Fast flag update (#1844)

Added additional flags for the front end based on our conversation in stand up this morning.
This commit is contained in:
Emma Nechamkin 2022-08-19 13:14:44 -04:00 committed by GitHub
commit d892bce6cf
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
14 changed files with 63 additions and 31 deletions

View file

@ -208,9 +208,10 @@ TILES_SCORE_COLUMNS = {
field_names.M_HEALTH: "M_HLTH",
# temporarily update this so that it's the Narwhal score that gets visualized on the map
# The NEW final score value INCLUDES the adjacency index.
field_names.SCORE_N_COMMUNITIES + field_names.ADJACENT_MEAN_SUFFIX: "SM_C",
field_names.FINAL_SCORE_N_BOOLEAN: "SM_C",
field_names.SCORE_N_COMMUNITIES
+ field_names.PERCENTILE_FIELD_SUFFIX: "SM_PFS",
+ field_names.ADJACENT_MEAN_SUFFIX: "SM_DON",
field_names.SCORE_N_COMMUNITIES: "SM_NO_DON",
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EPLRLI",
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EALRLI",
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EBLRLI",
@ -313,7 +314,8 @@ TILES_SCORE_COLUMNS = {
+ field_names.PERCENTILE_FIELD_SUFFIX: "IS_PFS",
field_names.NON_NATURAL_LOW_INCOME_FIELD_NAME: "IS_ET",
field_names.AML_BOOLEAN: "AML_ET",
field_names.ELIGIBLE_FUDS_BINARY_FIELD_NAME: "FUDS_ET"
field_names.ELIGIBLE_FUDS_BINARY_FIELD_NAME: "FUDS_ET",
field_names.IMPUTED_INCOME_FLAG_FIELD_NAME: "IMP_FLG"
## FPL 200 and low higher ed for all others should no longer be M_EBSI, but rather
## FPL_200 (there is no higher ed in narwhal)
}

View file

@ -471,6 +471,7 @@ class ScoreETL(ExtractTransformLoad):
field_names.AGRICULTURAL_VALUE_BOOL_FIELD,
field_names.ELIGIBLE_FUDS_BINARY_FIELD_NAME,
field_names.AML_BOOLEAN,
field_names.IMPUTED_INCOME_FLAG_FIELD_NAME,
]
# For some columns, high values are "good", so we want to reverse the percentile

View file

@ -521,8 +521,6 @@ class PostScoreETL(ExtractTransformLoad):
score_tiles_df.to_csv(tile_score_path, index=False, encoding="utf-8")
def _load_downloadable_zip(self, downloadable_info_path: Path) -> None:
logger.info("Saving Downloadable CSV")
downloadable_info_path.mkdir(parents=True, exist_ok=True)
csv_path = constants.SCORE_DOWNLOADABLE_CSV_FILE_PATH
excel_path = constants.SCORE_DOWNLOADABLE_EXCEL_FILE_PATH

File diff suppressed because one or more lines are too long

View file

@ -227,6 +227,7 @@ class CensusACSETL(ExtractTransformLoad):
self.COLLEGE_ATTENDANCE_FIELD,
self.COLLEGE_NON_ATTENDANCE_FIELD,
self.IMPUTED_COLLEGE_ATTENDANCE_FIELD,
field_names.IMPUTED_INCOME_FLAG_FIELD_NAME,
]
+ self.RE_OUTPUT_FIELDS
+ [self.PERCENT_PREFIX + field for field in self.RE_OUTPUT_FIELDS]
@ -503,6 +504,13 @@ class CensusACSETL(ExtractTransformLoad):
}
)
# We generate a boolean that is TRUE when there is an imputed income but not a baseline income, and FALSE otherwise.
# This allows us to see which tracts have an imputed income.
df[field_names.IMPUTED_INCOME_FLAG_FIELD_NAME] = (
df[field_names.POVERTY_LESS_THAN_200_FPL_IMPUTED_FIELD].notna()
& df[field_names.POVERTY_LESS_THAN_200_FPL_FIELD].isna()
)
# Strip columns and save results to self.
self.df = df[self.COLUMNS_TO_KEEP]

View file

@ -92,12 +92,17 @@ def calculate_income_measures(
)
# Iterate through the dataframe to impute in place
## TODO: We should probably convert this to a spatial join now that we are doing >1 imputation and it's taking a lot
## of time, but thinking through how to do this while maintaining the masking will take some time. I think the best
## way would be to (1) spatial join to all neighbors, and then (2) iterate to take the "smallest" set of neighbors...
## but haven't implemented it yet.
for index, row in geo_df.iterrows():
if row[geoid_field] in tract_list:
neighbor_mask = _get_neighbor_mask(geo_df, row)
county_mask = _get_fips_mask(
geo_df=geo_df, row=row, fips_digits=5, geoid_field=geoid_field
)
## TODO: Did CEQ decide to cut this?
state_mask = _get_fips_mask(
geo_df=geo_df, row=row, fips_digits=2, geoid_field=geoid_field
)