From 078bf6d8b6ffd0d491da200183ed2998d38a91dc Mon Sep 17 00:00:00 2001 From: Jorge Escobar <83969469+esfoobar-usds@users.noreply.github.com> Date: Mon, 29 Nov 2021 10:38:47 -0500 Subject: [PATCH] Tract Work Score Geo (#926) --- .../data_pipeline/etl/score/etl_score_geo.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/data/data-pipeline/data_pipeline/etl/score/etl_score_geo.py b/data/data-pipeline/data_pipeline/etl/score/etl_score_geo.py index ecb2b46e..edb11e68 100644 --- a/data/data-pipeline/data_pipeline/etl/score/etl_score_geo.py +++ b/data/data-pipeline/data_pipeline/etl/score/etl_score_geo.py @@ -66,11 +66,17 @@ class GeoScoreETL(ExtractTransformLoad): logger.info("Reading score CSV") self.score_usa_df = pd.read_csv( self.TILE_SCORE_CSV, - dtype={"GEOID10": "string"}, + dtype={self.GEOID_TRACT_FIELD_NAME: "string"}, low_memory=False, ) def transform(self) -> None: + # rename GEOID10_TRACT to GEOID10 on score to allow merging with Census GeoJSON + self.score_usa_df.rename( + columns={self.GEOID_TRACT_FIELD_NAME: "GEOID10"}, + inplace=True, + ) + logger.info("Pruning Census GeoJSON") fields = ["GEOID10", "geometry"] self.geojson_usa_df = self.geojson_usa_df[fields]