mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-02-24 18:44:20 -08:00
842312f69f
* first commit * checkpoint * checkpoint * first extract module 🎉 * completed census acs etl class * completed ejscreen etl * completed etl * score generation ready * improving census load and separation * score generation working 🎉 * completed etls * new score generation * PR reviews * run specific etl; starting docstrings * docstrings work * more docstrings * completed docstrings * adding pyenv version * more reasonable poetry req for python * PR comments
39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
import pandas as pd
|
|
|
|
from etl.base import ExtractTransformLoad
|
|
from utils import get_module_logger
|
|
|
|
logger = get_module_logger(__name__)
|
|
|
|
|
|
class EJScreenETL(ExtractTransformLoad):
|
|
def __init__(self):
|
|
self.EJSCREEN_FTP_URL = (
|
|
"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip"
|
|
)
|
|
self.EJSCREEN_CSV = self.TMP_PATH / "EJSCREEN_2020_StatePctile.csv"
|
|
self.CSV_PATH = self.DATA_PATH / "dataset" / "ejscreen_2020"
|
|
self.df: pd.DataFrame
|
|
|
|
def extract(self) -> None:
|
|
logger.info(f"Downloading EJScreen Data")
|
|
super().extract(
|
|
self.EJSCREEN_FTP_URL,
|
|
self.TMP_PATH,
|
|
)
|
|
|
|
def transform(self) -> None:
|
|
logger.info(f"Transforming EJScreen Data")
|
|
self.df = pd.read_csv(
|
|
self.EJSCREEN_CSV,
|
|
dtype={"ID": "string"},
|
|
# EJSCREEN writes the word "None" for NA data.
|
|
na_values=["None"],
|
|
low_memory=False,
|
|
)
|
|
|
|
def load(self) -> None:
|
|
logger.info(f"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)
|