publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-08-05 23:24:18 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

wip

Browse source
This commit is contained in:
lucasmbrown-usds 2022-09-28 17:02:54 -04:00
commit a7a4df037e
3 changed files with 29 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
data/data-pipeline/data_pipeline/etl/score/constants.py
View file

@ -58,6 +58,10 @@ SCORE_DOWNLOADABLE_CSV_FILE_PATH = (
SCORE_DOWNLOADABLE_EXCEL_FILE_PATH = (
SCORE_DOWNLOADABLE_DIR / f"communities-{timestamp_str}.xlsx"
)
ZIP_CODES_DOWNLOADABLE_CSV_FILE_PATH = (
SCORE_DOWNLOADABLE_DIR
/ f"communities-compared-to-zip-codes-{timestamp_str}.csv"
)
SCORE_DOWNLOADABLE_CODEBOOK_FILE_PATH = (
SCORE_DOWNLOADABLE_DIR / f"codebook-{timestamp_str}.csv"
)

6
data/data-pipeline/data_pipeline/etl/score/etl_score_post.py
View file

@ -387,6 +387,9 @@ class PostScoreETL(ExtractTransformLoad):
return final_df
def _create_zip_codes_data(self, downloadable_df):
pass
def transform(self) -> None:
logger.info("Transforming data sources for Score + County CSVs")
@ -543,6 +546,9 @@ class PostScoreETL(ExtractTransformLoad):
codebook_df.to_csv(codebook_path, index=False)
# TODO: Write zip-code based files
zip_codes_df = self._create_zip_codes_data(
downloadable_df=downloadable_df
)
logger.info("Compressing files")
files_to_compress = [