publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 09:11:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updating traffic barriers to include low pop threshold (#1889)

Browse source 
Changing the traffic barriers to only be included for places with recorded population
This commit is contained in:
Emma Nechamkin 2022-09-07 17:13:31 -04:00 • committed by GitHub
commit 426328e378
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

17
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -380,7 +380,8 @@ class ScoreETL(ExtractTransformLoad):
), "Join against national tract list ADDED rows" ), "Join against national tract list ADDED rows"
logger.info( logger.info(
"Dropped %s tracts not in the 2010 tract data", "Dropped %s tracts not in the 2010 tract data",
pre_join_len - census_tract_df[field_names.GEOID_TRACT_FIELD].nunique() pre_join_len
- census_tract_df[field_names.GEOID_TRACT_FIELD].nunique(),
) )
# Now sanity-check the merged df. # Now sanity-check the merged df.
@ -551,6 +552,9 @@ class ScoreETL(ExtractTransformLoad):
# For *Non-Natural Space*, we may only want to include tracts that have at least 35 acreas, I think. This will # For *Non-Natural Space*, we may only want to include tracts that have at least 35 acreas, I think. This will
# get rid of tracts that we think are aberrations statistically. Right now, we have left this out # get rid of tracts that we think are aberrations statistically. Right now, we have left this out
# pending ground-truthing. # pending ground-truthing.
#
# For *Traffic Barriers*, we want to exclude low population tracts, which may have high burden because they are
# low population alone. We set this low population constant in the if statement.
for numeric_column in numeric_columns: for numeric_column in numeric_columns:
drop_tracts = [] drop_tracts = []
@ -575,6 +579,17 @@ class ScoreETL(ExtractTransformLoad):
f"Dropping {len(drop_tracts)} tracts from Linguistic Isolation" f"Dropping {len(drop_tracts)} tracts from Linguistic Isolation"
) )
elif numeric_column == field_names.DOT_TRAVEL_BURDEN_FIELD:
# Not having any people appears to be correlated with transit burden, but also doesn't represent
# on the ground need. For now, we remove these tracts from the percentile calculation. (To be QAed live)
low_population = 20
drop_tracts = df_copy[
df_copy[field_names.TOTAL_POP_FIELD] <= low_population
][field_names.GEOID_TRACT_FIELD].to_list()
logger.info(
f"Dropping {len(drop_tracts)} tracts from DOT traffic burden"
)
df_copy = self._add_percentiles_to_df( df_copy = self._add_percentiles_to_df(
df=df_copy, df=df_copy,
input_column_name=numeric_column, input_column_name=numeric_column,