publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 15:51:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updates backend constants to N (#1854)

Browse source
This commit is contained in:
Emma Nechamkin 2022-08-23 16:19:00 -04:00 • committed by GitHub
commit 6418335219
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
15 changed files with 1277 additions and 911 deletions
Download patch file Download diff file Expand all files Collapse all files

28
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -9,23 +9,6 @@ GEOID_TRACT_FIELD = "GEOID10_TRACT"
STATE_FIELD = "State/Territory"
COUNTY_FIELD = "County Name"
# Score file field names
# Definition M fields
SCORE_M = "Definition M"
FINAL_SCORE_N_BOOLEAN = (
"Definition M community, including adjacency index tracts"
)
SCORE_M_COMMUNITIES = "Definition M (communities)"
M_CLIMATE = "Climate Factor (Definition M)"
M_ENERGY = "Energy Factor (Definition M)"
M_TRANSPORTATION = "Transportation Factor (Definition M)"
M_HOUSING = "Housing Factor (Definition M)"
M_POLLUTION = "Pollution Factor (Definition M)"
M_WATER = "Water Factor (Definition M)"
M_HEALTH = "Health Factor (Definition M)"
M_WORKFORCE = "Workforce Factor (Definition M)"
M_NON_WORKFORCE = "Any Non-Workforce Factor (Definition M)"
# Definition Narwhal fields
SCORE_N = "Definition N (communities)"
SCORE_N_COMMUNITIES = "Definition N (communities)"
@ -38,6 +21,9 @@ N_WATER = "Water Factor (Definition N)"
N_HEALTH = "Health Factor (Definition N)"
N_WORKFORCE = "Workforce Factor (Definition N)"
N_NON_WORKFORCE = "Any Non-Workforce Factor (Definition N)"
FINAL_SCORE_N_BOOLEAN = (
"Definition N community, including adjacency index tracts"
)
PERCENTILE = 90
MEDIAN_HOUSE_VALUE_PERCENTILE = 90
@ -545,22 +531,22 @@ LOW_LIFE_EXPECTANCY_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
# Workforce
UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
" and has low HS education?"
" and has low HS attainment?"
)
LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households in linguistic isolation"
" and has low HS education?"
" and has low HS attainment?"
)
POVERTY_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
" and has low HS education?"
" and has low HS attainment?"
)
LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for low median household income as a "
f"percent of area median income and has low HS education?"
f"percent of area median income and has low HS attainment?"
)
# Score M Workforce Variables

3
data/data-pipeline/data_pipeline/score/score_runner.py
View file

@ -1,5 +1,4 @@
import pandas as pd
from data_pipeline.score.score_m import ScoreM
from data_pipeline.score.score_narwhal import ScoreNarwhal
from data_pipeline.utils import get_module_logger
@ -13,8 +12,6 @@ class ScoreRunner:
self.df = df
def calculate_scores(self) -> pd.DataFrame:
# Index scores
self.df = ScoreM(df=self.df).add_columns()
self.df = ScoreNarwhal(df=self.df).add_columns()
return self.df