publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-23 10:04:18 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add backfill data to score (#1851)

Browse source
This commit is contained in:
matt bowen 2022-09-27 10:15:22 -04:00
parent df317bfb37
commit ee97b65dda
1 changed files with 35 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -1,4 +1,6 @@
import functools
from typing import List
from dataclasses import dataclass
import numpy as np
@ -56,6 +58,8 @@ class ScoreETL(ExtractTransformLoad):
self.fuds_df: pd.DataFrame
self.tribal_overlap_df: pd.DataFrame
self.ISLAND_DEMOGRAPHIC_BACKFILL_FIELDS: List[str] = []
def extract(self) -> None:
logger.info("Loading data sets from disk.")
@ -402,6 +406,25 @@ class ScoreETL(ExtractTransformLoad):
df[field_names.MEDIAN_INCOME_FIELD] / df[field_names.AMI_FIELD]
)
self.ISLAND_DEMOGRAPHIC_BACKFILL_FIELDS = [
field_names.PERCENT_BLACK_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_AMERICAN_INDIAN_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_ASIAN_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_HAWAIIAN_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_TWO_OR_MORE_RACES_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_NON_HISPANIC_WHITE_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_HISPANIC_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
field_names.PERCENT_OTHER_RACE_FIELD_NAME
+ field_names.ISLAND_AREA_BACKFILL_SUFFIX,
]
# Donut columns get added later
numeric_columns = [
field_names.HOUSING_BURDEN_FIELD,
@ -471,7 +494,7 @@ class ScoreETL(ExtractTransformLoad):
field_names.PERCENT_AGE_OVER_64,
field_names.PERCENT_OF_TRIBAL_AREA_IN_TRACT,
field_names.COUNT_OF_TRIBAL_AREAS_IN_TRACT,
]
] + self.ISLAND_DEMOGRAPHIC_BACKFILL_FIELDS
non_numeric_columns = [
self.GEOID_TRACT_FIELD_NAME,
@ -639,14 +662,23 @@ class ScoreETL(ExtractTransformLoad):
return df_copy
@staticmethod
def _backfill_island_data(df: pd.DataFrame) -> pd.DataFrame:
def _backfill_island_data(self, df: pd.DataFrame) -> pd.DataFrame:
logger.info("Backfilling island data")
island_index = (
df[field_names.GEOID_TRACT_FIELD]
.str[:2]
.isin(constants.TILES_ISLAND_AREA_FIPS_CODES)
)
for backfill_field_name in self.ISLAND_DEMOGRAPHIC_BACKFILL_FIELDS:
actual_field_name = backfill_field_name.replace(
field_names.ISLAND_AREA_BACKFILL_SUFFIX, ""
)
df.loc[island_index, actual_field_name] = df.loc[
island_index, backfill_field_name
]
df = df.drop(columns=self.ISLAND_DEMOGRAPHIC_BACKFILL_FIELDS)
df.loc[island_index, field_names.TOTAL_POP_FIELD] = df.loc[
island_index, field_names.COMBINED_CENSUS_TOTAL_POPULATION_2010
]