUPIED_NOT_COMPUTED_FIELDS = [
-            # Key: Column Name	Line_Type	Tenure	Household income	Cost burden	Facilities
-            # T8_est13	Subtotal	Owner occupied	less than or equal to 30% of HAMFI	not computed (no/negative income)	All
+            # Column Name
+            #   Line_Type
+            #   Tenure
+            #   Household income
+            #   Cost burden
+            #   Facilities
             "T8_est13",
-            # T8_est26	Subtotal	Owner occupied	greater than 30% but less than or equal to 50% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Owner occupied
+            #   less than or equal to 30% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est26",
-            # T8_est39	Subtotal	Owner occupied	greater than 50% but less than or equal to 80% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 30% but less than or equal to 50% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est39",
-            # T8_est52	Subtotal	Owner occupied	greater than 80% but less than or equal to 100% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 50% but less than or equal to 80% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est52",
-            # T8_est65	Subtotal	Owner occupied	greater than 100% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 80% but less than or equal to 100% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est65",
+            #   Subtotal
+            #   Owner occupied
+            #   greater than 100% of HAMFI
+            #   not computed (no/negative income)
+            #   All
         ]
 
-        # T8_est2	Subtotal	Owner occupied	All	All	All
         OWNER_OCCUPIED_POPULATION_FIELD = "T8_est2"
+        #   Subtotal
+        #   Owner occupied
+        #   All
+        #   All
+        #   All
 
         # Renter occupied numerator fields
         RENTER_OCCUPIED_NUMERATOR_FIELDS = [
-            # Key: Column Name	Line_Type	Tenure	Household income	Cost burden	Facilities
-            # T8_est73	Subtotal	Renter occupied	less than or equal to 30% of HAMFI	greater than 30% but less than or equal to 50%	All
+            # Column Name
+            #   Line_Type
+            #   Tenure
+            #   Household income
+            #   Cost burden
+            #   Facilities
             "T8_est73",
-            # T8_est76	Subtotal	Renter occupied	less than or equal to 30% of HAMFI	greater than 50%	All
+            #   Subtotal
+            #   Renter occupied
+            #   less than or equal to 30% of HAMFI
+            #   greater than 30% but less than or equal to 50%
+            #   All
             "T8_est76",
-            # T8_est86	Subtotal	Renter occupied	greater than 30% but less than or equal to 50% of HAMFI	greater than 30% but less than or equal to 50%	All
+            #   Subtotal
+            #   Renter occupied
+            #   less than or equal to 30% of HAMFI
+            #   greater than 50%
+            #   All
             "T8_est86",
-            # T8_est89	Subtotal	Renter occupied	greater than 30% but less than or equal to 50% of HAMFI	greater than 50%	All
+            #   Subtotal
+            #   Renter occupied
+            #   greater than 30% but less than or equal to 50% of HAMFI
+            #   greater than 30% but less than or equal to 50%
+            #   All
             "T8_est89",
-            # T8_est99	Subtotal	Renter occupied	greater than 50% but less than or equal to 80% of HAMFI	greater than 30% but less than or equal to 50%	All
+            #   Subtotal
+            #   Renter occupied
+            #   greater than 30% but less than or equal to 50% of HAMFI
+            #   greater than 50%
+            #   All
             "T8_est99",
-            # T8_est102	Subtotal	Renter occupied	greater than 50% but less than or equal to 80% of HAMFI	greater than 50%	All
+            #   Subtotal
+            #   Renter occupied	greater than 50% but less than or equal to 80% of HAMFI
+            #   greater than 30% but less than or equal to 50%
+            #   All
             "T8_est102",
+            #   Subtotal
+            #   Renter occupied
+            #   greater than 50% but less than or equal to 80% of HAMFI
+            #   greater than 50%
+            #   All
         ]
 
         # These rows have the values where HAMFI was not computed, b/c of no or negative income.
         RENTER_OCCUPIED_NOT_COMPUTED_FIELDS = [
-            # Key: Column Name	Line_Type	Tenure	Household income	Cost burden	Facilities
-            # T8_est79	Subtotal	Renter occupied	less than or equal to 30% of HAMFI	not computed (no/negative income)	All
+            # Column Name
+            #   Line_Type
+            #   Tenure
+            #   Household income
+            #   Cost burden
+            #   Facilities
             "T8_est79",
-            # T8_est92	Subtotal	Renter occupied	greater than 30% but less than or equal to 50% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Renter occupied	less than or equal to 30% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est92",
-            # T8_est105	Subtotal	Renter occupied	greater than 50% but less than or equal to 80% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Renter occupied	greater than 30% but less than or equal to 50% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est105",
-            # T8_est118	Subtotal	Renter occupied	greater than 80% but less than or equal to 100% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Renter occupied
+            #   greater than 50% but less than or equal to 80% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est118",
-            # T8_est131	Subtotal	Renter occupied	greater than 100% of HAMFI	not computed (no/negative income)	All
+            #   Subtotal
+            #   Renter occupied	greater than 80% but less than or equal to 100% of HAMFI
+            #   not computed (no/negative income)
+            #   All
             "T8_est131",
+            #   Subtotal
+            #   Renter occupied
+            #   greater than 100% of HAMFI
+            #   not computed (no/negative income)
+            #   All
         ]
 
         # T8_est68	Subtotal	Renter occupied	All	All	All
@@ -165,14 +274,12 @@ class HudHousingETL(ExtractTransformLoad):
         # TODO: add small sample size checks
         self.df[self.HOUSING_BURDEN_FIELD_NAME] = self.df[
             self.HOUSING_BURDEN_NUMERATOR_FIELD_NAME
-        ].astype(float) / self.df[
-            self.HOUSING_BURDEN_DENOMINATOR_FIELD_NAME
-        ].astype(
+        ].astype(float) / self.df[self.HOUSING_BURDEN_DENOMINATOR_FIELD_NAME].astype(
             float
         )
 
     def load(self) -> None:
-        logger.info(f"Saving HUD Housing Data")
+        logger.info("Saving HUD Housing Data")
 
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
 

data/data-pipeline/etl/sources/hud_recap/etl.py

@@ -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)

data/data-pipeline/etl/sources/tree_equity_score/etl.py

@@ -3,25 +3,72 @@ import geopandas as gpd
 
 from etl.base import ExtractTransformLoad
 from utils import get_module_logger
-import os
 
 logger = get_module_logger(__name__)
 
 
 class TreeEquityScoreETL(ExtractTransformLoad):
     def __init__(self):
-        self.TES_URL = "https://national-tes-data-share.s3.amazonaws.com/national_tes_share/"
+        self.TES_URL = (
+            "https://national-tes-data-share.s3.amazonaws.com/national_tes_share/"
+        )
         self.TES_CSV = self.TMP_PATH / "tes_2021_data.csv"
         self.CSV_PATH = self.DATA_PATH / "dataset" / "tree_equity_score"
         self.df: gpd.GeoDataFrame
-        self.states =  ["al", "az", "ar", "ca", "co", "ct", "de", "dc", "fl", 
-        "ga", "id", "il", "in", "ia", "ks", "ky", "la", "me", 
-        "md", "ma", "mi", "mn", "ms", "mo", "mt", "ne", "nv", "nh", 
-        "nj", "nm", "ny", "nc", "nd", "oh", "ok", "or", "pa", 
-        "ri", "sc", "sd", "tn", "tx", "ut", "vt", "va", "wa", "wv", "wi", "wy"]
+        self.states = [
+            "al",
+            "az",
+            "ar",
+            "ca",
+            "co",
+            "ct",
+            "de",
+            "dc",
+            "fl",
+            "ga",
+            "id",
+            "il",
+            "in",
+            "ia",
+            "ks",
+            "ky",
+            "la",
+            "me",
+            "md",
+            "ma",
+            "mi",
+            "mn",
+            "ms",
+            "mo",
+            "mt",
+            "ne",
+            "nv",
+            "nh",
+            "nj",
+            "nm",
+            "ny",
+            "nc",
+            "nd",
+            "oh",
+            "ok",
+            "or",
+            "pa",
+            "ri",
+            "sc",
+            "sd",
+            "tn",
+            "tx",
+            "ut",
+            "vt",
+            "va",
+            "wa",
+            "wv",
+            "wi",
+            "wy",
+        ]
 
     def extract(self) -> None:
-        logger.info(f"Downloading Tree Equity Score Data")
+        logger.info("Downloading Tree Equity Score Data")
         for state in self.states:
             super().extract(
                 f"{self.TES_URL}{state}.zip.zip",
@@ -29,14 +76,14 @@ class TreeEquityScoreETL(ExtractTransformLoad):
             )
 
     def transform(self) -> None:
-        logger.info(f"Transforming Tree Equity Score Data")
+        logger.info("Transforming Tree Equity Score Data")
         tes_state_dfs = []
         for state in self.states:
             tes_state_dfs.append(gpd.read_file(f"{self.TMP_PATH}/{state}/{state}.shp"))
         self.df = gpd.GeoDataFrame(pd.concat(tes_state_dfs), crs=tes_state_dfs[0].crs)
 
     def load(self) -> None:
-        logger.info(f"Saving Tree Equity Score GeoJSON")
+        logger.info("Saving Tree Equity Score GeoJSON")
         # write nationwide csv
         self.CSV_PATH.mkdir(parents=True, exist_ok=True)
-        self.df.to_file(self.CSV_PATH / "tes_conus.geojson", driver='GeoJSON')
+        self.df.to_file(self.CSV_PATH / "tes_conus.geojson", driver="GeoJSON")