publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 14:21:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove USVI and Guam territories from data and include/show on map American Samoa and Mariana Islands (#1248)

Browse source 
This updates the tile data so that guam and usvi do not appear in the tiles csv, from issue 1003
This commit is contained in:
Emma Nechamkin 2022-02-09 15:23:37 -05:00 • committed by GitHub
commit b86450c72b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 22 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
data/data-pipeline/data_pipeline/etl/score/constants.py
View file

@ -63,6 +63,9 @@ SCORE_DOWNLOADABLE_ZIP_FILE_PATH = (
# Column subsets
CENSUS_COUNTIES_COLUMNS = ["USPS", "GEOID", "NAME"]
# Drop FIPS codes from map
DROP_FIPS_CODES = ["66", "78"]
# Percent prefixes for rounding
PERCENT_PREFIXES_SUFFIXES = [
"Percent",

21
data/data-pipeline/data_pipeline/etl/score/etl_score_post.py
View file

@ -195,10 +195,11 @@ class PostScoreETL(ExtractTransformLoad):
return de_duplicated_df
def _create_tile_data(
self, score_county_state_merged_df: pd.DataFrame
self,
score_county_state_merged_df: pd.DataFrame,
) -> pd.DataFrame:
logger.info("Rounding Decimals")
logger.info("Rounding Decimals")
# grab all the keys from tiles score columns
tiles_score_column_titles = list(constants.TILES_SCORE_COLUMNS.keys())
@ -207,6 +208,22 @@ class PostScoreETL(ExtractTransformLoad):
tiles_score_column_titles
].copy()
# Currently, we do not want USVI or Guam on the map, so this will drop all
# rows with the FIPS codes (first two digits of the census tract)
logger.info(
f"Dropping specified FIPS codes from tile data: {constants.DROP_FIPS_CODES}"
)
tracts_to_drop = []
for fips_code in constants.DROP_FIPS_CODES:
tracts_to_drop += score_tiles[
score_tiles[field_names.GEOID_TRACT_FIELD].str.startswith(
fips_code
)
][field_names.GEOID_TRACT_FIELD].to_list()
score_tiles = score_tiles[
~score_tiles[field_names.GEOID_TRACT_FIELD].isin(tracts_to_drop)
]
score_tiles[constants.TILES_SCORE_FLOAT_COLUMNS] = score_tiles[
constants.TILES_SCORE_FLOAT_COLUMNS
].apply(