diff --git a/.github/workflows/build_docs.yaml b/.github/workflows/build_docs.yaml index ffff40381..1ffdf047f 100644 --- a/.github/workflows/build_docs.yaml +++ b/.github/workflows/build_docs.yaml @@ -25,6 +25,9 @@ jobs: - name: Build documentation run: Rscript scripts/build_docs.R + - name: Build data table + run: Rscript scripts/build_data_table.R + - name: Check for changes id: diff run: | diff --git a/.github/workflows/update_daily_data.yaml b/.github/workflows/update_daily_data.yaml index 6c99f4aff..3a435b7e0 100644 --- a/.github/workflows/update_daily_data.yaml +++ b/.github/workflows/update_daily_data.yaml @@ -51,6 +51,10 @@ jobs: name: Rebuild documentation and manifest run: Rscript scripts/build_docs.R + - if: ${{ steps.diff.outputs.changed == 'true' }} + name: Rebuild data table + run: Rscript scripts/build_data_table.R + - if: ${{ steps.diff.outputs.changed == 'true' }} name: Commit and push run: | diff --git a/docs/data-table.html b/docs/data-table.html new file mode 100644 index 000000000..14c14fa57 --- /dev/null +++ b/docs/data-table.html @@ -0,0 +1,1210 @@ + + + + + + + + + PopHIVE Data Table + + + + + + +

PopHIVE Data Table

+

+ Overview of all standardized data sources and combined bundles in the + PopHIVE/Ingest + repository. Automatically generated from repository files — last updated + July 02, 2026 + . + View full data documentation → +

+ +
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
DatasetContent TitleBrief DescriptionSpatial ResolutionAge ResolutionSex ResolutionOther ResolutionsEarliest DataLatest DataTime ScaleLast RefreshedData RestrictionsOrganizationSource URLData URL
+ + abcs + + Active Bacterial Core surveillance (ABCs)CDC monitors invasive bacterial infections that cause bloodstream infections, sepsis, and meningitis in persons living in the community through Active Bacterial Core surveillance (ABCs). The CAAP (Community-Acquired Acute Pneumonia) study by Ramirez et al.National, State<5 years, 5-49 years, 50+ yearsNot Stratified—1998-01-012024-01-01Annual2026-05-29Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + area_health_resource_file + + Area Health Resource File (AHRF)The Area Health Resource File (AHRF) is an annual county-level database produced by the Health Resources and Services Administration (HRSA).CountyNot StratifiedNot Stratified—1999-12-312025-12-31Annual2026-06-25Public domain. HRSA data is produced by a U.S. federal agency and is generally not subject to copyright restrictions.Health Resources and Services Administration (HRSA) + Link + + GitHub +
+ + brfss + + Behavioral Risk Factor Surveillance System (BRFSS)The Behavioral Risk Factor Surveillance System (BRFSS) is the nation's premier system of health-related telephone surveys that collect state data about U.S.National, State18-24 Years, 25-34 Years, 35-44 Years, 45-54 Years, 55-64 Years, 65+ YearsNot Stratified—2011-01-012025-01-01Annual2026-02-01Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + cdc_cfa_rt + + CDC Epidemic Trends and RtWeekly estimates of the effective reproduction number (Rt) for COVID-19, Influenza, and RSV at the US national and state level.StateNot StratifiedNot Stratified—2026-05-192026-06-16Daily2026-06-19Public domain. CDC data is generally not subject to copyright restrictions.CDC Center for Forecasting and Outbreak Analytics (CFA) + Link + + GitHub +
+ + census + + 2020 Census Urban Area to County Allocation FileThe 2020 Census Urban Area to County Allocation File maps Census-defined urban areas (urbanized areas with population ≥ 50,000 and urban clusters with population 2,500–49,999) to counties. Extraction and formatting provided by Metopio, The American Community Survey (ACS) is an ongoing survey conducted by the U.S.National, State, CountyNot StratifiedNot Stratified—2019-12-312024-12-31Annual2026-04-28Public domain. U.S. Census Bureau data are generally not subject to copyright restrictions.U.S. Census Bureau + Link + + GitHub +
+ + cms_mmd + + Mapping Medicare Disparities by Population ToolThe Mapping Medicare Disparities (MMD) by Population Tool is an interactive map that displays chronic disease prevalence, costs, hospitalization, and preventive care utilization data for Medicare Fee-for-Service beneficiaries.National, State, County<65 Years, 65-74 Years, 65+ Years, 75-84 Years, 85+ YearsStratifiedRace/Ethnicity2021-01-012023-01-01Annual2026-06-09Public domain. CMS data is generally not subject to copyright restrictions.Centers for Medicare and Medicaid Services (CMS) + Link + + GitHub +
+ + county_health_rankings + + County Health Rankings & RoadmapsThe County Health Rankings & Roadmaps (CHR&R) program, a collaboration between the Robert Wood Johnson Foundation and the University of Wisconsin Population Health Institute, ranks the health of nearly all counties in the nation.National, State, CountyNot StratifiedNot Stratified—2010-12-312025-12-31Annual2026-06-18CC BY 4.0. Attribution required. Cite as: University of Wisconsin Population Health Institute. County Health Rankings & Roadmaps. https://www.countyhealthrankings.org.University of Wisconsin Population Health Institute + Link + + GitHub +
+ + delphi_doctors_claims + + CMU Delphi COVIDcast - Doctor VisitsThe Delphi Doctor Visits signal estimates the percentage of outpatient doctor visits with COVID-related diagnoses based on claims data from health system partners.National, State, CountyNot StratifiedNot Stratified—2020-02-012026-05-30Weekly2026-06-09CC-BY Attribution license. Data may be used with attribution to the CMU Delphi Group.Carnegie Mellon University Delphi Research Group + Link + + GitHub +
+ + delphi_hospital_claims + + CMU Delphi COVIDcast - Hospital AdmissionsThe Delphi Hospital Admissions signal estimates the percentage of new hospital admissions with COVID-19 or influenza diagnoses based on electronic medical records and claims data from health system partners.National, State, CountyNot StratifiedNot Stratified—2020-02-012026-05-30Daily2026-06-09CC-BY Attribution license. Data may be used with attribution to the CMU Delphi Group.Carnegie Mellon University Delphi Research Group + Link + + GitHub +
+ + delphi_ili_fluview + + CMU Delphi Epidata - FluView (ILINet)Influenza-Like Illness (ILI) surveillance data from the CDC's ILINet network, accessed via the CMU Delphi Epidata API.National, StateNot StratifiedNot Stratified—1997-10-042026-06-20Weekly2026-06-30Public domain. Original CDC ILI data is not subject to copyright restrictions.Carnegie Mellon University Delphi Research Group + Link + + GitHub +
+ + delphi_nhsn + + CMU Delphi COVIDcast - NHSN Respiratory HospitalizationsWeekly hospital respiratory data reported to CDC's National Healthcare Safety Network (NHSN), accessed via the CMU Delphi Epidata API.National, StateNot StratifiedNot Stratified—2020-08-082026-06-20Weekly2026-06-26CC-BY Attribution license. Data may be used with attribution to the CMU Delphi Group and CDC NHSN.Carnegie Mellon University Delphi Research Group + Link + + GitHub +
+ + epic_chronic + + Epic CosmosEpic Cosmos is a collaborative research platform containing de-identified patient data from over 300 million patients across more than 1,600 hospitals and health systems using Epic electronic health record systems.National, State, County<18 Years, 18-24 Years, 25-34 Years, 35-44 Years, 45-54 Years, 55-64 Years, 65+ YearsNot Stratified—2016-01-012025-01-01Annual2026-06-24The data can be re-used with appropriate attribution. A suggested citation relating to this data is 'Results of research performed with Epic Cosmos were obtained from the PopHIVE platform (https://github.com/PopHIVE/Ingest).'Epic Systems + Link + + GitHub +
+ + epic_hepb_vax + + Epic CosmosEpic Cosmos is a collaborative research platform containing de-identified patient data from over 300 million patients across more than 1,600 hospitals and health systems using Epic electronic health record systems.National, StateNot StratifiedNot Stratified—2017-01-312026-01-31Monthly2026-03-11The data can be re-used with appropriate attribution. A suggested citation relating to this data is 'Results of research performed with Epic Cosmos were obtained from the PopHIVE platform (https://github.com/PopHIVE/Ingest).'Epic Systems + Link + + GitHub +
+ + epic_injury + + Epic CosmosEpic Cosmos is a collaborative research platform containing de-identified patient data from over 300 million patients across more than 1,600 hospitals and health systems using Epic electronic health record systems.National, State, County<15 Years, 15-25 Years, 25-45 Years, 45-64 Years, 65+ YearsNot Stratified—2018-01-012025-09-01Annual, Monthly2026-03-11The data can be re-used with appropriate attribution. A suggested citation relating to this data is 'Results of research performed with Epic Cosmos were obtained from the PopHIVE platform (https://github.com/PopHIVE/Ingest).'Epic Systems + Link + + GitHub +
+ + epic_resp_infections + + Epic CosmosEpic Cosmos is a collaborative research platform containing de-identified patient data from over 300 million patients across more than 1,600 hospitals and health systems using Epic electronic health record systems.National, State<1 Years, 1-4 Years, <5 Years, 5-17 Years, 18-39 Years, 18-49 Years, 40-64 Years, 50-64 Years, 65+ YearsNot Stratified—2017-01-012026-05-30Annual, Weekly, Monthly, Quarterly2026-06-19The data can be re-used with appropriate attribution. A suggested citation relating to this data is 'Results of research performed with Epic Cosmos were obtained from the PopHIVE platform (https://github.com/PopHIVE/Ingest).'Epic Systems + Link + + GitHub +
+ + gtrends + + Google Health Trends APIGoogle Health Trends data accessed via the Google Health Trends API, processed and collected using Yale DISSC's gtrends_collection framework.National, State, CountyNot StratifiedNot Stratified—2014-01-072026-06-27Weekly2026-06-30Data can be reused with attribution of data from the Google Health Trends API, obtained via the PopHIVE platform (https://github.com/PopHIVE/Ingest).Yale Data-Intensive Social Science Center (DISSC) + Link + + GitHub +
+ + kinsa_ili + + Kinsa Insights APIKinsa collects real-time illness data through its network of smart thermometers and a companion mobile app.NationalNot StratifiedNot Stratified—2019-01-012026-07-01Daily2026-07-02Data can be re-used with appropriate attribution. A suggested citation relating to this data is 'Results of research performed with Kinsa Insights data were obtained via the PopHIVE platform (https://github.com/PopHIVE/Ingest).'Kinsa + Link + + GitHub +
+ + measles_age_cdc2 + + CDC Measles Cases and Outbreaks - Age and Vaccination StatusWeekly new and cumulative case and hospitalization counts for measles in the United States, stratified by age group (<5, 5-19, 20+, and Total) and vaccination status (Total, Unvaccinated/Unknown, One dose MMR, Two doses MMR).National<5 years, 5-19 years, 20+ yearsNot Stratified—2025-02-082026-06-27Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + measles_cdc + + CDC Measles Cases and OutbreaksThe CDC Measles Cases and Outbreaks surveillance system tracks confirmed and probable measles cases reported to CDC by state and local health departments.NationalNot StratifiedNot Stratified—2022-01-082026-06-27Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + measles_jhu + + Johns Hopkins University Measles Tracking TeamThe Johns Hopkins University Measles Tracking Team compiles laboratory-confirmed measles case data from official state and county health department reports across the United States.National, State, CountyNot StratifiedNot Stratified—2025-01-112026-06-27Weekly2026-06-30CC BY 4.0. Attribution required for reuse. Please cite as JHU Measles Tracking Team Data Repository at Johns Hopkins University or JHU Measles Tracking Team Data for short. Copyright: Johns Hopkins University 2025Johns Hopkins Bloomberg School of Public Health + Link + + GitHub +
+ + medicaid_quality + + Medicaid and CHIP Adult and Child Core Set Quality MeasuresAnnual state-level performance data on the Medicaid and CHIP Adult Core Set and Child Core Set quality measures, as voluntarily reported by states to CMS and analyzed by Mathematica via the Quality Measure Reporting (QMR) system.CountyNot StratifiedNot StratifiedPayer2014-01-012023-01-01Annual2026-04-05Public domain. CMS/Medicaid.gov data is generally not subject to copyright restrictions.Centers for Medicare & Medicaid Services (CMS) + Link + + GitHub +
+ + mmr_healthmap + + HealthMap MMR Vaccine Coverage EstimatesCounty, ZIP code, and state-level estimates of MMR (measles, mumps, and rubella) vaccine coverage among US children, developed using small area estimation with multilevel regression and post-stratification (MRP).National, State, CountyNot StratifiedNot Stratified—2024-12-312024-12-31Cross-Sectional2026-04-06MIT License: Copyright (c) 2025 Eric Zhou. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the Software), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:Attribution required. Cite Zhou EG, Brownstein J, Rader B. Assessing MMR Vaccination Coverage Gaps in US Children with Digital Participatory Surveillance. Nature Health. 2025.HealthMap / Boston Children's Hospital + Link + + GitHub +
+ + narms + + NARMS Now: Human Data - Antimicrobial ResistanceDetailed antimicrobial resistance data from NARMS human clinical isolates, including resistance by individual antimicrobial agent (with CLSI class) and by resistance pattern (multidrug resistance profiles). Isolate-level antimicrobial susceptibility data from the FDA NARMS retail meats program. Antimicrobial susceptibility data from the FDA NARMS animal diagnostic pathogen surveillance program. Isolate-level antimicrobial susceptibility data from four FDA NARMS food-producing animal surveillance programs: (1) HACCP slaughter surveillance (1997-present), covering federally inspected slaughter and processing plants; (2) Cecal sampling at slaughter (2013-present), testing cecal contents from…National, StateNot StratifiedNot Stratified—1997-12-312025-12-31Annual2026-06-09Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + nccr + + National Childhood Cancer Registry Explorer (NCCR*Explorer)The National Childhood Cancer Registry (NCCR) is a federated data resource maintained by the National Cancer Institute (NCI) as part of the Childhood Cancer Data Initiative (CCDI).National0-19, 0-39, <1, 1-4, 5-9, 10-14, 15-19, 15-39, 20-24, 20-39, 25-29, 30-39StratifiedRace/Ethnicity2001-12-312022-12-31Annual2026-06-26Public domain. Data from the National Childhood Cancer Registry, produced by the National Cancer Institute, is generally not subject to copyright restrictions. Suggested attribution: National Childhood Cancer Registry Explorer (NCCR*Explorer), National Cancer Institute.National Cancer Institute (NCI), Childhood Cancer Data Initiative + Link + + GitHub +
+ + nchs_mortality + + NCHS VSRR Provisional Drug Overdose Death Counts (State)Provisional monthly counts of drug overdose deaths by type of drug, reported as 12-month backward rolling totals. Provisional monthly counts of drug overdose deaths at the county level, from the Vital Statistics Rapid Release (VSRR) program. Provisional quarterly age-adjusted mortality rates for 21 selected causes of death, from the Vital Statistics Rapid Release (VSRR) program.National, State, CountyNot StratifiedNot Stratified—2015-01-012026-01-01Monthly, Quarterly2026-06-23Public domain. CDC/NCHS data is generally not subject to copyright restrictions.National Center for Health Statistics (NCHS) + Link + + GitHub +
+ + nhtsa_crash + + Fatality Analysis Reporting System (FARS)FARS is a nationwide census providing NHTSA, Congress, and the American public with yearly data on fatal injuries suffered in motor vehicle traffic crashes.National, State, County0-14, 15-24, 25-44, 45-64, 65+Stratified—2000-12-312024-12-31Annual2026-06-29Public domain. NHTSA data is generally not subject to copyright restrictions.National Highway Traffic Safety Administration (NHTSA) + Link + + GitHub +
+ + nis + + National Immunization Survey (NIS)The National Immunization Surveys (NIS) are a group of telephone surveys used to monitor vaccination coverage among children 19-35 months, teens 13-17 years, flu vaccinations for children 6 months-17 years, and COVID-19 vaccination for children, teens, and adults.National, State, County0-1 Days, 0-2 Days, 0-3 Days, 3 Months, 5 Months, 7 Months, 8 Months, 13 Months, 19 Months, 24 Months, 35 MonthsNot StratifiedBirth Cohort, Insurance, Urbanicity2011-01-012024-11-30Annual2026-04-03Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + nnds + + National Notifiable Diseases Surveillance System (NNDSS)The National Notifiable Diseases Surveillance System (NNDSS) is a nationwide collaboration that enables all levels of public health to share notifiable disease related health information.National, StateNot StratifiedNot Stratified—2022-01-082026-03-28Weekly2026-04-03Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + noaa_heat_risk + + NOAA WPC HeatRiskThe NOAA Weather Prediction Center HeatRisk product provides a daily, gridded (2.5 km) assessment of heat risk across the contiguous United States for the current day and 7-day forecast period.National, State, CountyNot StratifiedNot Stratified—2024-08-012026-07-07Daily2026-07-02Public domain. NOAA data is generally not subject to copyright restrictions.NOAA Weather Prediction Center (WPC) + Link + + GitHub +
+ + NREVSS + + National Respiratory and Enteric Virus Surveillance System (NREVSS)The National Respiratory and Enteric Virus Surveillance System (NREVSS) is a voluntary, laboratory-based surveillance system that monitors temporal and geographic trends for respiratory syncytial virus (RSV), human parainfluenza viruses, respiratory adenoviruses, human metapneumovirus, human corona…NationalNot StratifiedNot Stratified—2020-04-112026-06-20Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + nssp + + National Syndromic Surveillance Program (NSSP)This dataset provides the percentage of emergency department patient visits for the specified pathogen of all ED patient visits for the specified geographic part of the country that were observed for the given week from data submitted to the National Syndromic Surveillance Program (NSSP).National, State, CountyNot StratifiedNot Stratified—2022-10-012026-06-20Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + respnet + + Respiratory Virus Hospitalization Surveillance Network (RESP-NET)The Respiratory Virus Hospitalization Surveillance Network (RESP-NET) monitors laboratory-confirmed hospitalizations associated with influenza, COVID-19, and respiratory syncytial virus (RSV) among children and adults.National, State<1 Years, 1-4 Years, 5-17 Years, 18-49 Years, 50-64 Years, 65+ YearsNot Stratified—2016-10-012026-06-20Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + schoolvax_washpost + + Washington Post School Vaccination RatesSchool and county-level vaccination rate data compiled by the Washington Post from state health department records. These data are from the 2024-2025 Kindergarten Immunization Compliance Assessment (i.e., Kindergarten Survey), an annual assessment completed by the Tennessee Department of Health's Vaccine-Preventable Diseases and Immunization Program (VPDIP) in collaboration with the Tennessee Department of Educa…State, CountyNot StratifiedNot StratifiedSchool Grade2018-09-012024-09-01Annual2026-06-09Attribution required. Cite The Washington Post.The Washington Post + Link + + GitHub +
+ + schoolvaxview + + SchoolVaxViewSchoolVaxView monitors vaccination coverage among U.S.National, StateNot StratifiedNot StratifiedSchool Grade2009-09-012024-09-01Annual2025-08-25Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + vaccine_exemptions_fattah + + Medical Exemptions From Childhood Vaccination in the US (Kiang et al. 2025)A comprehensive study of medical vaccine exemption rates among U.S.National, State, CountyNot StratifiedNot Stratified—2009-09-012025-09-01Annual2026-04-06Attribution required. Cite Fattah M, Stoffel LA, Bubar KM, Bents SJ, Maldonado Y, Hotez PJ, Kiang MV, Lo NC. Trends in County-Level Childhood Vaccination Exemptions in the US. JAMA. 2026 Feb 10;335(6):546-549. doi: 10.1001/jama.2025.24407. PMID: 41533386; PMCID: PMC12805488.Stanford University / Massachusetts General Hospital + Link + + GitHub +
+ + wastewater + + CDC National Wastewater Surveillance System (NWSS)The National Wastewater Surveillance System (NWSS) is a national surveillance system coordinated by CDC that monitors SARS-CoV-2, Influenza A, and RSV levels in wastewater across the United States.National, StateNot StratifiedNot Stratified—2022-01-012026-06-20Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + wastewater_measles + + CDC National Wastewater Surveillance System (NWSS) - MeaslesThe CDC National Wastewater Surveillance System (NWSS) tracks measles virus RNA in wastewater samples from participating wastewater treatment facilities across the United States.National, State, CountyNot StratifiedNot Stratified—2024-12-142026-06-27Weekly2026-06-26Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + wisqars + + Web-based Injury Statistics Query and Reporting System (WISQARS)WISQARS (Web-based Injury Statistics Query and Reporting System) is an interactive, online database that provides fatal and nonfatal injury, violent death, and cost of injury data from a variety of trusted sources.National, State0-14 Years, 15-24 Years, 25-44 Years, 45-64 Years, 65+ YearsStratifiedRace/Ethnicity2001-01-012024-01-01Annual2026-06-19Public domain. CDC data is generally not subject to copyright restrictions.Centers for Disease Control and Prevention + Link + + GitHub +
+ + yrbss + + CDC Youth Risk Behavior Surveillance System (YRBSS)The Youth Risk Behavior Surveillance System (YRBSS) is a set of school-based surveys conducted by the CDC that monitor health-related behaviors among U.S.National, State14, 15, 16, 17StratifiedRace/Ethnicity2005-12-312023-12-31Annual2026-06-25Public domain. Suggested attribution: Centers for Disease Control and Prevention (CDC). Youth Risk Behavior Surveillance System (YRBSS).Centers for Disease Control and Prevention + Link + + GitHub +
+
+
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
FolderBundle# DatasetsDatasets Involved
+ + bundle_antimicrobial_resistance + + Antimicrobial Resistance1NARMS
+ + bundle_cancer_screening + + Cancer Screening2CMS Mmd, Medicaid Quality
+ + bundle_childhood_immunizations + + Childhood Immunizations3NIS, Schoolvax Washpost, Schoolvaxview
+ + bundle_chronic_diseases + + Chronic Diseases3BRFSS, CMS Mmd, Epic Chronic
+ + bundle_county_access + + County Access1County Health Rankings
+ + bundle_county_chronic + + County Chronic1County Health Rankings
+ + bundle_injury_overdose + + Injury Overdose3Gtrends, Medicaid Quality, NCHS Mortality
+ + bundle_maternal_health + + Maternal Health3Census, County Health Rankings, Medicaid Quality
+ + bundle_measles + + Measles9Measles Age Cdc2, Measles CDC, Measles JHU, MMR Healthmap, NNDS, Schoolvax Washpost, Schoolvaxview, Vaccine Exemptions Fattah, Wastewater Measles
+ + bundle_preventative_services + + Preventative Services2CMS Mmd, Medicaid Quality
+ + bundle_respiratory + + Respiratory12Abcs, Delphi Doctors Claims, Delphi Hospital Claims, Delphi ILI Fluview, Delphi NHSN, Epic Resp Infections, Gtrends, Kinsa ILI, NREVSS, NSSP, Respnet, Wastewater
+ + bundle_youth_wellbeing + + Youth Wellbeing2CMS Mmd, Medicaid Quality
+
+
+
+ + + + + + + + diff --git a/docs/index.html b/docs/index.html index 19bee135e..99f3a6fa6 100644 --- a/docs/index.html +++ b/docs/index.html @@ -24,7 +24,10 @@
@@ -624,132 +627,6 @@
Sources
Public domain. CDC data is generally not subject to copyright restrictions.

Variables

-
- data_survey.csv.gz -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
VariableShort NameDescriptionTypeUnit
- geography - GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
- time - TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
- age - AgeAge group.integeryears
- prev_diabetes_survey - Diabetes Prevalence (Survey)Estimated diabetes prevalence from BRFSS survey data.percentpercent
- prev_diabetes_survey_lcl - Diabetes Prevalence Lower CILower bound of 95% confidence interval for diabetes prevalence.percentpercent
- prev_diabetes_survey_ucl - Diabetes Prevalence Upper CIUpper bound of 95% confidence interval for diabetes prevalence.percentpercent
- prev_obesity_survey - Obesity Prevalence (Survey)Estimated obesity prevalence (BMI >= 30) from BRFSS survey data.percentpercent
- prev_obesity_survey_lcl - Obesity Prevalence Lower CILower bound of 95% confidence interval for obesity prevalence.percentpercent
- prev_obesity_survey_ucl - Obesity Prevalence Upper CIUpper bound of 95% confidence interval for obesity prevalence.percentpercent
- agec - Age CategoryCategorical age grouping used in survey analysis.categoricalcategory
- sample_size_diab - Sample Size (Diabetes)Number of survey respondents used to estimate diabetes prevalence.integercount
- sample_size_obesity - Sample Size (Obesity)Number of survey respondents used to estimate obesity prevalence.integercount
-
data.csv.gz
@@ -939,6 +816,132 @@
+
+ data_survey.csv.gz +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
VariableShort NameDescriptionTypeUnit
+ geography + GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
+ time + TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
+ age + AgeAge group.integeryears
+ prev_diabetes_survey + Diabetes Prevalence (Survey)Estimated diabetes prevalence from BRFSS survey data.percentpercent
+ prev_diabetes_survey_lcl + Diabetes Prevalence Lower CILower bound of 95% confidence interval for diabetes prevalence.percentpercent
+ prev_diabetes_survey_ucl + Diabetes Prevalence Upper CIUpper bound of 95% confidence interval for diabetes prevalence.percentpercent
+ prev_obesity_survey + Obesity Prevalence (Survey)Estimated obesity prevalence (BMI >= 30) from BRFSS survey data.percentpercent
+ prev_obesity_survey_lcl + Obesity Prevalence Lower CILower bound of 95% confidence interval for obesity prevalence.percentpercent
+ prev_obesity_survey_ucl + Obesity Prevalence Upper CIUpper bound of 95% confidence interval for obesity prevalence.percentpercent
+ agec + Age CategoryCategorical age grouping used in survey analysis.categoricalcategory
+ sample_size_diab + Sample Size (Diabetes)Number of survey respondents used to estimate diabetes prevalence.integercount
+ sample_size_obesity + Sample Size (Obesity)Number of survey respondents used to estimate obesity prevalence.integercount
+

CDC Cfa Rt

@@ -4561,7 +4564,7 @@
Sources

Variables

- data_state_county_age_by_race.csv.gz + data_state_county_age.csv.gz
@@ -5038,7 +5041,7 @@
- data_state_county_age_by_sex.csv.gz + data_state_county_age_by_race.csv.gz
@@ -5515,7 +5518,7 @@
- data_state_county_age.csv.gz + data_state_county_age_by_sex.csv.gz
@@ -10816,7 +10819,7 @@
Sources

Variables

- data_dma_year.csv.gz + data.csv.gz
@@ -10850,82 +10853,82 @@
- - + + - - + + - - + + - - + + - - + + - - + + - - + + - - + + - - + + @@ -10938,6 +10941,15 @@
+ + + + + + +
- gtrends_drug+overdose + gtrends_rsv_vaccine Google Search Volume: Drug OverdoseGoogle search volume for the term drug overdose.Google Search Volume: rsv_vaccineGoogle search volume of the term rsv_vaccine. probability probability * 10M
- gtrends_naloxone + gtrends_9mm Google Search Volume: naloxoneGoogle search volume of the term naloxone.Google Search Volume: 9mmGoogle search volume for the term 9mm. probability probability * 10M
- gtrends_narcan + gtrends_naloxone Google Search Volume: narcanGoogle search volume of the term narcan.Google Search Volume: naloxoneGoogle search volume of the term naloxone. probability probability * 10M
- gtrends_overdose + gtrends_drug+overdose Google Search Volume: overdoseGoogle search volume of the term overdose.Google Search Volume: Drug OverdoseGoogle search volume for the term drug overdose. probability probability * 10M
- gtrends_rsv_vaccine + gtrends_heat+exhaustion Google Search Volume: rsv_vaccineGoogle search volume of the term rsv_vaccine.Google Search Volume: Heat ExhaustionGoogle search volume for the term heat exhaustion. probability probability * 10M
- gtrends_rsv + gtrends_heat+stroke Google Search Volume: rsvGoogle search volume of the term rsv.Google Search Volume: Heat StrokeGoogle search volume for the term heat stroke. probability probability * 10M
- gtrends_heat+exhaustion + gtrends_narcan Google Search Volume: Heat ExhaustionGoogle search volume for the term heat exhaustion.Google Search Volume: narcanGoogle search volume of the term narcan. probability probability * 10M
- gtrends_heat+stroke + gtrends_overdose Google Search Volume: Heat StrokeGoogle search volume for the term heat stroke.Google Search Volume: overdoseGoogle search volume of the term overdose. probability probability * 10M
- gtrends_9mm + gtrends_rsv Google Search Volume: 9mmGoogle search volume for the term 9mm.Google Search Volume: rsvGoogle search volume of the term rsv. probability probability * 10M
probability probability * 10M
+ gtrends_rsv_adjusted + Google Search Volume: rsv_adjustedGoogle search volume of the term rsv_adjusted.probabilityprobability * 10M
@@ -11068,7 +11080,7 @@
- data_year.csv.gz + data_dma_year.csv.gz
@@ -11102,19 +11114,10 @@
- - - - - - - - - + + @@ -11129,73 +11132,73 @@
- - + + - - + + - - + + - - + + - - + + - - + + - - + + - - + + @@ -11203,7 +11206,7 @@
- gtrends_rsv_vaccine - Google Search Volume: rsv_vaccineGoogle search volume of the term rsv_vaccine.probabilityprobability * 10M
- gtrends_9mm + gtrends_drug+overdose Google Search Volume: 9mmGoogle search volume for the term 9mm.Google Search Volume: Drug OverdoseGoogle search volume for the term drug overdose. probability probability * 10M
- gtrends_drug+overdose + gtrends_narcan Google Search Volume: Drug OverdoseGoogle search volume for the term drug overdose.Google Search Volume: narcanGoogle search volume of the term narcan. probability probability * 10M
- gtrends_heat+exhaustion + gtrends_overdose Google Search Volume: Heat ExhaustionGoogle search volume for the term heat exhaustion.Google Search Volume: overdoseGoogle search volume of the term overdose. probability probability * 10M
- gtrends_heat+stroke + gtrends_rsv_vaccine Google Search Volume: Heat StrokeGoogle search volume for the term heat stroke.Google Search Volume: rsv_vaccineGoogle search volume of the term rsv_vaccine. probability probability * 10M
- gtrends_narcan + gtrends_rsv Google Search Volume: narcanGoogle search volume of the term narcan.Google Search Volume: rsvGoogle search volume of the term rsv. probability probability * 10M
- gtrends_overdose + gtrends_heat+exhaustion Google Search Volume: overdoseGoogle search volume of the term overdose.Google Search Volume: Heat ExhaustionGoogle search volume for the term heat exhaustion. probability probability * 10M
- gtrends_rsv + gtrends_heat+stroke Google Search Volume: rsvGoogle search volume of the term rsv.Google Search Volume: Heat StrokeGoogle search volume for the term heat stroke. probability probability * 10M
- gtrends_shotgun + gtrends_9mm Google Search Volume: ShotgunGoogle search volume for the term shotgun.Google Search Volume: 9mmGoogle search volume for the term 9mm. probability probability * 10M
- gtrends_rsv_adjusted + gtrends_shotgun Google Search Volume: rsv_adjustedGoogle search volume of the term rsv_adjusted.Google Search Volume: ShotgunGoogle search volume for the term shotgun. probability probability * 10M
- data.csv.gz + data_year.csv.gz
@@ -11601,7 +11604,7 @@
Sources

Variables

- data_county.csv.gz + data.csv.gz
@@ -11646,7 +11649,7 @@
- data_state.csv.gz + data_county.csv.gz
@@ -11691,7 +11694,7 @@
- data.csv.gz + data_state.csv.gz
@@ -15817,6 +15820,168 @@
Sources

Variables

+
+ data.csv.gz +
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
VariableShort NameDescriptionTypeUnit
+ geography + GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
+ time + TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
+ n_deaths_cocaine + Cocaine overdose deaths12-month rolling total of provisional death counts involving cocaine.CountDeaths
+ n_deaths_heroin + Heroin overdose deaths12-month rolling total of provisional death counts involving heroin.CountDeaths
+ n_deaths_methadone + Methadone overdose deaths12-month rolling total of provisional death counts involving methadone.CountDeaths
+ n_deaths_any_opioid + Opioid overdose deaths12-month rolling total of provisional death counts involving natural, semi-synthetic, or synthetic opioids including methadone.CountDeaths
+ n_deaths_all_cause + All-cause deaths12-month rolling total of provisional all-cause death counts.CountDeaths
+ n_deaths_overdose + Drug overdose deathsProvisional count of drug overdose deaths. State-level data are 12-month rolling totals; county-level data are monthly.CountDeaths
+ pct_complete + Percent completePercentage of death records that have been fully processed for the reporting period.PercentPercent
+ pct_pending_invest + Percent pending investigationPercentage of death records still pending investigation for the reporting period.PercentPercent
+ suppressed_heroin + Heroin suppression flagIndicates whether the heroin death count was suppressed by NCHS. BinaryBinary indicator
+ suppressed_methadone + Methadone suppression flagIndicates whether the methadone death count was suppressed by NCHS.BinaryBinary indicator
+ suppressed_cocaine + Cocaine suppression flagIndicates whether the cocaine death count was suppressed by NCHS. BinaryBinary indicator
+ suppressed_any_opioid + Opioid suppression flagIndicates whether the opioid death count was suppressed by NCHS.BinaryBinary indicator
+ suppressed_all_cause + All-cause suppression flagIndicates whether the all-cause death count was suppressed by NCHS. BinaryBinary indicator
+ suppressed_overdose + Drug overdose suppression flag (state)Indicates whether the state drug overdose death count was suppressed by NCHS.BinaryBinary indicator
+
data_county.csv.gz
@@ -16105,6 +16270,25 @@
+
+
+

Nhtsa Crash

+

FARS is a nationwide census providing NHTSA, Congress, and the American public with yearly data on fatal injuries suffered in motor vehicle traffic crashes. FARS contains data on all crashes in the United States involving a fatality in a motor vehicle traffic crash on a public road. A fatal crash is one in which a motor vehicle is involved and at least one person dies within 30 days of the crash. Data are collected from police crash reports, state vehicle registration files, state driver licensing files, state highway department data, vital statistics, and other sources. FARS has been operational since 1975 and covers all 50 states, the District of Columbia, and Puerto Rico (national files cover the 50 states and DC).

+
Sources
+ +
+ Restrictions: + Public domain. NHTSA data is generally not subject to copyright restrictions. +
+

Variables

data.csv.gz
@@ -16140,152 +16324,34 @@
- n_deaths_cocaine - - Cocaine overdose deaths - 12-month rolling total of provisional death counts involving cocaine. - Count - Deaths - - - - n_deaths_heroin - - Heroin overdose deaths - 12-month rolling total of provisional death counts involving heroin. - Count - Deaths - - - - n_deaths_methadone - - Methadone overdose deaths - 12-month rolling total of provisional death counts involving methadone. - Count - Deaths - - - - n_deaths_any_opioid - - Opioid overdose deaths - 12-month rolling total of provisional death counts involving natural, semi-synthetic, or synthetic opioids including methadone. - Count - Deaths - - - - n_deaths_all_cause + nhtsa_fatalities - All-cause deaths - 12-month rolling total of provisional all-cause death counts. + Motor vehicle fatalities + Annual count of persons killed in motor vehicle traffic crashes. Count Deaths - n_deaths_overdose + nhtsa_fatal_crashes - Drug overdose deaths - Provisional count of drug overdose deaths. State-level data are 12-month rolling totals; county-level data are monthly. + Fatal crashes + Annual count of motor vehicle crashes resulting in at least one fatality. Count - Deaths - - - - pct_complete - - Percent complete - Percentage of death records that have been fully processed for the reporting period. - Percent - Percent - - - - pct_pending_invest - - Percent pending investigation - Percentage of death records still pending investigation for the reporting period. - Percent - Percent - - - - suppressed_heroin - - Heroin suppression flag - Indicates whether the heroin death count was suppressed by NCHS. - Binary - Binary indicator - - - - suppressed_methadone - - Methadone suppression flag - Indicates whether the methadone death count was suppressed by NCHS. - Binary - Binary indicator - - - - suppressed_cocaine - - Cocaine suppression flag - Indicates whether the cocaine death count was suppressed by NCHS. - Binary - Binary indicator - - - - suppressed_any_opioid - - Opioid suppression flag - Indicates whether the opioid death count was suppressed by NCHS. - Binary - Binary indicator - - - - suppressed_all_cause - - All-cause suppression flag - Indicates whether the all-cause death count was suppressed by NCHS. - Binary - Binary indicator + Crashes - suppressed_overdose + nhtsa_fatality_rate - Drug overdose suppression flag (state) - Indicates whether the state drug overdose death count was suppressed by NCHS. - Binary - Binary indicator + Fatality rate (per 100k) + Annual motor vehicle fatalities per 100,000 residents. Population denominator is 2021 Census. + Rate + Deaths per 100,000 -
-
-

Nhtsa Crash

-

FARS is a nationwide census providing NHTSA, Congress, and the American public with yearly data on fatal injuries suffered in motor vehicle traffic crashes. FARS contains data on all crashes in the United States involving a fatality in a motor vehicle traffic crash on a public road. A fatal crash is one in which a motor vehicle is involved and at least one person dies within 30 days of the crash. Data are collected from police crash reports, state vehicle registration files, state driver licensing files, state highway department data, vital statistics, and other sources. FARS has been operational since 1975 and covers all 50 states, the District of Columbia, and Puerto Rico (national files cover the 50 states and DC).

-
Sources
- -
- Restrictions: - Public domain. NHTSA data is generally not subject to copyright restrictions. -
-

Variables

data_age_sex.csv.gz
@@ -16520,69 +16586,6 @@
-
- data.csv.gz -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
VariableShort NameDescriptionTypeUnit
- geography - GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
- time - TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
- nhtsa_fatalities - Motor vehicle fatalitiesAnnual count of persons killed in motor vehicle traffic crashes.CountDeaths
- nhtsa_fatal_crashes - Fatal crashesAnnual count of motor vehicle crashes resulting in at least one fatality.CountCrashes
- nhtsa_fatality_rate - Fatality rate (per 100k)Annual motor vehicle fatalities per 100,000 residents. Population denominator is 2021 Census.RateDeaths per 100,000
-

NIS

@@ -16601,7 +16604,7 @@
Sources

Variables

- data_insurance.csv.gz + data.csv.gz
@@ -16617,31 +16620,22 @@
- - - - + + + + - - + + - - - - - - - - + - + - + - + + + + + + + + + + + + + + +
- geography + birth_year GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS codeBirth YearCalendar year the child was born.integeryear
- insurance + age Insurance StatusHealth insurance coverage status of the child.AgeAge group of surveyed children. categorical
- birth_year - Birth YearCalendar year the child was born.integeryear
vaccine @@ -16653,45 +16647,63 @@
- vax_uptake_insurance + vax_uptake_overall Insurance statusOverall Percent of survey respondents who received the indicated vaccine percent percent
- vax_uptake_insurance_lcl + vax_uptake_overall_lcl Insurance status lower 95% CIOverall lower 95% CI Percent of survey respondents who received the indicated vaccine percent percent
- vax_uptake_insurance_ucl + vax_uptake_overall_ucl Insurance status upper 95% CIOverall upper 95% CI Percent of survey respondents who received the indicated vaccine percent percent
- sample_size_insurance + sample_size_overall Insurance statusOverall Number of children surveyed for vaccination coverage estimates in the National Immunization Survey (NIS). percent percent
+ geography + GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
+ time + TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
- data_urban.csv.gz + data_insurance.csv.gz
@@ -16716,10 +16728,10 @@
- - + + @@ -16743,36 +16755,36 @@
- + - + - + - + @@ -16781,7 +16793,7 @@
- urban + insurance UrbanicityUrban or rural classification of residence.Insurance StatusHealth insurance coverage status of the child. categorical
- vax_uptake_urban + vax_uptake_insurance UrbanizationInsurance status Percent of survey respondents who received the indicated vaccine percent percent
- vax_uptake_urban_lcl + vax_uptake_insurance_lcl Urbanization lower 95% CIInsurance status lower 95% CI Percent of survey respondents who received the indicated vaccine percent percent
- vax_uptake_urban_ucl + vax_uptake_insurance_ucl Urbanization upper 95% CIInsurance status upper 95% CI Percent of survey respondents who received the indicated vaccine percent percent
- sample_size_urban + sample_size_insurance UrbanizationInsurance status Number of children surveyed for vaccination coverage estimates in the National Immunization Survey (NIS). percent percent
- data.csv.gz + data_urban.csv.gz
@@ -16797,22 +16809,31 @@
- - - - + + + + - - + + + + + + + + + - + - + - + - + - - - - - - - - - - - - - -
- birth_year + geography Birth YearCalendar year the child was born.integeryearGeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
- age + urban AgeAge group of surveyed children.UrbanicityUrban or rural classification of residence. categorical
+ birth_year + Birth YearCalendar year the child was born.integeryear
vaccine @@ -16824,58 +16845,40 @@
- vax_uptake_overall + vax_uptake_urban OverallUrbanization Percent of survey respondents who received the indicated vaccine percent percent
- vax_uptake_overall_lcl + vax_uptake_urban_lcl Overall lower 95% CIUrbanization lower 95% CI Percent of survey respondents who received the indicated vaccine percent percent
- vax_uptake_overall_ucl + vax_uptake_urban_ucl Overall upper 95% CIUrbanization upper 95% CI Percent of survey respondents who received the indicated vaccine percent percent
- sample_size_overall + sample_size_urban OverallUrbanization Number of children surveyed for vaccination coverage estimates in the National Immunization Survey (NIS). percent percent
- geography - GeographyFIPS code identifier (00 = national, 2-digit = state, 5-digit = county)identifierFIPS code
- time - TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
@@ -18735,7 +18738,7 @@
Sources

Variables

- data_exemptions.csv.gz + data.csv.gz
@@ -18825,7 +18828,7 @@
- data.csv.gz + data_exemptions.csv.gz
@@ -18932,7 +18935,7 @@
Sources

Variables

- data_county.csv.gz + data.csv.gz
@@ -18982,20 +18985,11 @@
- - - - - - -
Percent Percent
- is_state_estimate - is_state_estimate
- data_state.csv.gz + data_county.csv.gz
@@ -19045,11 +19039,20 @@
+ + + + + + +
Percent Percent
+ is_state_estimate + is_state_estimate
- data.csv.gz + data_state.csv.gz
@@ -19234,7 +19237,7 @@
Sources

Variables

- data_county.csv.gz + data.csv.gz
@@ -19306,7 +19309,7 @@
- data.csv.gz + data_county.csv.gz
@@ -19952,7 +19955,7 @@
Sources

Variables

- data_age_ethnicity.csv.gz + data_age.csv.gz
@@ -19993,15 +19996,6 @@
- - - - - - -
category
- race_ethnicity - Race/EthnicityRace/ethnicity categorycategory
pct_no_seatbelt @@ -22301,7 +22295,7 @@
- data_age_sex.csv.gz + data_age_ethnicity.csv.gz
@@ -22344,10 +22338,10 @@
- - + + @@ -24650,7 +24644,7 @@
- sex + race_ethnicity SexSex category (Male, Female, Overall)Race/EthnicityRace/ethnicity category category
- data_age.csv.gz + data_age_sex.csv.gz
@@ -24691,6 +24685,15 @@
+ + + + + + +
category
+ sex + SexSex category (Male, Female, Overall)category
pct_no_seatbelt @@ -28890,7 +28893,7 @@
- epic_prevalence_by_geography_county_and_source.parquet + epic_prevalence_by_geography.parquet
@@ -28913,6 +28916,15 @@
+ + + + + + + + + + + + + + - + + + + + + + + - + + + + + + + + + + + + +
identifier name or FIPS code
+ fips + FIPS CodeFIPS geographic identifieridentifierFIPS code
age @@ -28922,84 +28934,137 @@
category
+ outcome_name + OutcomeHealth outcome name (e.g., Diabetes, Obesity)category
source sourceSourceData source identifier for tall-format filescategory
- -
- - Values: - - Epic Cosmos: HbA1c - Epic Cosmos: BMI - Medicare FFS -
+ value 		value
- outcome_name + pct_captured outcome_namepct_captured
- -
- - Values: - - Diabetes - Obesity -
+ sample_size + 		sample_size
+
+
+ epic_prevalence_by_geography_county.parquet +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + +
VariableShort NameDescriptionTypeUnit
+ geography GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
+ age + Age GroupAge group categorycategory
+ outcome_name + OutcomeHealth outcome name (e.g., Diabetes, Obesity)category
- value + source Chronic disease prevalence (county)Estimated prevalence of diabetes or obesity at county level from Epic Cosmos or Medicare FFS.Percent%SourceData source identifier for tall-format filescategory
- year + value YearCalendar yeardateyearvalue
pct_captured Epic population capture (%, county)Percentage of the 2021 county population represented in the Epic Cosmos patient panel, by age group.Percent%pct_captured
sample_size Patient count (county)Number of patients used in the county-level analysis. Small counts from Epic Cosmos are reported as '10 or fewer'.CountCountsample_size
- epic_prevalence_by_geography_county.parquet + epic_prevalence_by_geography_county_and_source.parquet
@@ -29033,48 +29098,76 @@
+ + - - - + + + - - - + - - - - + + + + + + + + + + + - - - - + + + + - - - - + + + +
- outcome_name + source + source + +
+ + Values: + + Epic Cosmos: HbA1c + Epic Cosmos: BMI + Medicare FFS +
OutcomeHealth outcome name (e.g., Diabetes, Obesity)category
- source + outcome_name + outcome_name + +
+ + Values: + + Diabetes + Obesity +
SourceData source identifier for tall-format filescategory
value valueChronic disease prevalence (county)Estimated prevalence of diabetes or obesity at county level from Epic Cosmos or Medicare FFS.Percent%
+ year + YearCalendar yeardateyear
pct_captured pct_capturedEpic population capture (%, county)Percentage of the 2021 county population represented in the Epic Cosmos patient panel, by age group.Percent%
sample_size sample_sizePatient count (county)Number of patients used in the county-level analysis. Small counts from Epic Cosmos are reported as '10 or fewer'.CountCount
@@ -29198,7 +29291,7 @@
- epic_prevalence_by_geography.parquet + overdose_by_geography_and_source.parquet
@@ -29212,15 +29305,6 @@
- - - - - - - - - - - + + + + - - - + + + - - - + + + - + - - + + + + + + + + + - + - -
- geography - GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
fips @@ -29232,76 +29316,67 @@
- age + date Age GroupAge group categorycategoryDateDate (Saturday for weekly data)datedate
- outcome_name + value OutcomeHealth outcome name (e.g., Diabetes, Obesity)categoryvalue
- source + nchs_n_deaths_overdose SourceData source identifier for tall-format filescategorynchs_n_deaths_overdose
- value + suppressed valuesuppressed
- pct_captured + source pct_capturedSourceData source identifier for tall-format filescategory
+ age + Age GroupAge group categorycategory
- sample_size + time_end sample_sizetime_end
-
-
- overdose_by_geography_and_source_county.parquet -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - + @@ -29342,7 +29399,7 @@
VariableShort NameDescriptionTypeUnit
geography @@ -29313,27 +29388,9 @@
- date - DateDate (Saturday for weekly data)datedate
- source - SourceData source identifier for tall-format filescategory
- value + value_scale valuevalue_scale
- overdose_by_geography_and_source.parquet + overdose_by_geography_and_source_county.parquet
@@ -29358,12 +29415,12 @@
- - + + - + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + @@ -30167,7 +30170,7 @@
- fips + geography FIPS CodeFIPS geographic identifierGeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files) identifierFIPS codename or FIPS code
@@ -29374,33 +29431,6 @@
date date
- value - value
- nchs_n_deaths_overdose - nchs_n_deaths_overdose
- suppressed - suppressed
source @@ -29412,36 +29442,9 @@
- age - Age GroupAge group categorycategory
- time_end - time_end
- geography - GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
- value_scale + value value_scalevalue
- deaths_cause_age_demographics.parquet + deaths_cause_age.parquet
@@ -30199,33 +30202,6 @@
- - - - - - - - - - - - - - - - - - - - - - - - - + + + + - - - - + + + +
category
- sex - SexSex category (Male, Female, Overall)category
- race - race
- ethnicity - ethnicity
geography @@ -30270,25 +30246,25 @@
value value(source variable: bundle_injury_overdose/dist/deaths_cause_age.parquet|value)Injury death rateAge-adjusted death rate per 100,000 population by injury cause.RateDeaths per 100,000
N N(source variable: bundle_injury_overdose/dist/deaths_cause_age.parquet|N)Injury death countCount of injury deaths by cause of death and age group.CountDeaths
- deaths_cause_age.parquet + deaths_cause_age_demographics.parquet
@@ -30320,6 +30296,33 @@
+ + + + + + + + + + + + + + + + + + + + + - - - - + + + + - - - - + + + +
category
+ sex + SexSex category (Male, Female, Overall)category
+ race + race
+ ethnicity + ethnicity
geography @@ -30364,19 +30367,19 @@
value Injury death rateAge-adjusted death rate per 100,000 population by injury cause.RateDeaths per 100,000value(source variable: bundle_injury_overdose/dist/deaths_cause_age.parquet|value)
N Injury death countCount of injury deaths by cause of death and age group.CountDeathsN(source variable: bundle_injury_overdose/dist/deaths_cause_age.parquet|N)
@@ -31141,12 +31144,211 @@
- year + year + + Year + Calendar year + date + year + + + + age + + Age Group + Age group category + category + + + + + sex + + Sex + Sex category (Male, Female, Overall) + category + + + + + race_ethnicity + + Race/Ethnicity + Race/ethnicity category + category + + + + + payer + + payer + + + + + + + outcome_name + + outcome_name + + +
+ + Values: + + Opioid Use Disorder + Initiation and Engagement of Substance Use Treatment + Follow-Up After ED Visit for Alcohol and Drug Abuse + Concurrent Use of Opioids and Benzodiazepines +
+ + + + + + + source + + source + + +
+ + Values: + + Medicaid +
+ + + + + + + value + + Medicaid injury and overdose rate + Percentage of Medicaid beneficiaries with injury and overdose related measures. + Percent + % + + + +
+
+ overdose_by_demographics.parquet +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
VariableShort NameDescriptionTypeUnit
+ geography + GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
+ age + Age GroupAge group categorycategory
+ sex + SexSex category (Male, Female, Overall)category
+ race + race
+ ethnicity + ethnicity
+ time + TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
+ wisqars_rate_drug_poisoning + wisqars_rate_drug_poisoning(source variable: wisqars_rate_drug_poisoning)
+
+
+ overdose_by_geography_and_source.parquet +
+
+ + + + + + + + + + + + + + + + + + + + - - + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -31225,92 +31384,29 @@
- - - - - - -
VariableShort NameDescriptionTypeUnit
+ geography + GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
+ date YearCalendar yearDateDate (Saturday for weekly data)date dateyear
@@ -31157,53 +31359,6 @@
category
- sex - SexSex category (Male, Female, Overall)category
- race_ethnicity - Race/EthnicityRace/ethnicity categorycategory
- payer - payer
- outcome_name - outcome_name - -
- - Values: - - Opioid Use Disorder - Initiation and Engagement of Substance Use Treatment - Follow-Up After ED Visit for Alcohol and Drug Abuse - Concurrent Use of Opioids and Benzodiazepines -
-
source @@ -31215,7 +31370,11 @@
Values: - Medicaid + CDC/NCHS + Google Health Trends + CDC/WISQARS + Epic Cosmos + Medicare FFS
value Medicaid injury and overdose ratePercentage of Medicaid beneficiaries with injury and overdose related measures.Percent%
-
-
- overdose_by_demographics.parquet -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + - - - - + + + + - + - - - - - - - - - - - - - -
VariableShort NameDescriptionTypeUnit
- geography - GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
- age - Age GroupAge group categorycategory
- sex - SexSex category (Male, Female, Overall)categoryOverdose measureOverdose-related surveillance measure; units and definition depend on the source (see source column).Mixed (rate or probability, depending on source)Varies by source
- race + value_scale raceOverdose measure (scaled 0–1)Value rescaled to 0–1 relative to the geography and source maximum.Scaled0–1
- ethnicity + suppressed ethnicitysuppressed
- time - TimeDate in MM-DD-YYYY format (Saturday for weekly data)datedate
- wisqars_rate_drug_poisoning - wisqars_rate_drug_poisoning(source variable: wisqars_rate_drug_poisoning)
@@ -31473,99 +31569,6 @@
-
- overdose_by_geography_and_source.parquet -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
VariableShort NameDescriptionTypeUnit
- geography - GeographyGeographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)identifiername or FIPS code
- date - DateDate (Saturday for weekly data)datedate
- age - Age GroupAge group categorycategory
- source - source - -
- - Values: - - CDC/NCHS - Google Health Trends - CDC/WISQARS - Epic Cosmos - Medicare FFS -
-
- value - Overdose measureOverdose-related surveillance measure; units and definition depend on the source (see source column).Mixed (rate or probability, depending on source)Varies by source
- value_scale - Overdose measure (scaled 0–1)Value rescaled to 0–1 relative to the geography and source maximum.Scaled0–1
- suppressed - suppressed
-
overdose_deaths_county.parquet
@@ -33261,7 +33264,7 @@
- pneumococcus_by_geography_year.parquet + pneumococcus_by_geography.parquet
@@ -33320,20 +33323,11 @@
- - - - - - -
- value_smooth - Pneumococcal IPD % (3-year smoothed)3-year rolling average of the percent of IPD cases caused by each pneumococcal serotype.Percent%
- pneumococcus_by_geography.parquet + pneumococcus_by_geography_year.parquet
@@ -33392,6 +33386,15 @@
+ + + + + + +
+ value_smooth + Pneumococcal IPD % (3-year smoothed)3-year rolling average of the percent of IPD cases caused by each pneumococcal serotype.Percent%
diff --git a/resources/data_manifest.json b/resources/data_manifest.json index 584f3c5d0..530b71172 100644 --- a/resources/data_manifest.json +++ b/resources/data_manifest.json @@ -1,5 +1,5 @@ { - "generated": "2026-07-02T16:44:18Z", + "generated": "2026-07-02T13:07:24Z", "repository": "PopHIVE/Ingest", "github_raw_base": "https://raw.githubusercontent.com/PopHIVE/Ingest/main", "bundles": { @@ -1490,9 +1490,9 @@ ] }, { - "filename": "epic_prevalence_by_geography_county_and_source.parquet", - "path": "data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_county_and_source.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_county_and_source.parquet", + "filename": "epic_prevalence_by_geography.parquet", + "path": "data/bundle_chronic_diseases/dist/epic_prevalence_by_geography.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/epic_prevalence_by_geography.parquet", "columns": [ { "name": "geography", @@ -1502,6 +1502,14 @@ "unit": "name or FIPS code", "levels": {} }, + { + "name": "fips", + "short_name": "FIPS Code", + "description": "FIPS geographic identifier", + "measure_type": "identifier", + "unit": "FIPS code", + "levels": {} + }, { "name": "age", "short_name": "Age Group", @@ -1510,65 +1518,44 @@ "unit": "", "levels": {} }, - { - "name": "source", - "short_name": "source", - "description": "", - "measure_type": "", - "unit": "", - "levels": { - "Epic Cosmos: HbA1c": { - "source_id": "diabetes_a1c_6_5" - }, - "Epic Cosmos: BMI": { - "source_id": "obesity_bmi" - }, - "Medicare FFS": { - "source_id": "cms_diabetes" - } - } - }, { "name": "outcome_name", - "short_name": "outcome_name", - "description": "", - "measure_type": "", + "short_name": "Outcome", + "description": "Health outcome name (e.g., Diabetes, Obesity)", + "measure_type": "category", "unit": "", - "levels": { - "Diabetes": {}, - "Obesity": {} - } + "levels": {} }, { - "name": "value", - "short_name": "Chronic disease prevalence (county)", - "description": "Estimated prevalence of diabetes or obesity at county level from Epic Cosmos or Medicare FFS.", - "measure_type": "Percent", - "unit": "%", + "name": "source", + "short_name": "Source", + "description": "Data source identifier for tall-format files", + "measure_type": "category", + "unit": "", "levels": {} }, { - "name": "year", - "short_name": "Year", - "description": "Calendar year", - "measure_type": "date", - "unit": "year", + "name": "value", + "short_name": "value", + "description": "", + "measure_type": "", + "unit": "", "levels": {} }, { "name": "pct_captured", - "short_name": "Epic population capture (%, county)", - "description": "Percentage of the 2021 county population represented in the Epic Cosmos patient panel, by age group.", - "measure_type": "Percent", - "unit": "%", + "short_name": "pct_captured", + "description": "", + "measure_type": "", + "unit": "", "levels": {} }, { "name": "sample_size", - "short_name": "Patient count (county)", - "description": "Number of patients used in the county-level analysis. Small counts from Epic Cosmos are reported as '10 or fewer'.", - "measure_type": "Count", - "unit": "Count", + "short_name": "sample_size", + "description": "", + "measure_type": "", + "unit": "", "levels": {} } ] @@ -1637,9 +1624,9 @@ ] }, { - "filename": "epic_prevalence_by_geography_year.parquet", - "path": "data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_year.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_year.parquet", + "filename": "epic_prevalence_by_geography_county_and_source.parquet", + "path": "data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_county_and_source.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_county_and_source.parquet", "columns": [ { "name": "geography", @@ -1649,14 +1636,6 @@ "unit": "name or FIPS code", "levels": {} }, - { - "name": "fips", - "short_name": "FIPS Code", - "description": "FIPS geographic identifier", - "measure_type": "identifier", - "unit": "FIPS code", - "levels": {} - }, { "name": "age", "short_name": "Age Group", @@ -1665,25 +1644,6 @@ "unit": "", "levels": {} }, - { - "name": "year", - "short_name": "Year", - "description": "Calendar year", - "measure_type": "date", - "unit": "year", - "levels": {} - }, - { - "name": "outcome_name", - "short_name": "outcome_name", - "description": "", - "measure_type": "", - "unit": "", - "levels": { - "Diabetes": {}, - "Obesity": {} - } - }, { "name": "source", "short_name": "source", @@ -1694,34 +1654,53 @@ "Epic Cosmos: HbA1c": { "source_id": "diabetes_a1c_6_5" }, - "Epic Cosmos: ICD10": { - "source_id": "diabetes_dx_ccw" - }, "Epic Cosmos: BMI": { "source_id": "obesity_bmi" + }, + "Medicare FFS": { + "source_id": "cms_diabetes" } } }, + { + "name": "outcome_name", + "short_name": "outcome_name", + "description": "", + "measure_type": "", + "unit": "", + "levels": { + "Diabetes": {}, + "Obesity": {} + } + }, { "name": "value", - "short_name": "Chronic disease prevalence (Epic, state)", - "description": "Estimated prevalence of diabetes or obesity from Epic Cosmos EHR, by state and year.", + "short_name": "Chronic disease prevalence (county)", + "description": "Estimated prevalence of diabetes or obesity at county level from Epic Cosmos or Medicare FFS.", "measure_type": "Percent", "unit": "%", "levels": {} }, + { + "name": "year", + "short_name": "Year", + "description": "Calendar year", + "measure_type": "date", + "unit": "year", + "levels": {} + }, { "name": "pct_captured", - "short_name": "Epic population capture (%)", - "description": "Percentage of the 2021 state population represented in the Epic Cosmos patient panel, by age group.", + "short_name": "Epic population capture (%, county)", + "description": "Percentage of the 2021 county population represented in the Epic Cosmos patient panel, by age group.", "measure_type": "Percent", "unit": "%", "levels": {} }, { "name": "sample_size", - "short_name": "Epic patient count (state)", - "description": "Number of Epic Cosmos patients in the state-level analysis. Values ≤10 are reported as '10 or fewer'.", + "short_name": "Patient count (county)", + "description": "Number of patients used in the county-level analysis. Small counts from Epic Cosmos are reported as '10 or fewer'.", "measure_type": "Count", "unit": "Count", "levels": {} @@ -1729,9 +1708,9 @@ ] }, { - "filename": "epic_prevalence_by_geography.parquet", - "path": "data/bundle_chronic_diseases/dist/epic_prevalence_by_geography.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/epic_prevalence_by_geography.parquet", + "filename": "epic_prevalence_by_geography_year.parquet", + "path": "data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_year.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/epic_prevalence_by_geography_year.parquet", "columns": [ { "name": "geography", @@ -1758,82 +1737,64 @@ "levels": {} }, { - "name": "outcome_name", - "short_name": "Outcome", - "description": "Health outcome name (e.g., Diabetes, Obesity)", - "measure_type": "category", - "unit": "", - "levels": {} - }, - { - "name": "source", - "short_name": "Source", - "description": "Data source identifier for tall-format files", - "measure_type": "category", - "unit": "", - "levels": {} - }, - { - "name": "value", - "short_name": "value", - "description": "", - "measure_type": "", - "unit": "", + "name": "year", + "short_name": "Year", + "description": "Calendar year", + "measure_type": "date", + "unit": "year", "levels": {} }, { - "name": "pct_captured", - "short_name": "pct_captured", + "name": "outcome_name", + "short_name": "outcome_name", "description": "", "measure_type": "", "unit": "", - "levels": {} + "levels": { + "Diabetes": {}, + "Obesity": {} + } }, { - "name": "sample_size", - "short_name": "sample_size", + "name": "source", + "short_name": "source", "description": "", "measure_type": "", "unit": "", - "levels": {} - } - ] - }, - { - "filename": "overdose_by_geography_and_source_county.parquet", - "path": "data/bundle_chronic_diseases/dist/overdose_by_geography_and_source_county.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/overdose_by_geography_and_source_county.parquet", - "columns": [ - { - "name": "geography", - "short_name": "Geography", - "description": "Geographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)", - "measure_type": "identifier", - "unit": "name or FIPS code", - "levels": {} + "levels": { + "Epic Cosmos: HbA1c": { + "source_id": "diabetes_a1c_6_5" + }, + "Epic Cosmos: ICD10": { + "source_id": "diabetes_dx_ccw" + }, + "Epic Cosmos: BMI": { + "source_id": "obesity_bmi" + } + } }, { - "name": "date", - "short_name": "Date", - "description": "Date (Saturday for weekly data)", - "measure_type": "date", - "unit": "date", + "name": "value", + "short_name": "Chronic disease prevalence (Epic, state)", + "description": "Estimated prevalence of diabetes or obesity from Epic Cosmos EHR, by state and year.", + "measure_type": "Percent", + "unit": "%", "levels": {} }, { - "name": "source", - "short_name": "Source", - "description": "Data source identifier for tall-format files", - "measure_type": "category", - "unit": "", + "name": "pct_captured", + "short_name": "Epic population capture (%)", + "description": "Percentage of the 2021 state population represented in the Epic Cosmos patient panel, by age group.", + "measure_type": "Percent", + "unit": "%", "levels": {} }, { - "name": "value", - "short_name": "value", - "description": "", - "measure_type": "", - "unit": "", + "name": "sample_size", + "short_name": "Epic patient count (state)", + "description": "Number of Epic Cosmos patients in the state-level analysis. Values ≤10 are reported as '10 or fewer'.", + "measure_type": "Count", + "unit": "Count", "levels": {} } ] @@ -1925,6 +1886,45 @@ } ] }, + { + "filename": "overdose_by_geography_and_source_county.parquet", + "path": "data/bundle_chronic_diseases/dist/overdose_by_geography_and_source_county.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_chronic_diseases/dist/overdose_by_geography_and_source_county.parquet", + "columns": [ + { + "name": "geography", + "short_name": "Geography", + "description": "Geographic area name (state or country name for state/national files; 5-digit FIPS code for county-level files)", + "measure_type": "identifier", + "unit": "name or FIPS code", + "levels": {} + }, + { + "name": "date", + "short_name": "Date", + "description": "Date (Saturday for weekly data)", + "measure_type": "date", + "unit": "date", + "levels": {} + }, + { + "name": "source", + "short_name": "Source", + "description": "Data source identifier for tall-format files", + "measure_type": "category", + "unit": "", + "levels": {} + }, + { + "name": "value", + "short_name": "value", + "description": "", + "measure_type": "", + "unit": "", + "levels": {} + } + ] + }, { "filename": "overdose_deaths_county.parquet", "path": "data/bundle_chronic_diseases/dist/overdose_deaths_county.parquet", @@ -2524,9 +2524,9 @@ ] }, { - "filename": "deaths_cause_age_demographics.parquet", - "path": "data/bundle_injury_overdose/dist/deaths_cause_age_demographics.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/deaths_cause_age_demographics.parquet", + "filename": "deaths_cause_age.parquet", + "path": "data/bundle_injury_overdose/dist/deaths_cause_age.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/deaths_cause_age.parquet", "columns": [ { "name": "year", @@ -2544,30 +2544,6 @@ "unit": "", "levels": {} }, - { - "name": "sex", - "short_name": "Sex", - "description": "Sex category (Male, Female, Overall)", - "measure_type": "category", - "unit": "", - "levels": {} - }, - { - "name": "race", - "short_name": "race", - "description": "", - "measure_type": "", - "unit": "", - "levels": {} - }, - { - "name": "ethnicity", - "short_name": "ethnicity", - "description": "", - "measure_type": "", - "unit": "", - "levels": {} - }, { "name": "geography", "short_name": "Geography", @@ -2632,26 +2608,26 @@ }, { "name": "value", - "short_name": "value", - "description": "", - "measure_type": "", - "unit": "", + "short_name": "Injury death rate", + "description": "Age-adjusted death rate per 100,000 population by injury cause.", + "measure_type": "Rate", + "unit": "Deaths per 100,000", "levels": {} }, { "name": "N", - "short_name": "N", - "description": "", - "measure_type": "", - "unit": "", + "short_name": "Injury death count", + "description": "Count of injury deaths by cause of death and age group.", + "measure_type": "Count", + "unit": "Deaths", "levels": {} } ] }, { - "filename": "deaths_cause_age.parquet", - "path": "data/bundle_injury_overdose/dist/deaths_cause_age.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/deaths_cause_age.parquet", + "filename": "deaths_cause_age_demographics.parquet", + "path": "data/bundle_injury_overdose/dist/deaths_cause_age_demographics.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/deaths_cause_age_demographics.parquet", "columns": [ { "name": "year", @@ -2662,10 +2638,34 @@ "levels": {} }, { - "name": "age", - "short_name": "Age Group", - "description": "Age group category", - "measure_type": "category", + "name": "age", + "short_name": "Age Group", + "description": "Age group category", + "measure_type": "category", + "unit": "", + "levels": {} + }, + { + "name": "sex", + "short_name": "Sex", + "description": "Sex category (Male, Female, Overall)", + "measure_type": "category", + "unit": "", + "levels": {} + }, + { + "name": "race", + "short_name": "race", + "description": "", + "measure_type": "", + "unit": "", + "levels": {} + }, + { + "name": "ethnicity", + "short_name": "ethnicity", + "description": "", + "measure_type": "", "unit": "", "levels": {} }, @@ -2733,18 +2733,18 @@ }, { "name": "value", - "short_name": "Injury death rate", - "description": "Age-adjusted death rate per 100,000 population by injury cause.", - "measure_type": "Rate", - "unit": "Deaths per 100,000", + "short_name": "value", + "description": "", + "measure_type": "", + "unit": "", "levels": {} }, { "name": "N", - "short_name": "Injury death count", - "description": "Count of injury deaths by cause of death and age group.", - "measure_type": "Count", - "unit": "Deaths", + "short_name": "N", + "description": "", + "measure_type": "", + "unit": "", "levels": {} } ] @@ -3496,9 +3496,9 @@ ] }, { - "filename": "overdose_by_geography_and_source_county.parquet", - "path": "data/bundle_injury_overdose/dist/overdose_by_geography_and_source_county.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/overdose_by_geography_and_source_county.parquet", + "filename": "overdose_by_geography_and_source.parquet", + "path": "data/bundle_injury_overdose/dist/overdose_by_geography_and_source.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/overdose_by_geography_and_source.parquet", "columns": [ { "name": "geography", @@ -3508,14 +3508,6 @@ "unit": "name or FIPS code", "levels": {} }, - { - "name": "geography_fips", - "short_name": "geography_fips", - "description": "", - "measure_type": "", - "unit": "", - "levels": {} - }, { "name": "date", "short_name": "Date", @@ -3558,7 +3550,23 @@ }, { "name": "value", - "short_name": "value", + "short_name": "Overdose measure", + "description": "Overdose-related surveillance measure; units and definition depend on the source (see source column).", + "measure_type": "Mixed (rate or probability, depending on source)", + "unit": "Varies by source", + "levels": {} + }, + { + "name": "value_scale", + "short_name": "Overdose measure (scaled 0–1)", + "description": "Value rescaled to 0–1 relative to the geography and source maximum.", + "measure_type": "Scaled", + "unit": "0–1", + "levels": {} + }, + { + "name": "suppressed", + "short_name": "suppressed", "description": "", "measure_type": "", "unit": "", @@ -3567,9 +3575,9 @@ ] }, { - "filename": "overdose_by_geography_and_source_state_year.parquet", - "path": "data/bundle_injury_overdose/dist/overdose_by_geography_and_source_state_year.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/overdose_by_geography_and_source_state_year.parquet", + "filename": "overdose_by_geography_and_source_county.parquet", + "path": "data/bundle_injury_overdose/dist/overdose_by_geography_and_source_county.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/overdose_by_geography_and_source_county.parquet", "columns": [ { "name": "geography", @@ -3580,19 +3588,27 @@ "levels": {} }, { - "name": "age", - "short_name": "Age Group", - "description": "Age group category", - "measure_type": "category", + "name": "geography_fips", + "short_name": "geography_fips", + "description": "", + "measure_type": "", "unit": "", "levels": {} }, { - "name": "year", - "short_name": "Year", - "description": "Calendar year", + "name": "date", + "short_name": "Date", + "description": "Date (Saturday for weekly data)", "measure_type": "date", - "unit": "year", + "unit": "date", + "levels": {} + }, + { + "name": "age", + "short_name": "Age Group", + "description": "Age group category", + "measure_type": "category", + "unit": "", "levels": {} }, { @@ -3630,9 +3646,9 @@ ] }, { - "filename": "overdose_by_geography_and_source.parquet", - "path": "data/bundle_injury_overdose/dist/overdose_by_geography_and_source.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/overdose_by_geography_and_source.parquet", + "filename": "overdose_by_geography_and_source_state_year.parquet", + "path": "data/bundle_injury_overdose/dist/overdose_by_geography_and_source_state_year.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_injury_overdose/dist/overdose_by_geography_and_source_state_year.parquet", "columns": [ { "name": "geography", @@ -3642,14 +3658,6 @@ "unit": "name or FIPS code", "levels": {} }, - { - "name": "date", - "short_name": "Date", - "description": "Date (Saturday for weekly data)", - "measure_type": "date", - "unit": "date", - "levels": {} - }, { "name": "age", "short_name": "Age Group", @@ -3658,6 +3666,14 @@ "unit": "", "levels": {} }, + { + "name": "year", + "short_name": "Year", + "description": "Calendar year", + "measure_type": "date", + "unit": "year", + "levels": {} + }, { "name": "source", "short_name": "source", @@ -3684,23 +3700,7 @@ }, { "name": "value", - "short_name": "Overdose measure", - "description": "Overdose-related surveillance measure; units and definition depend on the source (see source column).", - "measure_type": "Mixed (rate or probability, depending on source)", - "unit": "Varies by source", - "levels": {} - }, - { - "name": "value_scale", - "short_name": "Overdose measure (scaled 0–1)", - "description": "Value rescaled to 0–1 relative to the geography and source maximum.", - "measure_type": "Scaled", - "unit": "0–1", - "levels": {} - }, - { - "name": "suppressed", - "short_name": "suppressed", + "short_name": "value", "description": "", "measure_type": "", "unit": "", @@ -5378,9 +5378,9 @@ ] }, { - "filename": "pneumococcus_by_geography_year.parquet", - "path": "data/bundle_respiratory/dist/pneumococcus_by_geography_year.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_respiratory/dist/pneumococcus_by_geography_year.parquet", + "filename": "pneumococcus_by_geography.parquet", + "path": "data/bundle_respiratory/dist/pneumococcus_by_geography.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_respiratory/dist/pneumococcus_by_geography.parquet", "columns": [ { "name": "serotype", @@ -5421,21 +5421,13 @@ "measure_type": "", "unit": "", "levels": {} - }, - { - "name": "value_smooth", - "short_name": "Pneumococcal IPD % (3-year smoothed)", - "description": "3-year rolling average of the percent of IPD cases caused by each pneumococcal serotype.", - "measure_type": "Percent", - "unit": "%", - "levels": {} } ] }, { - "filename": "pneumococcus_by_geography.parquet", - "path": "data/bundle_respiratory/dist/pneumococcus_by_geography.parquet", - "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_respiratory/dist/pneumococcus_by_geography.parquet", + "filename": "pneumococcus_by_geography_year.parquet", + "path": "data/bundle_respiratory/dist/pneumococcus_by_geography_year.parquet", + "url": "https://raw.githubusercontent.com/PopHIVE/Ingest/main/data/bundle_respiratory/dist/pneumococcus_by_geography_year.parquet", "columns": [ { "name": "serotype", @@ -5476,6 +5468,14 @@ "measure_type": "", "unit": "", "levels": {} + }, + { + "name": "value_smooth", + "short_name": "Pneumococcal IPD % (3-year smoothed)", + "description": "3-year rolling average of the percent of IPD cases caused by each pneumococcal serotype.", + "measure_type": "Percent", + "unit": "%", + "levels": {} } ] }, @@ -6560,130 +6560,41 @@ }, { "name": "ahrf_good_air_pct", - "short_name": "Good Air Quality (%)", - "description": "Percentage of measured days rated 'Good' by EPA Air Quality Index.", - "measure_type": "Percent", - "unit": "Percent" - }, - { - "name": "ahrf_pm25", - "short_name": "PM2.5 Annual Avg", - "description": "Annual average PM2.5 concentration (μg/m³) from EPA monitoring data.", - "measure_type": "Rate", - "unit": "μg/m³" - }, - { - "name": "ahrf_medicare_per_capita", - "short_name": "Medicare Per Capita Cost", - "description": "Actual Medicare FFS per capita spending for county residents.", - "measure_type": "Rate", - "unit": "Dollars per Medicare FFS enrollee" - }, - { - "name": "ahrf_ed_per_1k_medicare", - "short_name": "ED Visits per 1k Medicare", - "description": "County ED visit rate among traditional Medicare fee-for-service enrollees.", - "measure_type": "Rate", - "unit": "ED visits per 1,000 Medicare FFS beneficiaries" - } - ] - } - ] - }, - "brfss": { - "name": "brfss", - "display_name": "BRFSS", - "description": "The Behavioral Risk Factor Surveillance System (BRFSS) is the nation's premier system of health-related telephone surveys that collect state data about U.S. residents regarding their health-related risk behaviors, chronic health conditions, and use of preventive services. Established in 1984 with 15 states, BRFSS now collects data in all 50 states, the District of Columbia, and three U.S. territories, completing more than 400,000 adult interviews each year. BRFSS provides state-specific data on health conditions including obesity, diabetes, depression, and health behaviors such as heavy drinking, physical activity, and tobacco use. Data are available by age, sex, race/ethnicity, and education level. BRFSS is a critical resource for public health surveillance and policy-making at both state and national levels.", - "standard_files": [ - { - "filename": "data_survey.csv.gz", - "columns": [ - { - "name": "geography", - "short_name": "Geography", - "description": "FIPS code identifier (00 = national, 2-digit = state, 5-digit = county)", - "measure_type": "identifier", - "unit": "FIPS code" - }, - { - "name": "time", - "short_name": "Time", - "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", - "measure_type": "date", - "unit": "date" - }, - { - "name": "age", - "short_name": "Age", - "description": "Age group.", - "measure_type": "integer", - "unit": "years" - }, - { - "name": "prev_diabetes_survey", - "short_name": "Diabetes Prevalence (Survey)", - "description": "Estimated diabetes prevalence from BRFSS survey data.", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "prev_diabetes_survey_lcl", - "short_name": "Diabetes Prevalence Lower CI", - "description": "Lower bound of 95% confidence interval for diabetes prevalence.", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "prev_diabetes_survey_ucl", - "short_name": "Diabetes Prevalence Upper CI", - "description": "Upper bound of 95% confidence interval for diabetes prevalence.", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "prev_obesity_survey", - "short_name": "Obesity Prevalence (Survey)", - "description": "Estimated obesity prevalence (BMI >= 30) from BRFSS survey data.", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "prev_obesity_survey_lcl", - "short_name": "Obesity Prevalence Lower CI", - "description": "Lower bound of 95% confidence interval for obesity prevalence.", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "prev_obesity_survey_ucl", - "short_name": "Obesity Prevalence Upper CI", - "description": "Upper bound of 95% confidence interval for obesity prevalence.", - "measure_type": "percent", - "unit": "percent" + "short_name": "Good Air Quality (%)", + "description": "Percentage of measured days rated 'Good' by EPA Air Quality Index.", + "measure_type": "Percent", + "unit": "Percent" }, { - "name": "agec", - "short_name": "Age Category", - "description": "Categorical age grouping used in survey analysis.", - "measure_type": "categorical", - "unit": "category" + "name": "ahrf_pm25", + "short_name": "PM2.5 Annual Avg", + "description": "Annual average PM2.5 concentration (μg/m³) from EPA monitoring data.", + "measure_type": "Rate", + "unit": "μg/m³" }, { - "name": "sample_size_diab", - "short_name": "Sample Size (Diabetes)", - "description": "Number of survey respondents used to estimate diabetes prevalence.", - "measure_type": "integer", - "unit": "count" + "name": "ahrf_medicare_per_capita", + "short_name": "Medicare Per Capita Cost", + "description": "Actual Medicare FFS per capita spending for county residents.", + "measure_type": "Rate", + "unit": "Dollars per Medicare FFS enrollee" }, { - "name": "sample_size_obesity", - "short_name": "Sample Size (Obesity)", - "description": "Number of survey respondents used to estimate obesity prevalence.", - "measure_type": "integer", - "unit": "count" + "name": "ahrf_ed_per_1k_medicare", + "short_name": "ED Visits per 1k Medicare", + "description": "County ED visit rate among traditional Medicare fee-for-service enrollees.", + "measure_type": "Rate", + "unit": "ED visits per 1,000 Medicare FFS beneficiaries" } ] - }, + } + ] + }, + "brfss": { + "name": "brfss", + "display_name": "BRFSS", + "description": "The Behavioral Risk Factor Surveillance System (BRFSS) is the nation's premier system of health-related telephone surveys that collect state data about U.S. residents regarding their health-related risk behaviors, chronic health conditions, and use of preventive services. Established in 1984 with 15 states, BRFSS now collects data in all 50 states, the District of Columbia, and three U.S. territories, completing more than 400,000 adult interviews each year. BRFSS provides state-specific data on health conditions including obesity, diabetes, depression, and health behaviors such as heavy drinking, physical activity, and tobacco use. Data are available by age, sex, race/ethnicity, and education level. BRFSS is a critical resource for public health surveillance and policy-making at both state and national levels.", + "standard_files": [ { "filename": "data.csv.gz", "columns": [ @@ -6821,6 +6732,95 @@ "unit": "percent" } ] + }, + { + "filename": "data_survey.csv.gz", + "columns": [ + { + "name": "geography", + "short_name": "Geography", + "description": "FIPS code identifier (00 = national, 2-digit = state, 5-digit = county)", + "measure_type": "identifier", + "unit": "FIPS code" + }, + { + "name": "time", + "short_name": "Time", + "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", + "measure_type": "date", + "unit": "date" + }, + { + "name": "age", + "short_name": "Age", + "description": "Age group.", + "measure_type": "integer", + "unit": "years" + }, + { + "name": "prev_diabetes_survey", + "short_name": "Diabetes Prevalence (Survey)", + "description": "Estimated diabetes prevalence from BRFSS survey data.", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "prev_diabetes_survey_lcl", + "short_name": "Diabetes Prevalence Lower CI", + "description": "Lower bound of 95% confidence interval for diabetes prevalence.", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "prev_diabetes_survey_ucl", + "short_name": "Diabetes Prevalence Upper CI", + "description": "Upper bound of 95% confidence interval for diabetes prevalence.", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "prev_obesity_survey", + "short_name": "Obesity Prevalence (Survey)", + "description": "Estimated obesity prevalence (BMI >= 30) from BRFSS survey data.", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "prev_obesity_survey_lcl", + "short_name": "Obesity Prevalence Lower CI", + "description": "Lower bound of 95% confidence interval for obesity prevalence.", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "prev_obesity_survey_ucl", + "short_name": "Obesity Prevalence Upper CI", + "description": "Upper bound of 95% confidence interval for obesity prevalence.", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "agec", + "short_name": "Age Category", + "description": "Categorical age grouping used in survey analysis.", + "measure_type": "categorical", + "unit": "category" + }, + { + "name": "sample_size_diab", + "short_name": "Sample Size (Diabetes)", + "description": "Number of survey respondents used to estimate diabetes prevalence.", + "measure_type": "integer", + "unit": "count" + }, + { + "name": "sample_size_obesity", + "short_name": "Sample Size (Obesity)", + "description": "Number of survey respondents used to estimate obesity prevalence.", + "measure_type": "integer", + "unit": "count" + } + ] } ] }, @@ -9548,7 +9548,7 @@ "description": "The Mapping Medicare Disparities (MMD) by Population Tool is an interactive map that displays chronic disease prevalence, costs, hospitalization, and preventive care utilization data for Medicare Fee-for-Service beneficiaries. Data are available at the national, state, and county levels, stratified by age, race/ethnicity, and sex. Condition prevalence rates are calculated using ICD-10 diagnosis codes in Medicare claims data, following the Chronic Conditions Warehouse (CCW) definitions. The tool covers over 30 chronic conditions including diabetes, hypertension, COPD, heart failure, and mental health conditions, as well as preventive service utilization metrics. Data are updated annually.", "standard_files": [ { - "filename": "data_state_county_age_by_race.csv.gz", + "filename": "data_state_county_age.csv.gz", "columns": [ { "name": "geography", @@ -9910,7 +9910,7 @@ ] }, { - "filename": "data_state_county_age_by_sex.csv.gz", + "filename": "data_state_county_age_by_race.csv.gz", "columns": [ { "name": "geography", @@ -10272,7 +10272,7 @@ ] }, { - "filename": "data_state_county_age.csv.gz", + "filename": "data_state_county_age_by_sex.csv.gz", "columns": [ { "name": "geography", @@ -14154,7 +14154,7 @@ "description": "Google Health Trends data accessed via the Google Health Trends API, processed and collected using Yale DISSC's gtrends_collection framework. The data represents the probability of a short search session including a specific health-related term within a geography and timeframe, multiplied by 10 million for readability. Search volumes are provided at the DMA (Designated Market Area) and state level on a weekly basis. This data source enables tracking of public interest in health topics such as RSV, overdose, and naloxone as potential early indicators of disease activity or public health concerns.", "standard_files": [ { - "filename": "data_dma_year.csv.gz", + "filename": "data.csv.gz", "columns": [ { "name": "geography", @@ -14171,65 +14171,65 @@ "unit": "date" }, { - "name": "gtrends_drug+overdose", - "short_name": "Google Search Volume: Drug Overdose", - "description": "Google search volume for the term drug overdose.", + "name": "gtrends_rsv_vaccine", + "short_name": "Google Search Volume: rsv_vaccine", + "description": "Google search volume of the term rsv_vaccine.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_naloxone", - "short_name": "Google Search Volume: naloxone", - "description": "Google search volume of the term naloxone.", + "name": "gtrends_9mm", + "short_name": "Google Search Volume: 9mm", + "description": "Google search volume for the term 9mm.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_narcan", - "short_name": "Google Search Volume: narcan", - "description": "Google search volume of the term narcan.", + "name": "gtrends_naloxone", + "short_name": "Google Search Volume: naloxone", + "description": "Google search volume of the term naloxone.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_overdose", - "short_name": "Google Search Volume: overdose", - "description": "Google search volume of the term overdose.", + "name": "gtrends_drug+overdose", + "short_name": "Google Search Volume: Drug Overdose", + "description": "Google search volume for the term drug overdose.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_rsv_vaccine", - "short_name": "Google Search Volume: rsv_vaccine", - "description": "Google search volume of the term rsv_vaccine.", + "name": "gtrends_heat+exhaustion", + "short_name": "Google Search Volume: Heat Exhaustion", + "description": "Google search volume for the term heat exhaustion.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_rsv", - "short_name": "Google Search Volume: rsv", - "description": "Google search volume of the term rsv.", + "name": "gtrends_heat+stroke", + "short_name": "Google Search Volume: Heat Stroke", + "description": "Google search volume for the term heat stroke.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_heat+exhaustion", - "short_name": "Google Search Volume: Heat Exhaustion", - "description": "Google search volume for the term heat exhaustion.", + "name": "gtrends_narcan", + "short_name": "Google Search Volume: narcan", + "description": "Google search volume of the term narcan.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_heat+stroke", - "short_name": "Google Search Volume: Heat Stroke", - "description": "Google search volume for the term heat stroke.", + "name": "gtrends_overdose", + "short_name": "Google Search Volume: overdose", + "description": "Google search volume of the term overdose.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_9mm", - "short_name": "Google Search Volume: 9mm", - "description": "Google search volume for the term 9mm.", + "name": "gtrends_rsv", + "short_name": "Google Search Volume: rsv", + "description": "Google search volume of the term rsv.", "measure_type": "probability", "unit": "probability * 10M" }, @@ -14239,6 +14239,13 @@ "description": "Google search volume for the term shotgun.", "measure_type": "probability", "unit": "probability * 10M" + }, + { + "name": "gtrends_rsv_adjusted", + "short_name": "Google Search Volume: rsv_adjusted", + "description": "Google search volume of the term rsv_adjusted.", + "measure_type": "probability", + "unit": "probability * 10M" } ] }, @@ -14332,7 +14339,7 @@ ] }, { - "filename": "data_year.csv.gz", + "filename": "data_dma_year.csv.gz", "columns": [ { "name": "geography", @@ -14349,65 +14356,65 @@ "unit": "date" }, { - "name": "gtrends_rsv_vaccine", - "short_name": "Google Search Volume: rsv_vaccine", - "description": "Google search volume of the term rsv_vaccine.", + "name": "gtrends_drug+overdose", + "short_name": "Google Search Volume: Drug Overdose", + "description": "Google search volume for the term drug overdose.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_9mm", - "short_name": "Google Search Volume: 9mm", - "description": "Google search volume for the term 9mm.", + "name": "gtrends_naloxone", + "short_name": "Google Search Volume: naloxone", + "description": "Google search volume of the term naloxone.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_naloxone", - "short_name": "Google Search Volume: naloxone", - "description": "Google search volume of the term naloxone.", + "name": "gtrends_narcan", + "short_name": "Google Search Volume: narcan", + "description": "Google search volume of the term narcan.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_drug+overdose", - "short_name": "Google Search Volume: Drug Overdose", - "description": "Google search volume for the term drug overdose.", + "name": "gtrends_overdose", + "short_name": "Google Search Volume: overdose", + "description": "Google search volume of the term overdose.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_heat+exhaustion", - "short_name": "Google Search Volume: Heat Exhaustion", - "description": "Google search volume for the term heat exhaustion.", + "name": "gtrends_rsv_vaccine", + "short_name": "Google Search Volume: rsv_vaccine", + "description": "Google search volume of the term rsv_vaccine.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_heat+stroke", - "short_name": "Google Search Volume: Heat Stroke", - "description": "Google search volume for the term heat stroke.", + "name": "gtrends_rsv", + "short_name": "Google Search Volume: rsv", + "description": "Google search volume of the term rsv.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_narcan", - "short_name": "Google Search Volume: narcan", - "description": "Google search volume of the term narcan.", + "name": "gtrends_heat+exhaustion", + "short_name": "Google Search Volume: Heat Exhaustion", + "description": "Google search volume for the term heat exhaustion.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_overdose", - "short_name": "Google Search Volume: overdose", - "description": "Google search volume of the term overdose.", + "name": "gtrends_heat+stroke", + "short_name": "Google Search Volume: Heat Stroke", + "description": "Google search volume for the term heat stroke.", "measure_type": "probability", "unit": "probability * 10M" }, { - "name": "gtrends_rsv", - "short_name": "Google Search Volume: rsv", - "description": "Google search volume of the term rsv.", + "name": "gtrends_9mm", + "short_name": "Google Search Volume: 9mm", + "description": "Google search volume for the term 9mm.", "measure_type": "probability", "unit": "probability * 10M" }, @@ -14417,18 +14424,11 @@ "description": "Google search volume for the term shotgun.", "measure_type": "probability", "unit": "probability * 10M" - }, - { - "name": "gtrends_rsv_adjusted", - "short_name": "Google Search Volume: rsv_adjusted", - "description": "Google search volume of the term rsv_adjusted.", - "measure_type": "probability", - "unit": "probability * 10M" } ] }, { - "filename": "data.csv.gz", + "filename": "data_year.csv.gz", "columns": [ { "name": "geography", @@ -14672,7 +14672,7 @@ "description": "The Johns Hopkins University Measles Tracking Team compiles laboratory-confirmed measles case data from official state and county health department reports across the United States. The team aggregates data from 37+ jurisdictions, providing both state-level weekly summaries (using rash onset dates when available) and county-level daily case counts (based on official reporting dates). Data is updated on Tuesdays and Fridays at approximately 5:00 PM Eastern Time. The tracking effort was established in response to the 2025 measles outbreak to provide timely, granular geographic data on measles transmission. All data is released under CC BY 4.0 license with attribution required.", "standard_files": [ { - "filename": "data_county.csv.gz", + "filename": "data.csv.gz", "columns": [ { "name": "geography", @@ -14698,7 +14698,7 @@ ] }, { - "filename": "data_state.csv.gz", + "filename": "data_county.csv.gz", "columns": [ { "name": "geography", @@ -14724,7 +14724,7 @@ ] }, { - "filename": "data.csv.gz", + "filename": "data_state.csv.gz", "columns": [ { "name": "geography", @@ -17739,6 +17739,123 @@ "display_name": "NCHS Mortality", "description": "Provisional monthly counts of drug overdose deaths by type of drug, reported as 12-month backward rolling totals. Includes deaths involving cocaine, heroin, methadone, and opioids broadly. Data are from the Vital Statistics Rapid Release (VSRR) program and are provisional, meaning they are subject to revision as more death certificates are received and processed. Covers national and state levels. New York City and New York State are combined.", "standard_files": [ + { + "filename": "data.csv.gz", + "columns": [ + { + "name": "geography", + "short_name": "Geography", + "description": "FIPS code identifier (00 = national, 2-digit = state, 5-digit = county)", + "measure_type": "identifier", + "unit": "FIPS code" + }, + { + "name": "time", + "short_name": "Time", + "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", + "measure_type": "date", + "unit": "date" + }, + { + "name": "n_deaths_cocaine", + "short_name": "Cocaine overdose deaths", + "description": "12-month rolling total of provisional death counts involving cocaine.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "n_deaths_heroin", + "short_name": "Heroin overdose deaths", + "description": "12-month rolling total of provisional death counts involving heroin.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "n_deaths_methadone", + "short_name": "Methadone overdose deaths", + "description": "12-month rolling total of provisional death counts involving methadone.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "n_deaths_any_opioid", + "short_name": "Opioid overdose deaths", + "description": "12-month rolling total of provisional death counts involving natural, semi-synthetic, or synthetic opioids including methadone.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "n_deaths_all_cause", + "short_name": "All-cause deaths", + "description": "12-month rolling total of provisional all-cause death counts.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "n_deaths_overdose", + "short_name": "Drug overdose deaths", + "description": "Provisional count of drug overdose deaths. State-level data are 12-month rolling totals; county-level data are monthly.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "pct_complete", + "short_name": "Percent complete", + "description": "Percentage of death records that have been fully processed for the reporting period.", + "measure_type": "Percent", + "unit": "Percent" + }, + { + "name": "pct_pending_invest", + "short_name": "Percent pending investigation", + "description": "Percentage of death records still pending investigation for the reporting period.", + "measure_type": "Percent", + "unit": "Percent" + }, + { + "name": "suppressed_heroin", + "short_name": "Heroin suppression flag", + "description": "Indicates whether the heroin death count was suppressed by NCHS. ", + "measure_type": "Binary", + "unit": "Binary indicator" + }, + { + "name": "suppressed_methadone", + "short_name": "Methadone suppression flag", + "description": "Indicates whether the methadone death count was suppressed by NCHS.", + "measure_type": "Binary", + "unit": "Binary indicator" + }, + { + "name": "suppressed_cocaine", + "short_name": "Cocaine suppression flag", + "description": "Indicates whether the cocaine death count was suppressed by NCHS. ", + "measure_type": "Binary", + "unit": "Binary indicator" + }, + { + "name": "suppressed_any_opioid", + "short_name": "Opioid suppression flag", + "description": "Indicates whether the opioid death count was suppressed by NCHS.", + "measure_type": "Binary", + "unit": "Binary indicator" + }, + { + "name": "suppressed_all_cause", + "short_name": "All-cause suppression flag", + "description": "Indicates whether the all-cause death count was suppressed by NCHS. ", + "measure_type": "Binary", + "unit": "Binary indicator" + }, + { + "name": "suppressed_overdose", + "short_name": "Drug overdose suppression flag (state)", + "description": "Indicates whether the state drug overdose death count was suppressed by NCHS.", + "measure_type": "Binary", + "unit": "Binary indicator" + } + ] + }, { "filename": "data_county.csv.gz", "columns": [ @@ -17936,129 +18053,12 @@ "measure_type": "Rate", "unit": "Deaths per 100,000" }, - { - "name": "rate_unintentional_injuries", - "short_name": "Unintentional injury mortality rate", - "description": "Quarterly age-adjusted death rate from unintentional injuries per 100,000 population.", - "measure_type": "Rate", - "unit": "Deaths per 100,000" - } - ] - }, - { - "filename": "data.csv.gz", - "columns": [ - { - "name": "geography", - "short_name": "Geography", - "description": "FIPS code identifier (00 = national, 2-digit = state, 5-digit = county)", - "measure_type": "identifier", - "unit": "FIPS code" - }, - { - "name": "time", - "short_name": "Time", - "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", - "measure_type": "date", - "unit": "date" - }, - { - "name": "n_deaths_cocaine", - "short_name": "Cocaine overdose deaths", - "description": "12-month rolling total of provisional death counts involving cocaine.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "n_deaths_heroin", - "short_name": "Heroin overdose deaths", - "description": "12-month rolling total of provisional death counts involving heroin.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "n_deaths_methadone", - "short_name": "Methadone overdose deaths", - "description": "12-month rolling total of provisional death counts involving methadone.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "n_deaths_any_opioid", - "short_name": "Opioid overdose deaths", - "description": "12-month rolling total of provisional death counts involving natural, semi-synthetic, or synthetic opioids including methadone.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "n_deaths_all_cause", - "short_name": "All-cause deaths", - "description": "12-month rolling total of provisional all-cause death counts.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "n_deaths_overdose", - "short_name": "Drug overdose deaths", - "description": "Provisional count of drug overdose deaths. State-level data are 12-month rolling totals; county-level data are monthly.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "pct_complete", - "short_name": "Percent complete", - "description": "Percentage of death records that have been fully processed for the reporting period.", - "measure_type": "Percent", - "unit": "Percent" - }, - { - "name": "pct_pending_invest", - "short_name": "Percent pending investigation", - "description": "Percentage of death records still pending investigation for the reporting period.", - "measure_type": "Percent", - "unit": "Percent" - }, - { - "name": "suppressed_heroin", - "short_name": "Heroin suppression flag", - "description": "Indicates whether the heroin death count was suppressed by NCHS. ", - "measure_type": "Binary", - "unit": "Binary indicator" - }, - { - "name": "suppressed_methadone", - "short_name": "Methadone suppression flag", - "description": "Indicates whether the methadone death count was suppressed by NCHS.", - "measure_type": "Binary", - "unit": "Binary indicator" - }, - { - "name": "suppressed_cocaine", - "short_name": "Cocaine suppression flag", - "description": "Indicates whether the cocaine death count was suppressed by NCHS. ", - "measure_type": "Binary", - "unit": "Binary indicator" - }, - { - "name": "suppressed_any_opioid", - "short_name": "Opioid suppression flag", - "description": "Indicates whether the opioid death count was suppressed by NCHS.", - "measure_type": "Binary", - "unit": "Binary indicator" - }, - { - "name": "suppressed_all_cause", - "short_name": "All-cause suppression flag", - "description": "Indicates whether the all-cause death count was suppressed by NCHS. ", - "measure_type": "Binary", - "unit": "Binary indicator" - }, - { - "name": "suppressed_overdose", - "short_name": "Drug overdose suppression flag (state)", - "description": "Indicates whether the state drug overdose death count was suppressed by NCHS.", - "measure_type": "Binary", - "unit": "Binary indicator" + { + "name": "rate_unintentional_injuries", + "short_name": "Unintentional injury mortality rate", + "description": "Quarterly age-adjusted death rate from unintentional injuries per 100,000 population.", + "measure_type": "Rate", + "unit": "Deaths per 100,000" } ] } @@ -18069,6 +18069,46 @@ "display_name": "Nhtsa Crash", "description": "FARS is a nationwide census providing NHTSA, Congress, and the American public with yearly data on fatal injuries suffered in motor vehicle traffic crashes. FARS contains data on all crashes in the United States involving a fatality in a motor vehicle traffic crash on a public road. A fatal crash is one in which a motor vehicle is involved and at least one person dies within 30 days of the crash. Data are collected from police crash reports, state vehicle registration files, state driver licensing files, state highway department data, vital statistics, and other sources. FARS has been operational since 1975 and covers all 50 states, the District of Columbia, and Puerto Rico (national files cover the 50 states and DC).", "standard_files": [ + { + "filename": "data.csv.gz", + "columns": [ + { + "name": "geography", + "short_name": "Geography", + "description": "FIPS code identifier (00 = national, 2-digit = state, 5-digit = county)", + "measure_type": "identifier", + "unit": "FIPS code" + }, + { + "name": "time", + "short_name": "Time", + "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", + "measure_type": "date", + "unit": "date" + }, + { + "name": "nhtsa_fatalities", + "short_name": "Motor vehicle fatalities", + "description": "Annual count of persons killed in motor vehicle traffic crashes.", + "measure_type": "Count", + "unit": "Deaths" + }, + { + "name": "nhtsa_fatal_crashes", + "short_name": "Fatal crashes", + "description": "Annual count of motor vehicle crashes resulting in at least one fatality.", + "measure_type": "Count", + "unit": "Crashes" + }, + { + "name": "nhtsa_fatality_rate", + "short_name": "Fatality rate (per 100k)", + "description": "Annual motor vehicle fatalities per 100,000 residents. Population denominator is 2021 Census.", + "measure_type": "Rate", + "unit": "Deaths per 100,000" + } + ] + }, { "filename": "data_age_sex.csv.gz", "columns": [ @@ -18223,10 +18263,66 @@ "unit": "Deaths" } ] - }, + } + ] + }, + "nis": { + "name": "nis", + "display_name": "NIS", + "description": "The National Immunization Surveys (NIS) are a group of telephone surveys used to monitor vaccination coverage among children 19-35 months, teens 13-17 years, flu vaccinations for children 6 months-17 years, and COVID-19 vaccination for children, teens, and adults. The surveys are sponsored and conducted by the National Center for Immunization and Respiratory Diseases (NCIRD) of the CDC and authorized by the Public Health Service Act. NIS provides population-based, state and local area estimates of vaccination coverage using a standard survey methodology. Surveys collect data through telephone interviews with parents or guardians in all 50 states, the District of Columbia, and some U.S. territories. Cell phone numbers are randomly selected and called to enroll age-eligible children. With parental permission, vaccination providers are contacted to verify immunization records. Children and teens are classified as up to date based on ACIP-recommended vaccine doses.", + "standard_files": [ { "filename": "data.csv.gz", "columns": [ + { + "name": "birth_year", + "short_name": "Birth Year", + "description": "Calendar year the child was born.", + "measure_type": "integer", + "unit": "year" + }, + { + "name": "age", + "short_name": "Age", + "description": "Age group of surveyed children.", + "measure_type": "categorical", + "unit": "" + }, + { + "name": "vaccine", + "short_name": "Vaccine", + "description": "Type of vaccine being measured.", + "measure_type": "categorical", + "unit": "" + }, + { + "name": "vax_uptake_overall", + "short_name": "Overall", + "description": "Percent of survey respondents who received the indicated vaccine", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "vax_uptake_overall_lcl", + "short_name": "Overall lower 95% CI", + "description": "Percent of survey respondents who received the indicated vaccine", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "vax_uptake_overall_ucl", + "short_name": "Overall upper 95% CI", + "description": "Percent of survey respondents who received the indicated vaccine", + "measure_type": "percent", + "unit": "percent" + }, + { + "name": "sample_size_overall", + "short_name": "Overall", + "description": "Number of children surveyed for vaccination coverage estimates in the National Immunization Survey (NIS).", + "measure_type": "percent", + "unit": "percent" + }, { "name": "geography", "short_name": "Geography", @@ -18240,37 +18336,9 @@ "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", "measure_type": "date", "unit": "date" - }, - { - "name": "nhtsa_fatalities", - "short_name": "Motor vehicle fatalities", - "description": "Annual count of persons killed in motor vehicle traffic crashes.", - "measure_type": "Count", - "unit": "Deaths" - }, - { - "name": "nhtsa_fatal_crashes", - "short_name": "Fatal crashes", - "description": "Annual count of motor vehicle crashes resulting in at least one fatality.", - "measure_type": "Count", - "unit": "Crashes" - }, - { - "name": "nhtsa_fatality_rate", - "short_name": "Fatality rate (per 100k)", - "description": "Annual motor vehicle fatalities per 100,000 residents. Population denominator is 2021 Census.", - "measure_type": "Rate", - "unit": "Deaths per 100,000" } ] - } - ] - }, - "nis": { - "name": "nis", - "display_name": "NIS", - "description": "The National Immunization Surveys (NIS) are a group of telephone surveys used to monitor vaccination coverage among children 19-35 months, teens 13-17 years, flu vaccinations for children 6 months-17 years, and COVID-19 vaccination for children, teens, and adults. The surveys are sponsored and conducted by the National Center for Immunization and Respiratory Diseases (NCIRD) of the CDC and authorized by the Public Health Service Act. NIS provides population-based, state and local area estimates of vaccination coverage using a standard survey methodology. Surveys collect data through telephone interviews with parents or guardians in all 50 states, the District of Columbia, and some U.S. territories. Cell phone numbers are randomly selected and called to enroll age-eligible children. With parental permission, vaccination providers are contacted to verify immunization records. Children and teens are classified as up to date based on ACIP-recommended vaccine doses.", - "standard_files": [ + }, { "filename": "data_insurance.csv.gz", "columns": [ @@ -18392,74 +18460,6 @@ "unit": "percent" } ] - }, - { - "filename": "data.csv.gz", - "columns": [ - { - "name": "birth_year", - "short_name": "Birth Year", - "description": "Calendar year the child was born.", - "measure_type": "integer", - "unit": "year" - }, - { - "name": "age", - "short_name": "Age", - "description": "Age group of surveyed children.", - "measure_type": "categorical", - "unit": "" - }, - { - "name": "vaccine", - "short_name": "Vaccine", - "description": "Type of vaccine being measured.", - "measure_type": "categorical", - "unit": "" - }, - { - "name": "vax_uptake_overall", - "short_name": "Overall", - "description": "Percent of survey respondents who received the indicated vaccine", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "vax_uptake_overall_lcl", - "short_name": "Overall lower 95% CI", - "description": "Percent of survey respondents who received the indicated vaccine", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "vax_uptake_overall_ucl", - "short_name": "Overall upper 95% CI", - "description": "Percent of survey respondents who received the indicated vaccine", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "sample_size_overall", - "short_name": "Overall", - "description": "Number of children surveyed for vaccination coverage estimates in the National Immunization Survey (NIS).", - "measure_type": "percent", - "unit": "percent" - }, - { - "name": "geography", - "short_name": "Geography", - "description": "FIPS code identifier (00 = national, 2-digit = state, 5-digit = county)", - "measure_type": "identifier", - "unit": "FIPS code" - }, - { - "name": "time", - "short_name": "Time", - "description": "Date in MM-DD-YYYY format (Saturday for weekly data)", - "measure_type": "date", - "unit": "date" - } - ] } ] }, @@ -19769,7 +19769,7 @@ "description": "SchoolVaxView monitors vaccination coverage among U.S. school-aged children. Data are collected annually by states, territories, and select local jurisdictions through school vaccination assessments, which review student vaccination records at kindergarten entry. These data are made available by the CDC.", "standard_files": [ { - "filename": "data_exemptions.csv.gz", + "filename": "data.csv.gz", "columns": [ { "name": "time", @@ -19830,7 +19830,7 @@ ] }, { - "filename": "data.csv.gz", + "filename": "data_exemptions.csv.gz", "columns": [ { "name": "time", @@ -19898,7 +19898,7 @@ "description": "A comprehensive study of medical vaccine exemption rates among U.S. kindergartners from 2009-2024, published in JAMA by Kiang et al. The study compiled exemption data from all 50 U.S. states and Washington, DC, providing state- and county-level medical exemption rates for MMR vaccination. The dataset spans prepandemic (2009-2019) and postpandemic (2020-2024) periods, enabling analysis of how exemption patterns changed over time and following the COVID-19 pandemic. Medical exemptions are granted when a physician determines that vaccination poses a health risk to a specific child, distinct from religious or philosophical exemptions. Values are rounded for privacy protection. The research was conducted in collaboration with NBC News and methodology is documented in an accompanying article. Full data and code are available on GitHub.", "standard_files": [ { - "filename": "data_county.csv.gz", + "filename": "data.csv.gz", "columns": [ { "name": "geography", @@ -19927,18 +19927,11 @@ "description": "Percentage of kindergarten children with non-medical exemptions from MMR vaccination requirements", "measure_type": "Percent", "unit": "Percent" - }, - { - "name": "is_state_estimate", - "short_name": "is_state_estimate", - "description": "", - "measure_type": "", - "unit": "" } ] }, { - "filename": "data_state.csv.gz", + "filename": "data_county.csv.gz", "columns": [ { "name": "geography", @@ -19967,11 +19960,18 @@ "description": "Percentage of kindergarten children with non-medical exemptions from MMR vaccination requirements", "measure_type": "Percent", "unit": "Percent" + }, + { + "name": "is_state_estimate", + "short_name": "is_state_estimate", + "description": "", + "measure_type": "", + "unit": "" } ] }, { - "filename": "data.csv.gz", + "filename": "data_state.csv.gz", "columns": [ { "name": "geography", @@ -20058,7 +20058,7 @@ "description": "The CDC National Wastewater Surveillance System (NWSS) tracks measles virus RNA in wastewater samples from participating wastewater treatment facilities across the United States. Wastewater surveillance provides a complement to traditional clinical surveillance by detecting viral shedding in a community regardless of healthcare-seeking behavior. The measles wastewater surveillance program was expanded in response to the 2025 measles outbreak to provide early warning of community transmission. Data include detection rates (percentage of samples positive), detection counts, sample counts, and population served by participating sewersheds. Surveillance data are aggregated at state and national levels on a weekly basis. This approach can detect measles circulation before cases are clinically confirmed, supporting rapid public health response.", "standard_files": [ { - "filename": "data_county.csv.gz", + "filename": "data.csv.gz", "columns": [ { "name": "geography", @@ -20105,7 +20105,7 @@ ] }, { - "filename": "data.csv.gz", + "filename": "data_county.csv.gz", "columns": [ { "name": "geography", @@ -20577,7 +20577,7 @@ "description": "The Youth Risk Behavior Surveillance System (YRBSS) is a set of school-based surveys conducted by the CDC that monitor health-related behaviors among U.S. high school students. The biennial national, state, and local surveys provide weighted prevalence estimates of behaviors contributing to the leading causes of death and disability. Data were accessed via the YRBS Explorer API. Estimates are provided overall and stratified (separately, not crossed) by sex, race/ethnicity, and grade. Estimates that CDC suppressed (e.g., small sample sizes) are omitted rather than imputed. State estimates are available only for jurisdictions that share data with CDC; Minnesota, Oregon, and Washington are not included, and New York state excludes New York City.", "standard_files": [ { - "filename": "data_age_ethnicity.csv.gz", + "filename": "data_age.csv.gz", "columns": [ { "name": "geography", @@ -20600,13 +20600,6 @@ "measure_type": "category", "unit": "" }, - { - "name": "race_ethnicity", - "short_name": "Race/Ethnicity", - "description": "Race/ethnicity category", - "measure_type": "category", - "unit": "" - }, { "name": "pct_no_seatbelt", "short_name": "Did not always wear a seat belt", @@ -22395,7 +22388,7 @@ ] }, { - "filename": "data_age_sex.csv.gz", + "filename": "data_age_ethnicity.csv.gz", "columns": [ { "name": "geography", @@ -22419,9 +22412,9 @@ "unit": "" }, { - "name": "sex", - "short_name": "Sex", - "description": "Sex category (Male, Female, Overall)", + "name": "race_ethnicity", + "short_name": "Race/Ethnicity", + "description": "Race/ethnicity category", "measure_type": "category", "unit": "" }, @@ -24213,7 +24206,7 @@ ] }, { - "filename": "data_age.csv.gz", + "filename": "data_age_sex.csv.gz", "columns": [ { "name": "geography", @@ -24236,6 +24229,13 @@ "measure_type": "category", "unit": "" }, + { + "name": "sex", + "short_name": "Sex", + "description": "Sex category (Male, Female, Overall)", + "measure_type": "category", + "unit": "" + }, { "name": "pct_no_seatbelt", "short_name": "Did not always wear a seat belt", diff --git a/scripts/build_data_table.R b/scripts/build_data_table.R new file mode 100644 index 000000000..25baa7bd5 --- /dev/null +++ b/scripts/build_data_table.R @@ -0,0 +1,588 @@ +# ============================================================================= +# Build Data Table +# Generates docs/data-table.html: an auto-updating overview table with one row +# per data source (Datasets tab) and one row per bundle (Bundles tab). +# +# Columns are derived automatically from the repository: +# - measure_info.json "_sources" (title, description, organization, url, +# restrictions, time_resolution) +# - standard/*.csv.gz data files (spatial / age / sex / other resolutions, +# earliest & latest observation dates) +# - git commit history (last-updated date of the standard data files) +# +# Run from the repository root (same as scripts/build_docs.R): +# Rscript scripts/build_data_table.R +# ============================================================================= + +suppressMessages({ + library(jsonlite) + library(vroom) + library(htmltools) +}) + +`%||%` <- function(x, y) { + if (is.null(x) || length(x) == 0) return(y) + if (is.character(x) && (is.na(x[1]) || !nzchar(x[1]))) return(y) + x +} + +# ----------------------------------------------------------------------------- +# Configuration +# ----------------------------------------------------------------------------- + +# Columns (as they appear in the standard files) that count toward each +# stratification. Detection is presence-based, per the data-table spec: +# a source is "Stratified" on a dimension if ANY of its standard files carries +# the corresponding column. +AGE_COLS <- c("age", "age_group", "agec") +SEX_COLS <- c("sex") + +# "Other" stratifying demographics -> display label. Extend as new sources add +# demographic breakdowns. (Measure dimensions such as virus/serotype/vaccine are +# intentionally excluded -- this column is for demographic strata only.) +OTHER_STRAT <- c( + race_ethnicity = "Race/Ethnicity", + race = "Race/Ethnicity", + ethnicity = "Race/Ethnicity", + education = "Education", + education_level = "Education", + educ = "Education", + urban = "Urbanicity", + urbanicity = "Urbanicity", + rural_urban = "Urbanicity", + metro = "Urbanicity", + insurance = "Insurance", + insurance_status = "Insurance", + payer = "Payer", + income = "Income", + income_level = "Income", + poverty = "Poverty", + disability = "Disability", + disability_status= "Disability", + grade = "School Grade", + wapo_school_grade= "School Grade", + birth_year = "Birth Cohort" +) + +# Candidate time columns, in preference order. +TIME_COLS <- c("time", "date", "week_end", "year") + +# Base URL for the source folders on GitHub (for the "Data URL" column). +GITHUB_DATA_BASE <- "https://github.com/PopHIVE/Ingest/tree/main/data" + +# Section anchor id for a folder on the data-dictionary page (docs/index.html). +# Must match build_docs.R: gsub("[^a-zA-Z0-9]", "-", name). +doc_section_id <- function(name) gsub("[^a-zA-Z0-9]", "-", name) + +# ----------------------------------------------------------------------------- +# Display-name helpers (kept consistent with scripts/build_docs.R) +# ----------------------------------------------------------------------------- +format_source_name <- function(name) { + name <- gsub("_", " ", name) + name <- tools::toTitleCase(name) + repl <- c("Cdc"="CDC","Jhu"="JHU","Mmr"="MMR","Cms"="CMS","Nssp"="NSSP", + "Nis"="NIS","Nrevss"="NREVSS","Nchs"="NCHS","Brfss"="BRFSS", + "Vaers"="VAERS","Amr"="AMR","Ili"="ILI","Nhsn"="NHSN","Nnds"="NNDS", + "Yrbss"="YRBSS","Ahrf"="AHRF","Acs"="ACS","Narms"="NARMS", + "Nhtsa"="NHTSA","Wisqars"="WISQARS","Nccr"="NCCR","Chr"="CHR") + for (k in names(repl)) name <- gsub(paste0("\\b", k, "\\b"), repl[[k]], name) + name +} + +format_bundle_name <- function(name) { + display <- sub("^bundle_", "", name) + display <- gsub("_", " ", display) + tools::toTitleCase(display) +} + +# Short one-sentence summary of a (possibly long) description. +short_summary <- function(x, max_chars = 300) { + x <- x %||% "" + x <- trimws(gsub("\\s+", " ", x)) + if (!nzchar(x)) return("") + first <- strsplit(x, "(?<=[.!?])\\s+", perl = TRUE)[[1]][1] + if (is.na(first)) first <- x + if (nchar(first) > max_chars) first <- paste0(substr(first, 1, max_chars - 1), "…") + first +} + +# ----------------------------------------------------------------------------- +# Data-file inspection helpers +# ----------------------------------------------------------------------------- + +get_standard_files <- function(source_dir) { + standard_dir <- file.path(source_dir, "standard") + if (!dir.exists(standard_dir)) return(character(0)) + list.files(standard_dir, pattern = "\\.csv\\.gz$", full.names = TRUE) +} + +get_columns <- function(filepath) { + tryCatch(names(vroom::vroom(filepath, n_max = 0, show_col_types = FALSE)), + error = function(e) character(0)) +} + +# Classify the geography levels present in one file. A file with no geography +# column represents a national aggregate (e.g. CDC national counts by age), so +# it is treated as "National". +GEO_COLS <- c("geography", "fips") +geo_levels <- function(filepath, cols) { + gcol <- GEO_COLS[GEO_COLS %in% cols][1] + if (is.na(gcol)) return("National") + vals <- tryCatch( + vroom::vroom(filepath, col_select = tidyselect::all_of(gcol), + col_types = cols(.default = col_character()), + show_col_types = FALSE)[[1]], + error = function(e) NULL) + if (is.null(vals)) return(character(0)) + vals <- trimws(vals[!is.na(vals) & nzchar(trimws(vals))]) + if (!length(vals)) return(character(0)) + vals <- unique(vals) + levs <- character(0) + is_nat <- vals %in% c("00", "0", "US", "USA", "United States") + if (any(is_nat)) levs <- c(levs, "National") + nc <- nchar(vals) + if (any(!is_nat & nc <= 2)) levs <- c(levs, "State") + if (any(nc >= 4 & nc <= 5)) levs <- c(levs, "County") + levs +} + +# Safe, format-aware date parser: never errors, returns a Date vector. +# Handles ISO (YYYY-MM-DD), US month-first (MM-DD-YYYY or MM/DD/YYYY) and +# year-only (YYYY) values, then drops implausible years (parse artifacts). +parse_dates <- function(vals) { + vals <- trimws(vals[!is.na(vals)]) + vals <- vals[nzchar(vals)] + if (!length(vals)) return(as.Date(character(0))) + # Year-only values (e.g. "2024") -> Dec 31 of that year. + if (all(grepl("^[0-9]{4}$", vals))) return(as.Date(paste0(vals, "-12-31"))) + + d <- rep(as.Date(NA), length(vals)) + iso <- grepl("^[0-9]{4}[-/]", vals) # 2024-01-31 + mdy <- grepl("^[0-9]{1,2}[-/][0-9]{1,2}[-/][0-9]{4}$", vals) # 01-31-2024 + if (any(iso)) d[iso] <- as.Date(gsub("/", "-", vals[iso]), format = "%Y-%m-%d") + if (any(mdy)) d[mdy] <- as.Date(gsub("/", "-", vals[mdy]), format = "%m-%d-%Y") + rest <- is.na(d) & !iso & !mdy + if (any(rest)) { + d[rest] <- suppressWarnings(tryCatch(as.Date(vals[rest]), + error = function(e) as.Date(NA))) + } + + d <- d[!is.na(d)] + if (!length(d)) return(as.Date(character(0))) + yr <- as.integer(format(d, "%Y")) + cur <- as.integer(format(Sys.Date(), "%Y")) + d[yr >= 1980 & yr <= cur + 1] +} + +# TRUE if any of `candidate_cols` is present AND carries a value other than the +# non-stratifying placeholders ("Overall", "All", "Total", ...). This makes a +# dataset count as stratified only when it actually breaks the measure down. +NONSTRAT_VALS <- c("overall", "all", "total", "all ages", "all races", + "both sexes", "all sexes", "") + +is_stratified <- function(filepath, cols, candidate_cols) { + length(strat_values(filepath, cols, candidate_cols)) > 0 +} + +# Distinct non-placeholder values of the first present stratifying column +# (e.g. the actual age groups). Empty if the column is absent or all "Overall". +strat_values <- function(filepath, cols, candidate_cols) { + col <- candidate_cols[candidate_cols %in% cols][1] + if (is.na(col)) return(character(0)) + vals <- tryCatch( + vroom::vroom(filepath, col_select = tidyselect::all_of(col), + col_types = cols(.default = col_character()), + show_col_types = FALSE)[[1]], + error = function(e) NULL) + if (is.null(vals)) return(character(0)) + vals <- trimws(vals[!is.na(vals)]) + vals <- vals[nzchar(vals)] + unique(vals[!(tolower(vals) %in% NONSTRAT_VALS)]) +} + +# Order age groups by their leading number ("0-4" < "18-49" < "65+"); values +# with no leading number sort last. +sort_age_groups <- function(x) { + num <- suppressWarnings(as.integer(sub("^[^0-9]*([0-9]+).*", "\\1", x))) + x[order(num, x, na.last = TRUE)] +} + +read_time_col <- function(filepath, cols) { + tcol <- TIME_COLS[TIME_COLS %in% cols][1] + if (is.na(tcol)) return(NULL) + tryCatch( + vroom::vroom(filepath, col_select = tidyselect::all_of(tcol), + col_types = cols(.default = col_character()), + show_col_types = FALSE)[[1]], + error = function(e) NULL) +} + +# Earliest / latest observation dates from one file (returns Date, length 2). +date_range <- function(filepath, cols) { + vals <- read_time_col(filepath, cols) + if (is.null(vals)) return(c(NA, NA)) + d <- parse_dates(vals) + if (!length(d)) return(c(NA, NA)) + c(min(d), max(d)) +} + +# Time resolution from measure_info (preferred) with a data-derived fallback. +normalize_resolution <- function(x) { + x <- tolower(trimws(x %||% "")) + if (!nzchar(x)) return(NA_character_) + if (grepl("week", x)) return("Weekly") + if (grepl("month", x)) return("Monthly") + if (grepl("year|annual", x)) return("Annual") + if (grepl("day|daily", x)) return("Daily") + if (grepl("quarter", x)) return("Quarterly") + tools::toTitleCase(x) +} + +resolution_from_dates <- function(filepath, cols) { + vals <- read_time_col(filepath, cols) + if (is.null(vals)) return(NA_character_) + d <- sort(unique(parse_dates(vals))) + if (length(d) < 2) return(NA_character_) + g <- as.numeric(stats::median(diff(d))) + if (g <= 2) "Daily" + else if (g <= 10) "Weekly" + else if (g <= 45) "Monthly" + else if (g <= 100) "Quarterly" + else "Annual" +} + +# Most recent git commit date (YYYY-MM-DD) across a set of files. +git_last_updated <- function(files) { + if (!length(files)) return(NA_character_) + dates <- vapply(files, function(f) { + out <- tryCatch( + system2("git", c("log", "-1", "--format=%cs", "--", f), + stdout = TRUE, stderr = FALSE), + error = function(e) character(0)) + if (length(out) == 0) NA_character_ else out[1] + }, character(1)) + dates <- dates[!is.na(dates) & nzchar(dates)] + if (!length(dates)) return(NA_character_) + max(dates) # ISO dates sort lexicographically +} + +# ----------------------------------------------------------------------------- +# Per-source summary +# ----------------------------------------------------------------------------- +summarize_source <- function(source_name, source_dir) { + measure_info <- tryCatch( + fromJSON(file.path(source_dir, "measure_info.json"), simplifyVector = FALSE), + error = function(e) list()) + + sources_meta <- measure_info[["_sources"]] + first_source <- if (!is.null(sources_meta) && length(sources_meta) > 0) sources_meta[[1]] else list() + + title <- first_source$name %||% format_source_name(source_name) + organization <- first_source$organization %||% "" + + # Brief description spans ALL sources so multi-source datasets aren't + # misrepresented by only the first (e.g. NCHS covers overdose AND 21 causes + # of mortality). One sentence per distinct source, joined. + descs <- character(0) + if (!is.null(sources_meta)) { + for (s in sources_meta) { + ss <- short_summary(s$description %||% "") + if (nzchar(ss)) descs <- c(descs, ss) + } + } + description <- paste(unique(descs), collapse = " ") + + data_url <- first_source$url %||% "" + restrictions <- first_source$restrictions %||% "" + + # time_resolution declared in measure_info (across all measures). + declared_res <- character(0) + for (key in names(measure_info)) { + if (key == "_sources") next + m <- measure_info[[key]] + if (is.list(m) && !is.null(m$time_resolution)) { + r <- normalize_resolution(m$time_resolution) + if (!is.na(r)) declared_res <- c(declared_res, r) + } + } + declared_res <- unique(declared_res) + + files <- get_standard_files(source_dir) + + geo <- character(0) + age_groups <- character(0) + sex_strat <- FALSE + other <- character(0) + mins <- as.Date(character(0)); maxs <- as.Date(character(0)) + derived_res <- character(0) + + for (f in files) { + cols <- get_columns(f) + if (!length(cols)) next + geo <- union(geo, geo_levels(f, cols)) + age_groups <- union(age_groups, strat_values(f, cols, AGE_COLS)) + if (!sex_strat && is_stratified(f, cols, SEX_COLS)) sex_strat <- TRUE + # Value-based (like age/sex): only count an "other" dimension when it + # actually varies -- a column that is entirely "Total"/"Overall" does not. + for (oc in intersect(names(OTHER_STRAT), cols)) { + if (length(strat_values(f, cols, oc))) other <- union(other, OTHER_STRAT[[oc]]) + } + dr <- date_range(f, cols) + if (!is.na(dr[1])) mins <- c(mins, as.Date(dr[1], origin = "1970-01-01")) + if (!is.na(dr[2])) maxs <- c(maxs, as.Date(dr[2], origin = "1970-01-01")) + if (!length(declared_res)) { + rr <- resolution_from_dates(f, cols) + if (!is.na(rr)) derived_res <- c(derived_res, rr) + } + } + + geo_order <- c("National", "State", "County") + spatial <- paste(geo_order[geo_order %in% geo], collapse = ", ") + + time_scale <- if (length(declared_res)) paste(declared_res, collapse = ", ") + else paste(unique(derived_res), collapse = ", ") + + list( + folder = source_name, + title = title, + description = description, + spatial = if (nzchar(spatial)) spatial else "—", + age = if (length(age_groups)) paste(sort_age_groups(age_groups), collapse = ", ") + else "Not Stratified", + sex = if (sex_strat) "Stratified" else "Not Stratified", + other = if (length(other)) paste(sort(other), collapse = ", ") else "—", + earliest = if (length(mins)) format(min(mins), "%Y-%m-%d") else "—", + latest = if (length(maxs)) format(max(maxs), "%Y-%m-%d") else "—", + time_scale = if (nzchar(time_scale)) time_scale else "—", + last_updated = git_last_updated(files) %||% "—", + restrictions = if (nzchar(restrictions)) restrictions else "—", + organization = if (nzchar(organization)) organization else "—", + data_url = data_url + ) +} + +# ----------------------------------------------------------------------------- +# Per-bundle summary (datasets involved come from process.json$source_files) +# ----------------------------------------------------------------------------- +summarize_bundle <- function(bundle_name, bundle_dir, valid_sources) { + datasets <- character(0) + + # (a) dcf-tracked source files, when present. + proc <- tryCatch( + fromJSON(file.path(bundle_dir, "process.json"), simplifyVector = FALSE), + error = function(e) list()) + src_files <- proc$source_files + if (!is.null(src_files) && length(src_files) > 0) { + datasets <- vapply(names(src_files), function(k) strsplit(k, "/")[[1]][1], + character(1)) + } + + # (b) sibling-source references in build.R (..//...). This is the + # authoritative current wiring and covers bundles with no source_files record. + build_path <- file.path(bundle_dir, "build.R") + if (file.exists(build_path)) { + txt <- readLines(build_path, warn = FALSE) + hits <- unlist(regmatches(txt, gregexpr("\\.\\./([A-Za-z0-9_]+)/", txt))) + hits <- sub("\\.\\./([A-Za-z0-9_]+)/.*", "\\1", hits) + datasets <- c(datasets, hits) + } + + # Keep only real sibling data sources; drop resources/, data/, self-refs, etc. + datasets <- unique(datasets) + datasets <- datasets[datasets %in% valid_sources & datasets != bundle_name] + datasets <- sort(vapply(datasets, format_source_name, character(1))) + + list( + folder = bundle_name, + title = format_bundle_name(bundle_name), + n = length(datasets), + datasets = if (length(datasets)) paste(datasets, collapse = ", ") else "—" + ) +} + +# ----------------------------------------------------------------------------- +# HTML building +# ----------------------------------------------------------------------------- +DATASET_HEADERS <- c("Dataset", "Content Title", "Brief Description", + "Spatial Resolution", "Age Resolution", "Sex Resolution", + "Other Resolutions", "Earliest Data", "Latest Data", + "Time Scale", "Last Refreshed", "Data Restrictions", + "Organization", "Source URL", "Data URL") + +strat_class <- function(v) if (identical(v, "Not Stratified")) "strat-notstratified" else "strat-stratified" + +dataset_row <- function(s) { + source_cell <- if (nzchar(s$data_url)) { + tags$a(href = s$data_url, target = "_blank", rel = "noopener", "Link") + } else "—" + data_cell <- tags$a(href = paste0(GITHUB_DATA_BASE, "/", s$folder), + target = "_blank", rel = "noopener", "GitHub") + dataset_cell <- tags$a(href = paste0("index.html#", doc_section_id(s$folder)), + tags$code(s$folder)) + tags$tr( + tags$td(dataset_cell), + tags$td(class = "title-cell", s$title), + tags$td(s$description), + tags$td(s$spatial), + tags$td(class = strat_class(s$age), s$age), + tags$td(class = strat_class(s$sex), s$sex), + tags$td(s$other), + tags$td(s$earliest), + tags$td(s$latest), + tags$td(s$time_scale), + tags$td(s$last_updated), + tags$td(s$restrictions), + tags$td(s$organization), + tags$td(source_cell), + tags$td(data_cell) + ) +} + +bundle_row <- function(b) { + folder_cell <- tags$a(href = paste0("index.html#", doc_section_id(b$folder)), + tags$code(b$folder)) + tags$tr( + tags$td(folder_cell), + tags$td(class = "title-cell", b$title), + tags$td(class = "text-center", b$n), + tags$td(b$datasets) + ) +} + +# ----------------------------------------------------------------------------- +# Main +# ----------------------------------------------------------------------------- +cat("Building data table...\n") + +data_dir <- "data" +all_dirs <- list.dirs(data_dir, recursive = FALSE, full.names = TRUE) + +# Every non-bundle data directory is a candidate "source" a bundle may reference. +valid_sources <- basename(all_dirs[!grepl("^bundle_", basename(all_dirs))]) + +all_dirs <- all_dirs[sapply(all_dirs, function(d) file.exists(file.path(d, "measure_info.json")))] + +source_dirs <- all_dirs[!grepl("^bundle_", basename(all_dirs))] +bundle_dirs <- all_dirs[grepl("^bundle_", basename(all_dirs))] + +# Only list sources that actually have standardized data files -- every dataset +# column is derived from standard/*.csv.gz, so sources with none (scaffolding +# templates or not-yet-standardized sources) are skipped. They appear +# automatically once standardized data is added. +has_standard <- vapply(source_dirs, function(d) length(get_standard_files(d)) > 0, logical(1)) +skipped <- basename(source_dirs[!has_standard]) +if (length(skipped)) { + cat(sprintf("Skipping %d source(s) with no standard data: %s\n", + length(skipped), paste(skipped, collapse = ", "))) +} +source_dirs <- source_dirs[has_standard] + +source_dirs <- source_dirs[order(basename(source_dirs))] +bundle_dirs <- bundle_dirs[order(basename(bundle_dirs))] + +cat(sprintf("Found %d data sources and %d bundles\n", length(source_dirs), length(bundle_dirs))) + +source_summaries <- lapply(seq_along(source_dirs), function(i) { + cat(sprintf(" source %s (%d/%d)\n", basename(source_dirs[i]), i, length(source_dirs))) + summarize_source(basename(source_dirs[i]), source_dirs[i]) +}) + +bundle_summaries <- lapply(seq_along(bundle_dirs), function(i) { + cat(sprintf(" bundle %s (%d/%d)\n", basename(bundle_dirs[i]), i, length(bundle_dirs))) + summarize_bundle(basename(bundle_dirs[i]), bundle_dirs[i], valid_sources) +}) + +updated_stamp <- format(Sys.Date(), "%B %d, %Y") + +datasets_table <- tags$table(id = "datasets-table", + class = "display table table-striped table-bordered table-hover", style = "width:100%", + tags$thead(tags$tr(lapply(DATASET_HEADERS, tags$th))), + tags$tbody(lapply(source_summaries, dataset_row)) +) + +bundles_table <- tags$table(id = "bundles-table", + class = "display table table-striped table-bordered table-hover", style = "width:100%", + tags$thead(tags$tr( + tags$th("Folder"), tags$th("Bundle"), tags$th("# Datasets"), + tags$th("Datasets Involved") + )), + tags$tbody(lapply(bundle_summaries, bundle_row)) +) + +page <- tags$html(lang = "en", + tags$head( + tags$meta(charset = "UTF-8"), + tags$meta(name = "viewport", content = "width=device-width, initial-scale=1"), + tags$title("PopHIVE Data Table"), + tags$link(rel = "stylesheet", + href = "https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css"), + tags$link(rel = "stylesheet", + href = "https://cdn.datatables.net/1.13.8/css/dataTables.bootstrap5.min.css"), + tags$style(HTML(" + body { padding: 1.5rem; } + h1 { margin-bottom: .25rem; } + .subtitle { color: #6c757d; margin-bottom: 1rem; } + table.dataTable td { font-size: .85rem; vertical-align: top; } + table.dataTable th { font-size: .8rem; } + .title-cell { font-weight: 600; } + .strat-stratified { color: #146c43; font-weight: 600; } + .strat-notstratified { color: #6c757d; } + .nav-tabs { margin-bottom: 1rem; } + ")) + ), + tags$body( + tags$h1("PopHIVE Data Table"), + tags$p(class = "subtitle", + "Overview of all standardized data sources and combined bundles in the ", + tags$a(href = "https://github.com/PopHIVE/Ingest", target = "_blank", "PopHIVE/Ingest"), + " repository. Automatically generated from repository files — last updated ", + updated_stamp, ". ", + tags$a(href = "index.html", "View full data documentation →")), + + tags$ul(class = "nav nav-tabs", id = "mainTabs", role = "tablist", + tags$li(class = "nav-item", role = "presentation", + tags$button(class = "nav-link active", id = "datasets-tab", + `data-bs-toggle` = "tab", `data-bs-target` = "#datasets-pane", + type = "button", role = "tab", "Datasets", + tags$span(class = "badge bg-secondary ms-2", length(source_summaries)))), + tags$li(class = "nav-item", role = "presentation", + tags$button(class = "nav-link", id = "bundles-tab", + `data-bs-toggle` = "tab", `data-bs-target` = "#bundles-pane", + type = "button", role = "tab", "Bundles", + tags$span(class = "badge bg-secondary ms-2", length(bundle_summaries)))) + ), + + tags$div(class = "tab-content", + tags$div(class = "tab-pane fade show active", id = "datasets-pane", role = "tabpanel", + tags$div(class = "table-responsive", datasets_table)), + tags$div(class = "tab-pane fade", id = "bundles-pane", role = "tabpanel", + tags$div(class = "table-responsive", bundles_table)) + ), + + tags$script(src = "https://code.jquery.com/jquery-3.7.1.min.js"), + tags$script(src = "https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"), + tags$script(src = "https://cdn.datatables.net/1.13.8/js/jquery.dataTables.min.js"), + tags$script(src = "https://cdn.datatables.net/1.13.8/js/dataTables.bootstrap5.min.js"), + tags$script(HTML(" + $(function () { + var dsTable = $('#datasets-table').DataTable({ + pageLength: 25, order: [[1, 'asc']], scrollX: true + }); + $('#bundles-table').DataTable({ + pageLength: 25, order: [[1, 'asc']] + }); + // DataTables mis-measures column widths when initialized inside a hidden + // tab; recalculate when a tab is shown. + $('button[data-bs-toggle=\"tab\"]').on('shown.bs.tab', function () { + $.fn.dataTable.tables({visible: true, api: true}).columns.adjust(); + }); + }); + ")) + ) +) + +if (!dir.exists("docs")) dir.create("docs") +output_path <- "docs/data-table.html" +cat(sprintf("Writing %s...\n", output_path)) +save_html(page, output_path) +cat("Done.\n") diff --git a/scripts/build_docs.R b/scripts/build_docs.R index 125aa9239..bbe480d0e 100644 --- a/scripts/build_docs.R +++ b/scripts/build_docs.R @@ -750,8 +750,12 @@ html_page <- tags$html(lang = "en", tags$nav(class = "navbar navbar-dark fixed-top", tags$div(class = "container-fluid", tags$a(class = "navbar-brand", href = "#", "PopHIVE Data Documentation"), - tags$span(class = "navbar-text text-light", - sprintf("Last updated: %s", format(Sys.Date(), "%B %d, %Y")) + tags$div(class = "d-flex align-items-center", + tags$a(class = "btn btn-outline-light btn-sm me-3", href = "data-table.html", + "Data Table →"), + tags$span(class = "navbar-text text-light", + sprintf("Last updated: %s", format(Sys.Date(), "%B %d, %Y")) + ) ) ) ),