mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-02-24 18:44:20 -08:00
5504528fdf
* 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
69 lines
2.6 KiB
Python
69 lines
2.6 KiB
Python
import pandas as pd
|
|
|
|
from etl.base import ExtractTransformLoad
|
|
from utils import get_module_logger
|
|
|
|
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.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_PRIORITY_COMMUNITY_FIELD_NAME = (
|
|
"calenviroscreen_priority_community"
|
|
)
|
|
|
|
# Choosing constants.
|
|
# None of these numbers are final, but just for the purposes of comparison.
|
|
self.CALENVIROSCREEN_PRIORITY_COMMUNITY_THRESHOLD = 75
|
|
|
|
self.df: pd.DataFrame
|
|
|
|
def extract(self) -> None:
|
|
logger.info("Downloading CalEnviroScreen Data")
|
|
super().extract(
|
|
self.CALENVIROSCREEN_FTP_URL,
|
|
self.TMP_PATH,
|
|
)
|
|
|
|
def transform(self) -> None:
|
|
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
|
|
# Load comparison index (CalEnviroScreen 4)
|
|
self.df = pd.read_csv(
|
|
self.CALENVIROSCREEN_CSV, dtype={"Census Tract": "string"}
|
|
)
|
|
|
|
self.df.rename(
|
|
columns={
|
|
"Census Tract": self.GEOID_TRACT_FIELD_NAME,
|
|
"DRAFT CES 4.0 Score": self.CALENVIROSCREEN_SCORE_FIELD_NAME,
|
|
"DRAFT CES 4.0 Percentile": self.CALENVIROSCREEN_PERCENTILE_FIELD_NAME,
|
|
},
|
|
inplace=True,
|
|
)
|
|
|
|
# Add a leading "0" to the Census Tract to match our format in other data frames.
|
|
self.df[self.GEOID_TRACT_FIELD_NAME] = (
|
|
"0" + self.df[self.GEOID_TRACT_FIELD_NAME]
|
|
)
|
|
|
|
# Calculate the top K% of prioritized communities
|
|
self.df[self.CALENVIROSCREEN_PRIORITY_COMMUNITY_FIELD_NAME] = (
|
|
self.df[self.CALENVIROSCREEN_PERCENTILE_FIELD_NAME]
|
|
>= self.CALENVIROSCREEN_PRIORITY_COMMUNITY_THRESHOLD
|
|
)
|
|
|
|
def load(self) -> None:
|
|
logger.info("Saving CalEnviroScreen CSV")
|
|
# write nationwide csv
|
|
self.CSV_PATH.mkdir(parents=True, exist_ok=True)
|
|
self.df.to_csv(self.CSV_PATH / "data06.csv", index=False)
|