mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-07-29 18:11:17 -07:00
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
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
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
|
|
|
|
logger = get_module_logger(__name__)
|
|
|
|
|
|
class HousingTransportationETL(ExtractTransformLoad):
|
|
def __init__(self):
|
|
self.HOUSING_FTP_URL = (
|
|
"https://htaindex.cnt.org/download/download.php?focus=blkgrp&geoid="
|
|
)
|
|
self.OUTPUT_PATH = (
|
|
self.DATA_PATH / "dataset" / "housing_and_transportation_index"
|
|
)
|
|
self.df: pd.DataFrame
|
|
|
|
def extract(self) -> None:
|
|
# Download each state / territory individually
|
|
dfs = []
|
|
zip_file_dir = self.TMP_PATH / "housing_and_transportation_index"
|
|
for fips in get_state_fips_codes(self.DATA_PATH):
|
|
logger.info(
|
|
f"Downloading housing data for state/territory with FIPS code {fips}"
|
|
)
|
|
|
|
# Puerto Rico has no data, so skip
|
|
if fips == "72":
|
|
continue
|
|
|
|
unzip_file_from_url(
|
|
f"{self.HOUSING_FTP_URL}{fips}", self.TMP_PATH, zip_file_dir
|
|
)
|
|
|
|
# New file name:
|
|
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)
|
|
|
|
self.df = pd.concat(dfs)
|
|
|
|
def transform(self) -> None:
|
|
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(
|
|
'"', ""
|
|
)
|
|
|
|
def load(self) -> None:
|
|
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)
|