Merge branch 'main' of https://github.com/SatcherInstitute/health-equ…

…ity-tracker

.vscode/settings.json

@@ -73,5 +73,8 @@
 		"yaml",
 		"yml",
 		"dockercompose"
+	],
+	"mypy-type-checker.args": [
+		"\"--config-file=pyproject.toml\""
 	]
 }

python/ingestion/graphql_ahr_utils.py

@@ -22,8 +22,7 @@ def generate_cols_map(prefixes: list[str], suffix: str):
     return {prefix: prefix.replace(f"_{std_col.RAW_SUFFIX}", "") + f"_{suffix}" for prefix in prefixes}
 
 
-AHR_BASE_MEASURES = {
-    'Voter Participation (Presidential)': 'voter_participation_pct_rate',
+AHR_MEASURES_TO_RATES_MAP_18PLUS = {
     'Asthma': 'asthma_per_100k',
     'Avoided Care Due to Cost': 'avoided_care_pct_rate',
     'Cardiovascular Diseases': 'cardiovascular_diseases_per_100k',
@@ -33,11 +32,30 @@ def generate_cols_map(prefixes: list[str], suffix: str):
     'Diabetes': 'diabetes_per_100k',
     'Excessive Drinking': 'excessive_drinking_per_100k',
     'Frequent Mental Distress': 'frequent_mental_distress_per_100k',
-    'Preventable Hospitalizations': 'preventable_hospitalizations_per_100k',
     'Non-Medical Drug Use - Past Year': 'non_medical_drug_use_per_100k',
+}
+
+AHR_MEASURES_TO_RATES_MAP_ALL_AGES = {
     'Suicide': 'suicide_per_100k',
 }
 
+AHR_MEASURES_TO_RATES_MAP_CITIZENS_18PLUS = {
+    'Voter Participation (Presidential)': 'voter_participation_pct_rate',
+}
+
+AHR_MEASURES_TO_RATES_MAP_MEDICARE_18PLUS = {
+    'Preventable Hospitalizations': 'preventable_hospitalizations_per_100k',
+}
+
+
+AHR_BASE_MEASURES_TO_RATES_MAP = {
+    **AHR_MEASURES_TO_RATES_MAP_18PLUS,
+    **AHR_MEASURES_TO_RATES_MAP_CITIZENS_18PLUS,
+    **AHR_MEASURES_TO_RATES_MAP_MEDICARE_18PLUS,
+    **AHR_MEASURES_TO_RATES_MAP_ALL_AGES,
+}
+
+# AHR provides case per 100; HET needs per 100k
 PCT_RATE_TO_PER_100K_TOPICS = [
     "Asthma",
     "Cardiovascular Diseases",

python/ingestion/standardized_columns.py

@@ -61,6 +61,20 @@
 PCT_REL_INEQUITY_SUFFIX = "pct_relative_inequity"
 RAW_SUFFIX = "estimated_total"
 POP_PCT_SUFFIX = 'population_pct'
+RATIO_AGE_ADJUSTED_SUFFIX = "ratio_age_adjusted"
+INDEX_SUFFIX = "index"
+
+SUFFIXES = [
+    PER_100K_SUFFIX,
+    PCT_RATE_SUFFIX,
+    PCT_SHARE_SUFFIX,
+    PCT_REL_INEQUITY_SUFFIX,
+    SHARE_OF_KNOWN_SUFFIX,
+    RAW_SUFFIX,
+    POP_PCT_SUFFIX,
+    RATIO_AGE_ADJUSTED_SUFFIX,
+    INDEX_SUFFIX,
+]
 
 COVID_CASES_PREFIX = "covid_cases"
 COVID_HOSP_PREFIX = "covid_hosp"
@@ -421,3 +435,15 @@ def generate_column_name(prefix, suffix):
     suffix: a type of measurement (pct_share, per_100k)"""
 
     return f'{prefix}_{suffix}'
+
+
+def extract_prefix(col_name: str) -> str:
+    """Extracts the prefix from a column name that contains one of out standard HET suffixes."""
+
+    for suffix in SUFFIXES:
+        underscore_suffix = f'_{suffix}'
+        if col_name.endswith(underscore_suffix):
+            prefix = col_name[: -len(underscore_suffix)]
+            return prefix
+
+    raise ValueError(f"Column {col_name} does not contain a standard suffix from {SUFFIXES}")

python/tests/data/graphql_ahr/golden_data/age_national_current.csv

@@ -1,13 +1,13 @@
-state_name,state_fips,age,voter_participation_pct_rate,asthma_per_100k,avoided_care_pct_rate,cardiovascular_diseases_per_100k,chronic_kidney_disease_per_100k,copd_per_100k,depression_per_100k,diabetes_per_100k,excessive_drinking_per_100k,frequent_mental_distress_per_100k,preventable_hospitalizations_per_100k,non_medical_drug_use_per_100k,suicide_per_100k,population,population_pct
-United States,00,45-64,,10100.0,9.6,9100.0,3200.0,7700.0,19100.0,15100.0,15100.0,13500.0,,,,85333288.0,25.6
-United States,00,15-24,,,,,,,,,,,,,15.2,43666116.0,13.1
-United States,00,18-44,,9900.0,13.1,1900.0,1100.0,2700.0,22200.0,3400.0,23200.0,18400.0,,,,119279569.0,35.8
-United States,00,24-34,,,,,,,,,,,,,19.5,,
-United States,00,35-44,,,,,,,,,,,,,18.1,42845441.0,12.9
-United States,00,45-54,,,,,,,,,,,,,18.2,42062109.0,12.6
-United States,00,55-64,,,,,,,,,,,,,17.0,43271179.0,13.0
-United States,00,65+,,8600.0,3.4,20600.0,7100.0,12300.0,14600.0,22600.0,7000.0,8500.0,,,16.9,53592546.0,16.1
-United States,00,65-74,,,,,,,,,,,,,15.3,31968856.0,9.6
-United States,00,75-84,,,,,,,,,,,,,19.6,15235011.0,4.6
-United States,00,85+,,,,,,,,,,,,,22.4,6388679.0,1.9
-United States,00,All,,9800.0,8.8,8000.0,3000.0,6200.0,20500.0,10900.0,17300.0,14700.0,2681.0,12.0,14.5,333036755.0,100.0
+state_name,state_fips,age,voter_participation_pct_rate,asthma_per_100k,avoided_care_pct_rate,cardiovascular_diseases_per_100k,chronic_kidney_disease_per_100k,copd_per_100k,depression_per_100k,diabetes_per_100k,excessive_drinking_per_100k,frequent_mental_distress_per_100k,preventable_hospitalizations_per_100k,non_medical_drug_use_per_100k,suicide_per_100k,population,population_pct,suicide_estimated_total
+United States,00,45-64,,10100.0,9.6,9100.0,3200.0,7700.0,19100.0,15100.0,15100.0,13500.0,,,,85333288.0,25.6,
+United States,00,15-24,,,,,,,,,,,,,15.2,43666116.0,13.1,6637.0
+United States,00,18-44,,9900.0,13.1,1900.0,1100.0,2700.0,22200.0,3400.0,23200.0,18400.0,,,,119279569.0,35.8,
+United States,00,24-34,,,,,,,,,,,,,19.5,,,
+United States,00,35-44,,,,,,,,,,,,,18.1,42845441.0,12.9,7755.0
+United States,00,45-54,,,,,,,,,,,,,18.2,42062109.0,12.6,7655.0
+United States,00,55-64,,,,,,,,,,,,,17.0,43271179.0,13.0,7356.0
+United States,00,65+,,8600.0,3.4,20600.0,7100.0,12300.0,14600.0,22600.0,7000.0,8500.0,,,16.9,53592546.0,16.1,9057.0
+United States,00,65-74,,,,,,,,,,,,,15.3,31968856.0,9.6,4891.0
+United States,00,75-84,,,,,,,,,,,,,19.6,15235011.0,4.6,2986.0
+United States,00,85+,,,,,,,,,,,,,22.4,6388679.0,1.9,1431.0
+United States,00,All,,9800.0,8.8,8000.0,3000.0,6200.0,20500.0,10900.0,17300.0,14700.0,2681.0,12.0,14.5,333036755.0,100.0,48290.0