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

Hot fix for Score M (#1182)

Browse source 
* fixes

* pr feedback

* tuple
This commit is contained in:
Jorge Escobar 2022-01-27 17:22:39 -05:00 • committed by GitHub
commit 2b35a8937a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 9 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

19
data/data-pipeline/data_pipeline/etl/score/etl_score_post.py
View file

@ -17,6 +17,9 @@ from . import constants
logger = get_module_logger(__name__)
# Define the DAC variable
DISADVANTAGED_COMMUNITIES_FIELD = field_names.SCORE_M_COMMUNITIES
class PostScoreETL(ExtractTransformLoad):
"""
@ -184,17 +187,9 @@ class PostScoreETL(ExtractTransformLoad):
merged_df["Total population"].fillna(0.0).astype(int)
)
# list the null score tracts
null_tract_df = merged_df[
merged_df[field_names.SCORE_L_COMMUNITIES].isnull()
]
# subtract data sets
# this follows the XOR pattern outlined here:
# https://stackoverflow.com/a/37313953
de_duplicated_df = pd.concat(
[merged_df, null_tract_df, null_tract_df]
).drop_duplicates(keep=False)
de_duplicated_df = merged_df.dropna(
subset=[DISADVANTAGED_COMMUNITIES_FIELD]
)
# set the score to the new df
return de_duplicated_df
@ -333,7 +328,7 @@ class PostScoreETL(ExtractTransformLoad):
# Rename score column
downloadable_df_copy = downloadable_df.rename(
columns={
field_names.SCORE_M_COMMUNITIES: "Identified as disadvantaged (v0.1)"
DISADVANTAGED_COMMUNITIES_FIELD: "Identified as disadvantaged (v0.1)"
},
inplace=False,
)