mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-02-24 18:44:20 -08:00
876655d2b2
* Refactor CDC life-expectancy (1554) * Update to new tract list (#1554) * Adjust for tests (#1848) * Add tests for cdc_places (#1848) * Add EJScreen tests (#1848) * Add tests for HUD housing (#1848) * Add tests for GeoCorr (#1848) * Add persistent poverty tests (#1848) * Update for sources without zips, for new validation (#1848) * Update tests for new multi-CSV but (#1848) Lucas updated the CDC life expectancy data to handle a bug where two states are missing from the US Overall download. Since virtually none of our other ETL classes download multiple CSVs directly like this, it required a pretty invasive new mocking strategy. * Add basic tests for nature deprived (#1848) * Add wildfire tests (#1848) * Add flood risk tests (#1848) * Add DOT travel tests (#1848) * Add historic redlining tests (#1848) * Add tests for ME and WI (#1848) * Update now that validation exists (#1848) * Adjust for validation (#1848) * Add health insurance back to cdc places (#1848) Ooops * Update tests with new field (#1848) * Test for blank tract removal (#1848) * Add tracts for clipping behavior * Test clipping and zfill behavior (#1848) * Fix bad test assumption (#1848) * Simplify class, add test for tract padding (#1848) * Fix percentage inversion, update tests (#1848) Looking through the transformations, I noticed that we were subtracting a percentage that is usually between 0-100 from 1 instead of 100, and so were endind up with some surprising results. Confirmed with lucasmbrown-usds * Add note about first street data (#1848)
87 lines
3.3 KiB
Python
87 lines
3.3 KiB
Python
import pandas as pd
|
|
|
|
from data_pipeline.etl.base import ExtractTransformLoad, ValidGeoLevel
|
|
from data_pipeline.score import field_names
|
|
from data_pipeline.utils import get_module_logger
|
|
|
|
logger = get_module_logger(__name__)
|
|
|
|
|
|
class EJSCREENETL(ExtractTransformLoad):
|
|
"""Load updated EJSCREEN data."""
|
|
|
|
NAME = "ejscreen"
|
|
GEO_LEVEL: ValidGeoLevel = ValidGeoLevel.CENSUS_TRACT
|
|
INPUT_GEOID_TRACT_FIELD_NAME: str = "ID"
|
|
|
|
def __init__(self):
|
|
self.EJSCREEN_FTP_URL = "https://gaftp.epa.gov/EJSCREEN/2021/EJSCREEN_2021_USPR_Tracts.csv.zip"
|
|
self.EJSCREEN_CSV = (
|
|
self.get_tmp_path() / "EJSCREEN_2021_USPR_Tracts.csv"
|
|
)
|
|
self.CSV_PATH = self.DATA_PATH / "dataset" / "ejscreen"
|
|
self.df: pd.DataFrame
|
|
|
|
self.COLUMNS_TO_KEEP = [
|
|
self.GEOID_TRACT_FIELD_NAME,
|
|
field_names.TOTAL_POP_FIELD,
|
|
# pylint: disable=duplicate-code
|
|
field_names.AIR_TOXICS_CANCER_RISK_FIELD,
|
|
field_names.RESPIRATORY_HAZARD_FIELD,
|
|
field_names.DIESEL_FIELD,
|
|
field_names.PM25_FIELD,
|
|
field_names.OZONE_FIELD,
|
|
field_names.TRAFFIC_FIELD,
|
|
field_names.RMP_FIELD,
|
|
field_names.TSDF_FIELD,
|
|
field_names.NPL_FIELD,
|
|
field_names.WASTEWATER_FIELD,
|
|
field_names.HOUSEHOLDS_LINGUISTIC_ISO_FIELD,
|
|
field_names.POVERTY_FIELD,
|
|
field_names.OVER_64_FIELD,
|
|
field_names.UNDER_5_FIELD,
|
|
field_names.LEAD_PAINT_FIELD,
|
|
field_names.UST_FIELD,
|
|
]
|
|
|
|
def extract(self) -> None:
|
|
logger.info("Downloading EJScreen Data")
|
|
super().extract(
|
|
self.EJSCREEN_FTP_URL,
|
|
self.get_tmp_path(),
|
|
verify=False, # EPA EJScreen end point has certificate issues often
|
|
)
|
|
|
|
def transform(self) -> None:
|
|
logger.info("Transforming EJScreen Data")
|
|
self.df = pd.read_csv(
|
|
self.EJSCREEN_CSV,
|
|
dtype={self.INPUT_GEOID_TRACT_FIELD_NAME: str},
|
|
# EJSCREEN writes the word "None" for NA data.
|
|
na_values=["None"],
|
|
low_memory=False,
|
|
)
|
|
|
|
# rename ID to Tract ID
|
|
self.output_df = self.df.rename(
|
|
columns={
|
|
self.INPUT_GEOID_TRACT_FIELD_NAME: self.GEOID_TRACT_FIELD_NAME,
|
|
"ACSTOTPOP": field_names.TOTAL_POP_FIELD,
|
|
"CANCER": field_names.AIR_TOXICS_CANCER_RISK_FIELD,
|
|
"RESP": field_names.RESPIRATORY_HAZARD_FIELD,
|
|
"DSLPM": field_names.DIESEL_FIELD,
|
|
"PM25": field_names.PM25_FIELD,
|
|
"OZONE": field_names.OZONE_FIELD,
|
|
"PTRAF": field_names.TRAFFIC_FIELD,
|
|
"PRMP": field_names.RMP_FIELD,
|
|
"PTSDF": field_names.TSDF_FIELD,
|
|
"PNPL": field_names.NPL_FIELD,
|
|
"PWDIS": field_names.WASTEWATER_FIELD,
|
|
"LINGISOPCT": field_names.HOUSEHOLDS_LINGUISTIC_ISO_FIELD,
|
|
"LOWINCPCT": field_names.POVERTY_FIELD,
|
|
"OVER64PCT": field_names.OVER_64_FIELD,
|
|
"UNDER5PCT": field_names.UNDER_5_FIELD,
|
|
"PRE1960PCT": field_names.LEAD_PAINT_FIELD,
|
|
"UST": field_names.UST_FIELD, # added for 2021 update
|
|
},
|
|
)
|