publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-23 01:54:18 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

updating

Browse source
This commit is contained in:
Emma Nechamkin 2022-07-13 09:56:09 -04:00
parent 2e38aaa369
commit 92d68ba8be
1 changed files with 26 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

49
data/data-pipeline/data_pipeline/score/score_narwhal.py
View file

@ -314,16 +314,17 @@ class ScoreNarwhal(Score):
housing_eligibility_columns = [ housing_eligibility_columns = [
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD, field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD,
field_names.HOUSING_BURDEN_LOW_INCOME_FIELD, field_names.HOUSING_BURDEN_LOW_INCOME_FIELD,
field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD, # Until we get confirmation -- NOT included
# field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD,
] ]
# design question -- should read in scalar with threshold here instead? # # design question -- should read in scalar with threshold here instead?
self.df[ # self.df[
field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD # field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD
] = ( # ] = (
self.df[field_names.HISTORIC_REDLINING_SCORE_EXCEEDED] # self.df[field_names.HISTORIC_REDLINING_SCORE_EXCEEDED]
& self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED] # & self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
) # )
self.df[field_names.LEAD_PAINT_PROXY_PCTILE_THRESHOLD] = ( self.df[field_names.LEAD_PAINT_PROXY_PCTILE_THRESHOLD] = (
self.df[ self.df[
@ -639,7 +640,10 @@ class ScoreNarwhal(Score):
) )
| ( | (
self.df[field_names.LINGUISTIC_ISOLATION_PCTILE_THRESHOLD] self.df[field_names.LINGUISTIC_ISOLATION_PCTILE_THRESHOLD]
& (self.df[field_names.GEOID_TRACT_FIELD].str[:2] != constants.TILES_PUERTO_RICO_FIPS_CODE[0] ) & (
self.df[field_names.GEOID_TRACT_FIELD].str[:2]
!= constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
) )
) )
@ -647,21 +651,16 @@ class ScoreNarwhal(Score):
# otherwise use all criteria. # otherwise use all criteria.
workforce_combined_criteria_for_states = ( workforce_combined_criteria_for_states = (
( (
( self.df[field_names.GEOID_TRACT_FIELD].str[:2]
self.df[field_names.GEOID_TRACT_FIELD].str[:2] == constants.TILES_PUERTO_RICO_FIPS_CODE[0] == constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
&
self.df[pr_workforce_eligibility_columns].any(axis="columns")
) )
| & self.df[pr_workforce_eligibility_columns].any(axis="columns")
) | (
( (
( self.df[field_names.GEOID_TRACT_FIELD].str[:2]
self.df[field_names.GEOID_TRACT_FIELD].str[:2] != constants.TILES_PUERTO_RICO_FIPS_CODE[0] != constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
& self.df[
workforce_eligibility_columns
].any(axis="columns")
) )
& self.df[workforce_eligibility_columns].any(axis="columns")
) )
self._increment_total_eligibility_exceeded( self._increment_total_eligibility_exceeded(
@ -793,7 +792,10 @@ class ScoreNarwhal(Score):
) )
| ( | (
self.df[field_names.LINGUISTIC_ISOLATION_PCTILE_THRESHOLD] self.df[field_names.LINGUISTIC_ISOLATION_PCTILE_THRESHOLD]
& ( self.df[field_names.GEOID_TRACT_FIELD].str[:2] != constants.TILES_PUERTO_RICO_FIPS_CODE[0] ) & (
self.df[field_names.GEOID_TRACT_FIELD].str[:2]
!= constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
) )
) | ( ) | (
## then we calculate just for the island areas ## then we calculate just for the island areas
@ -859,7 +861,8 @@ class ScoreNarwhal(Score):
self.df[field_names.CATEGORY_COUNT] = self.df[factors].sum(axis=1) self.df[field_names.CATEGORY_COUNT] = self.df[factors].sum(axis=1)
self.df[field_names.SCORE_N_COMMUNITIES] = self.df[factors].any(axis=1) self.df[field_names.SCORE_N_COMMUNITIES] = self.df[factors].any(axis=1)
self.df[ self.df[
field_names.SCORE_N_COMMUNITIES + field_names.PERCENTILE_FIELD_SUFFIX field_names.SCORE_N_COMMUNITIES
+ field_names.PERCENTILE_FIELD_SUFFIX
] = self.df[field_names.SCORE_N_COMMUNITIES].astype(int) ] = self.df[field_names.SCORE_N_COMMUNITIES].astype(int)
return self.df return self.df