Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Emma nechamkin/holc patch #1742

Merged
merged 3 commits into from
Jul 15, 2022
Merged

Emma nechamkin/holc patch #1742

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3ef5192
updating
emma-nechamkin Jul 13, 2022
f6e161f
Merge branch 'emma-nechamkin/release/score-narwhal' of github.com:usd…
emma-nechamkin Jul 13, 2022
7cccbb3
updating holc part of the code, sorry for defying branch naming conve…
emma-nechamkin Jul 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 27 additions & 23 deletions data/data-pipeline/data_pipeline/score/score_narwhal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -314,16 +314,18 @@ def _housing_factor(self) -> bool:
housing_eligibility_columns = [
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_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
# Updated in a patch
# field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD,
]

# design question -- should read in scalar with threshold here instead?
self.df[
field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD
] = (
self.df[field_names.HISTORIC_REDLINING_SCORE_EXCEEDED]
& self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
)
# # design question -- should read in scalar with threshold here instead?
# self.df[
# field_names.HISTORIC_REDLINING_SCORE_EXCEEDED_LOW_INCOME_FIELD
# ] = (
# self.df[field_names.HISTORIC_REDLINING_SCORE_EXCEEDED]
# & self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
# )

self.df[field_names.LEAD_PAINT_PROXY_PCTILE_THRESHOLD] = (
self.df[
Expand Down Expand Up @@ -639,29 +641,27 @@ def _workforce_factor(self) -> bool:
)
| (
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]
)
)
)

# Use only PR combined criteria for rows with PR FIPS code;
# otherwise use all criteria.
workforce_combined_criteria_for_states = (
(
(
self.df[field_names.GEOID_TRACT_FIELD].str[:2] == constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
&
self.df[pr_workforce_eligibility_columns].any(axis="columns")
self.df[field_names.GEOID_TRACT_FIELD].str[:2]
== constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
|
& self.df[pr_workforce_eligibility_columns].any(axis="columns")
) | (
(
(
self.df[field_names.GEOID_TRACT_FIELD].str[:2] != constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
& self.df[
workforce_eligibility_columns
].any(axis="columns")
self.df[field_names.GEOID_TRACT_FIELD].str[:2]
!= constants.TILES_PUERTO_RICO_FIPS_CODE[0]
)
& self.df[workforce_eligibility_columns].any(axis="columns")
)

self._increment_total_eligibility_exceeded(
Expand Down Expand Up @@ -793,7 +793,10 @@ def _workforce_factor(self) -> bool:
)
| (
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
Expand Down Expand Up @@ -859,7 +862,8 @@ def add_columns(self) -> pd.DataFrame:
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 + field_names.PERCENTILE_FIELD_SUFFIX
field_names.SCORE_N_COMMUNITIES
+ field_names.PERCENTILE_FIELD_SUFFIX
] = self.df[field_names.SCORE_N_COMMUNITIES].astype(int)

return self.df