Skip to content

Commit

Permalink
Fix: Use Population Percentage Instead of Raw Population Counts (#3186)
Browse files Browse the repository at this point in the history 
Fix #3185: Use population percentage for relative inequity calculations and update docstring placement.
  • Loading branch information
@eriwarr
eriwarr committed Apr 23, 2024
1 parent ddf9acd commit 6851562
Show file tree
Hide file tree
Showing 3 changed files with 573 additions and 581 deletions.
66 changes: 29 additions & 37 deletions python/datasources/cdc_wisqars_youth.py
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,30 @@
"""
This documentation outlines the procedure for acquiring gun violence data for the youth/young adult
population from the CDC WISQARS database. The data, once downloaded, is stored locally in
the `data/cdc_wisqars` directory for further processing and analysis.
Instructions for Downloading Data:
1. Access the WISQARS website at https://wisqars.cdc.gov/reports/.
2. Select `Fatal` as the injury outcome.
3. Specify the data years of interest, from `2018-2021 by Single Race`.
4. Set geography to `United States`.
5. Choose `All Intents` for the intent.
6. Under mechanism, opt for `Firearm`.
7. For youth demographics, select `Custom Age Range: <1 to 17`, `Both Sexes`, `All Races`.
8. For youth demographics, select `Custom Age Range: 18 to 25`, `Both Sexes`, `All Races`.
9. Decide on the report layout based on your requirements:
- For youth-national-all: `Intent`, `None`, `None`, `None`
- For youth-national-race: `Intent`, `Race`, `Ethnicity`, `None`
- For youth-state-all: `Intent`, `State`, `None`, `None`
- For youth-state-race: `Intent`, `State`, `Race`, `Ethnicity`
Notes:
- There is no county-level data.
- Race data is provided only for fatal data outcomes and covers the period from 2018-2021.
Last Updated: 4/23
"""

import pandas as pd

from datasources.data_source import DataSource
Expand All @@ -24,41 +51,6 @@
)
from ingestion.merge_utils import merge_state_ids

"""
Data Source: CDC WISQARS Youth (data on gun violence)
Description:
- The data on gun violence by youth and race is downloaded from the CDC WISQARS database.
- The downloaded data is stored locally in our data/cdc_wisqars directory for subsequent use.
Instructions for Downloading Data:
1. Visit the WISQARS website: https://wisqars.cdc.gov/reports/
2. Select the injury outcome:
- `Fatal`
3. Select the year and race options:
- `2018-2021 by Single Race`
4. Select the desired data years:
- `2018-2021`
5. Select the geography:
- `United States`
6. Select the intent:
- `All Intents`
7. Select the mechanism:
- `Firearm`
8. Select the demographic selections:
- `Custom Age Range: <1 to Unknown`, `Both Sexes`, `All Races`
5. Select appropriate report layout:
- For youth-national-all: `Intent`, `None`, `None`, `None`
- For youth-national-race: `Intent`, `Race`, `Ethnicity`, `None`
- For youth-state-all: `Intent`, `State`, `None`, `None`
- For youth-state-race: `Intent`, `State`, `Race`, `Ethnicity`
Notes:
- There is no county-level data.
- Race data is only available for fatal data and is available from 2018-2021.
Last Updated: 2/24
"""

CATEGORIES_LIST = [std_col.GUN_DEATHS_YOUNG_ADULTS_PREFIX, std_col.GUN_DEATHS_YOUTH_PREFIX]
ESTIMATED_TOTALS_MAP = generate_cols_map(CATEGORIES_LIST, std_col.RAW_SUFFIX)
PCT_REL_INEQUITY_MAP = generate_cols_map(ESTIMATED_TOTALS_MAP.values(), std_col.PCT_REL_INEQUITY_SUFFIX)
Expand Down Expand Up @@ -131,9 +123,9 @@ def generate_breakdown_df(self, breakdown: str, geo_level: str, alls_df: pd.Data

for col in ESTIMATED_TOTALS_MAP.values():
pop_col = (
std_col.GUN_DEATHS_YOUNG_ADULTS_POPULATION
std_col.GUN_DEATHS_YOUNG_ADULTS_POP_PCT
if col == std_col.GUN_DEATHS_YOUNG_ADULTS_PREFIX
else std_col.GUN_DEATHS_YOUTH_POPULATION
else std_col.GUN_DEATHS_YOUTH_POP_PCT
)
df = generate_pct_rel_inequity_col(df, PCT_SHARE_MAP[col], pop_col, PCT_REL_INEQUITY_MAP[col])

Expand Down
58 changes: 29 additions & 29 deletions ...on/tests/data/cdc_wisqars/golden_data/youth_by_race_and_ethnicity_national_historical.csv
View file
Original file line number Diff line number Diff line change
@@ -1,37 +1,37 @@
time_period,state_name,state_fips,race_and_ethnicity,gun_deaths_young_adults_pct_relative_inequity,gun_deaths_youth_pct_relative_inequity,gun_deaths_young_adults_pct_share,gun_deaths_youth_pct_share,gun_deaths_young_adults_per_100k,gun_deaths_youth_per_100k
2018,United States,00,American Indian and Alaska Native (NH),-100.0,,1.2,,28.56,
2018,United States,00,Asian (NH),-100.0,-100.0,1.2,2.4,4.23,1.03
2018,United States,00,Black or African American (NH),-100.0,-100.0,43.3,36.0,60.86,6.03
2018,United States,00,Hispanic or Latino,-100.0,-100.0,16.5,15.3,15.0,1.0
2018,United States,00,Two or more races (NH),-100.0,-100.0,1.6,2.4,10.9,1.26
2018,United States,00,American Indian and Alaska Native (NH),50.0,,1.2,,28.56,
2018,United States,00,Asian (NH),-77.4,-54.7,1.2,2.4,4.23,1.03
2018,United States,00,Black or African American (NH),216.1,162.8,43.3,36.0,60.86,6.03
2018,United States,00,Hispanic or Latino,-34.5,-39.3,16.5,15.3,15.0,1.0
2018,United States,00,Two or more races (NH),-63.6,-45.5,1.6,2.4,10.9,1.26
2018,United States,00,Native Hawaiian and Pacific Islander (NH),,,,,,
2018,United States,00,White (NH),-100.0,-100.0,36.2,43.9,13.62,2.0
2019,United States,00,American Indian and Alaska Native (NH),-100.0,-100.0,1.1,1.4,25.59,3.82
2019,United States,00,Asian (NH),-100.0,-100.0,1.5,1.5,5.18,0.67
2019,United States,00,Black or African American (NH),-100.0,-100.0,45.9,39.6,65.43,6.69
2019,United States,00,Hispanic or Latino,-100.0,-100.0,15.4,16.1,14.0,1.0
2019,United States,00,Two or more races (NH),-100.0,-100.0,1.9,2.4,11.98,1.24
2018,United States,00,White (NH),-28.0,-12.7,36.2,43.9,13.62,2.0
2019,United States,00,American Indian and Alaska Native (NH),37.5,75.0,1.1,1.4,25.59,3.82
2019,United States,00,Asian (NH),-72.2,-72.2,1.5,1.5,5.18,0.67
2019,United States,00,Black or African American (NH),235.0,189.1,45.9,39.6,65.43,6.69
2019,United States,00,Hispanic or Latino,-39.4,-36.6,15.4,16.1,14.0,1.0
2019,United States,00,Two or more races (NH),-57.8,-46.7,1.9,2.4,11.98,1.24
2019,United States,00,Native Hawaiian and Pacific Islander (NH),,,,,,
2019,United States,00,White (NH),-100.0,-100.0,34.3,39.0,13.04,1.81
2020,United States,00,American Indian and Alaska Native (NH),-100.0,-100.0,1.2,1.6,37.79,5.96
2020,United States,00,Asian (NH),-100.0,-100.0,1.3,1.2,5.84,0.65
2020,United States,00,Black or African American (NH),-100.0,-100.0,49.3,42.7,92.04,9.37
2020,United States,00,Hispanic or Latino,-100.0,-100.0,16.0,16.6,18.0,2.0
2020,United States,00,Two or more races (NH),-100.0,-100.0,1.7,2.0,13.68,1.29
2019,United States,00,White (NH),-31.3,-21.8,34.3,39.0,13.04,1.81
2020,United States,00,American Indian and Alaska Native (NH),50.0,100.0,1.2,1.6,37.79,5.96
2020,United States,00,Asian (NH),-75.9,-77.8,1.3,1.2,5.84,0.65
2020,United States,00,Black or African American (NH),259.9,211.7,49.3,42.7,92.04,9.37
2020,United States,00,Hispanic or Latino,-37.5,-35.2,16.0,16.6,18.0,2.0
2020,United States,00,Two or more races (NH),-63.0,-56.5,1.7,2.0,13.68,1.29
2020,United States,00,Native Hawaiian and Pacific Islander (NH),,,,,,
2020,United States,00,White (NH),-100.0,-100.0,30.5,36.0,15.09,2.18
2021,United States,00,American Indian and Alaska Native (NH),-100.0,-100.0,1.1,1.0,35.88,4.37
2021,United States,00,Asian (NH),-100.0,-100.0,1.4,1.4,6.68,0.9
2021,United States,00,Black or African American (NH),-100.0,-100.0,48.8,46.6,96.78,11.81
2021,United States,00,Hispanic or Latino,-100.0,-100.0,17.1,16.3,20.0,2.0
2021,United States,00,Two or more races (NH),-100.0,-100.0,2.1,2.4,17.5,1.77
2021,United States,00,Native Hawaiian and Pacific Islander (NH),-100.0,,0.2,,30.61,
2021,United States,00,White (NH),-100.0,-100.0,29.3,32.2,15.31,2.28
2020,United States,00,White (NH),-38.6,-27.6,30.5,36.0,15.09,2.18
2021,United States,00,American Indian and Alaska Native (NH),37.5,25.0,1.1,1.0,35.88,4.37
2021,United States,00,Asian (NH),-74.1,-74.1,1.4,1.4,6.68,0.9
2021,United States,00,Black or African American (NH),253.6,237.7,48.8,46.6,96.78,11.81
2021,United States,00,Hispanic or Latino,-33.5,-36.6,17.1,16.3,20.0,2.0
2021,United States,00,Two or more races (NH),-55.3,-48.9,2.1,2.4,17.5,1.77
2021,United States,00,Native Hawaiian and Pacific Islander (NH),0.0,,0.2,,30.61,
2021,United States,00,White (NH),-40.7,-34.8,29.3,32.2,15.31,2.28
2018,United States,00,Unknown race,,,,,,
2019,United States,00,Unknown race,,,,,,
2020,United States,00,Unknown race,,,,,,
2021,United States,00,Unknown race,,,,,,
2021,United States,00,All,-100.0,-100.0,100.0,100.0,27.73,3.52
2020,United States,00,All,-100.0,-100.0,100.0,100.0,26.36,3.07
2019,United States,00,All,-100.0,-100.0,100.0,100.0,20.45,2.37
2018,United States,00,All,-100.0,-100.0,100.0,100.0,20.35,2.36
2021,United States,00,All,0.0,0.0,100.0,100.0,27.73,3.52
2020,United States,00,All,0.0,0.0,100.0,100.0,26.36,3.07
2019,United States,00,All,0.0,0.0,100.0,100.0,20.45,2.37
2018,United States,00,All,0.0,0.0,100.0,100.0,20.35,2.36
Loading

0 comments on commit 6851562

Please sign in to comment.