mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-02-24 18:44:20 -08:00
03a6d3c660
Update logging messages and message consistency This update includes changes to the level of many log messages. Rather than everything being logged at the info level, it differentiates between debug, info, warning, and error messages. It also changes the default log level to info to avoid much of the noise previously in the logs. It also removes many extra log messages, and adds additional decorators at the beginning of each pipeline run.
83 lines
3.1 KiB
Python
83 lines
3.1 KiB
Python
import pandas as pd
|
|
from data_pipeline.etl.base import ExtractTransformLoad
|
|
from data_pipeline.etl.base import 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,
|
|
# 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:
|
|
super().extract(
|
|
self.EJSCREEN_FTP_URL,
|
|
self.get_tmp_path(),
|
|
verify=False, # EPA EJScreen end point has certificate issues often
|
|
)
|
|
|
|
def transform(self) -> None:
|
|
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,
|
|
"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
|
|
},
|
|
)
|