search

CSSEGISandData / COVID-19

Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE
https://systems.jhu.edu/research/public-health/ncov/
29.11k stars 18.39k forks source link

Why time series for Czechia decreases? #6620

Closed radekm closed 1 year ago

radekm commented 1 year ago

Hi,

I'm looking in time_series_covid19_confirmed_global.csv at data for Czechia. On 2022-10-26 there are 4519021 cases and 1 day later on 2022-10-27 there are 4512136 cases.

How is it possible that cumulative data decreased by 6885 cases? Or are these not cumulative?

Thanks

radekm commented 1 year ago

I also looked official source and got following

image

But it's possible that I'm looking at something different, unfortunately I'm not sure.

CSSEGISandData commented 1 year ago

Hello,

Our data is cumulative. Decreases in our time series files occur when sources publish decreases in their data (due to data cleaning processes, etc.). We do our best to not retroactively modify our historical data. Czechia modifies their historical data with some regularity, hence why you don't see the decrease in their data. This has been discussed in #4296 and #3819. You'll find that the data snapshots in our repository do not perfectly line up with the historical data table published on their website due to data cleaning on their end.