publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 14:11:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Prototype H (#682)

Browse source
This commit is contained in:
Lucas Merrill Brown 2021-09-14 16:16:41 -05:00 • committed by GitHub
commit 52e70653f0
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 213 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

28
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -161,6 +161,11 @@ class ScoreETL(ExtractTransformLoad):
renamed_field=self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME,
bucket=None,
),
DataSet(
input_field=self.MEDIAN_INCOME_FIELD_NAME,
renamed_field=self.MEDIAN_INCOME_FIELD_NAME,
bucket=None,
),
# The following data sets have buckets, because they're used in Score C
DataSet(
input_field="CANCER",
@ -540,6 +545,7 @@ class ScoreETL(ExtractTransformLoad):
logger.info("Adding Score G")
high_school_cutoff_threshold = 0.05
high_school_cutoff_threshold_2 = 0.06
df["Score G (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.7)
@ -551,6 +557,25 @@ class ScoreETL(ExtractTransformLoad):
df["Score G"] = df["Score G (communities)"].astype(int)
df["Score G (percentile)"] = df["Score G"]
df["Score H (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold_2)
) | (
(df[self.POVERTY_LESS_THAN_200_FPL_FIELD_NAME] > 0.40)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold_2)
)
df["Score H"] = df["Score H (communities)"].astype(int)
# df["80% AMI & 6% high school (communities)"] = (
# (df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
# & (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold_2)
# )
#
# df["FPL200>40% & 6% high school (communities)"] = (
# (df[self.POVERTY_LESS_THAN_200_FPL_FIELD_NAME] > 0.40)
# & (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold_2)
# )
df["NMTC (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
) | (
@ -637,7 +662,8 @@ class ScoreETL(ExtractTransformLoad):
# Skip GEOID_FIELD_NAME, because it's a string.
if data_set.renamed_field == self.GEOID_FIELD_NAME:
continue
df[f"{data_set.renamed_field}"] = pd.to_numeric(
df[data_set.renamed_field] = pd.to_numeric(
df[data_set.renamed_field]
)