publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 12:31:18 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updating higher education to be reversed (#1387)

Browse source 
Summary In this PR, we create a new variable so that the % college students is expressed as % not college students. This means that the front end can display % not college students.

Includes old variables so that this will not break fe.
This commit is contained in:
Emma Nechamkin 2022-03-15 16:43:32 -04:00 • committed by GitHub
commit e7c7c0abeb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
12 changed files with 30 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

7
data/data-pipeline/data_pipeline/etl/sources/census_acs/etl.py
View file

@ -136,6 +136,8 @@ class CensusACSETL(ExtractTransformLoad):
"Percent enrollment in college or graduate school"
)
self.COLLEGE_NON_ATTENDANCE_FIELD = "Percent of population not currently enrolled in college or graduate school"
self.RE_FIELDS = [
"B02001_001E",
"B02001_002E",
@ -190,6 +192,7 @@ class CensusACSETL(ExtractTransformLoad):
self.MEDIAN_HOUSE_VALUE_FIELD_NAME,
self.HIGH_SCHOOL_ED_FIELD,
self.COLLEGE_ATTENDANCE_FIELD,
self.COLLEGE_NON_ATTENDANCE_FIELD,
]
+ self.RE_OUTPUT_FIELDS
+ [self.PERCENT_PREFIX + field for field in self.RE_OUTPUT_FIELDS]
@ -354,6 +357,10 @@ class CensusACSETL(ExtractTransformLoad):
+ df[self.COLLEGE_ATTENDANCE_FEMALE_ENROLLED_PRIVATE]
) / df[self.COLLEGE_ATTENDANCE_TOTAL_POPULATION_ASKED]
df[self.COLLEGE_NON_ATTENDANCE_FIELD] = (
1 - df[self.COLLEGE_ATTENDANCE_FIELD]
)
# strip columns
df = df[self.COLUMNS_TO_KEEP]