Update downloadable zip file (#659)

* Update downloadable zip file

* Don't use spaces in the name, as per #620
* Add the score D columns, as per #596

* fix paths and directories in etl_score_post

while the tests seemed to  be passing, I encountered an error when
running poetry run score, which was caused by us creating a directory
called <name>.csv, instead of creating the parent directory.

Co-authored-by: Shelby Switzer <shelby.switzer@cms.hhs.gov>

data/data-pipeline/data_pipeline/etl/score/constants.py

@@ -39,7 +39,7 @@ DATA_SCORE_TILES_FILE_PATH = DATA_SCORE_TILES_DIR / "usa.csv"
 SCORE_DOWNLOADABLE_DIR = DATA_SCORE_DIR / "downloadable"
 SCORE_DOWNLOADABLE_CSV_FILE_PATH = SCORE_DOWNLOADABLE_DIR / "usa.csv"
 SCORE_DOWNLOADABLE_EXCEL_FILE_PATH = SCORE_DOWNLOADABLE_DIR / "usa.xlsx"
-SCORE_DOWNLOADABLE_ZIP_FILE_PATH = SCORE_DOWNLOADABLE_DIR / "Screening Tool Data.zip"
+SCORE_DOWNLOADABLE_ZIP_FILE_PATH = SCORE_DOWNLOADABLE_DIR / "Screening_Tool_Data.zip"
 
 # Column subsets
 CENSUS_COUNTIES_COLUMNS = ["USPS", "GEOID", "NAME"]
@@ -104,5 +104,7 @@ DOWNLOADABLE_SCORE_COLUMNS = [
     "GEOID10",
     "County Name",
     "State Name",
+    "Score D (percentile)",
+    "Score D (top 25th percentile)",
     *DOWNLOADABLE_SCORE_INDICATOR_COLUMNS_FULL,
 ]

data/data-pipeline/data_pipeline/etl/score/etl_score_post.py

@@ -219,9 +219,7 @@ class PostScoreETL(ExtractTransformLoad):
         self, score_tiles_df: pd.DataFrame, tile_score_path: Path
     ) -> None:
         logger.info("Saving Tile Score CSV")
-        # TODO: check which are the columns we'll use
-        # Related to: https://github.com/usds/justice40-tool/issues/302
-        tile_score_path.mkdir(parents=True, exist_ok=True)
+        tile_score_path.parent.mkdir(parents=True, exist_ok=True)
         score_tiles_df.to_csv(tile_score_path, index=False)
 
     def _load_downloadable_zip(
@@ -230,9 +228,9 @@ class PostScoreETL(ExtractTransformLoad):
         logger.info("Saving Downloadable CSV")
 
         downloadable_info_path.mkdir(parents=True, exist_ok=True)
-        csv_path = downloadable_info_path / "usa.csv"
-        excel_path = downloadable_info_path / "usa.xlsx"
-        zip_path = downloadable_info_path / "Screening Tool Data.zip"
+        csv_path = constants.SCORE_DOWNLOADABLE_CSV_FILE_PATH
+        excel_path = constants.SCORE_DOWNLOADABLE_EXCEL_FILE_PATH
+        zip_path = constants.SCORE_DOWNLOADABLE_ZIP_FILE_PATH
 
         logger.info("Writing downloadable csv")
         downloadable_df.to_csv(csv_path, index=False)