Awesome
Historical CDC Vaccination Time Series Data
Note: CDC stopped daily reporting of vaccination data on 2022-06-16 and changed to weekly reporting, so that is the final date of our data collection
This repository contains the most comprehensive and up-to-date historical CDC vaccination data. We aggregate daily vaccination snapshots from the CDC Vaccinations page. This is different than the CDC Vaccination Trends data, as that dataset is retroactively updated based on the date of vaccination, whereas this one is based on date of reporting and hence is not retroactively updated. Hence, for model training, we recommend using this non-retroactive dataset to avoid look-ahead bias.
Visualization of CDC data available at covid19-projections.com (through March 8, 2021). Learn more about how covid19-projections.com used this data on the Path to Normality page.
Raw Endpoints
Below are the raw API endpionts that we use to download and save the data daily:
- Vaccinations: https://covid.cdc.gov/covid-data-tracker/COVIDData/getAjaxData?id=vaccination_data
- Trends (New since 2021-02-03): https://covid.cdc.gov/covid-data-tracker/COVIDData/getAjaxData?id=vaccination_trends_data
Files
aggregated.csv- Raw/unedited CDC vaccination time series data, aggregated from daily CDC updates. Starts from 2020-12-20 for US nationwide and 2020-12-30 for all states. Missing dates mean that there were no CDC updates on those dates.aggregated_adjusted.csv- Adjusted time series data to account for missing days/entries. All lower-case columns are not in the original dataset. Column names should be self-explanatory. Feel free to open an issue with any questions/comments/bugs.cdc_vaccination_trends_data.csv- Raw US and Long-Term Care time series vaccination data (newly released by the CDC on 2021-02-03)