publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-22 17:44:20 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tract Work Score Geo (#926)

Browse source
This commit is contained in:
Jorge Escobar 2021-11-29 10:38:47 -05:00 • committed by lucasmbrown-usds
parent cc7bf0d73d
commit 078bf6d8b6
1 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
data/data-pipeline/data_pipeline/etl/score/etl_score_geo.py
View file

@ -66,11 +66,17 @@ class GeoScoreETL(ExtractTransformLoad):
logger.info("Reading score CSV") logger.info("Reading score CSV")
self.score_usa_df = pd.read_csv( self.score_usa_df = pd.read_csv(
self.TILE_SCORE_CSV, self.TILE_SCORE_CSV,
dtype={"GEOID10": "string"}, dtype={self.GEOID_TRACT_FIELD_NAME: "string"},
low_memory=False, low_memory=False,
) )
def transform(self) -> None: 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") logger.info("Pruning Census GeoJSON")
fields = ["GEOID10", "geometry"] fields = ["GEOID10", "geometry"]
self.geojson_usa_df = self.geojson_usa_df[fields] self.geojson_usa_df = self.geojson_usa_df[fields]