# COVID19 Global Forecasting (Week 3) — Data

来源：https://www.kaggle.com/competitions/covid19-global-forecasting-week-3/data

采集时间：2026-10-24T10:03:48Z

In this challenge, you will be predicting the *cumulative* number of confirmed COVID19 cases in various locations across the world, as well as the number of resulting fatalities, for _future_ dates.

*We understand this is a serious situation, and in no way want to trivialize the human impact this crisis is causing by predicting fatalities. Our goal is to provide better methods for estimates that can assist medical and governmental institutions to prepare and adjust as pandemics unfold*.

## Files
 - `train.csv` - the training data (you are encouraged to join in many more useful external datasets)
 - `test.csv` - the dates to predict; there is a week of overlap with the training data for the initial Public leaderboard. Once submissions are paused, the Public leaderboard will update based on last 28 days of predicted data.
 - `submission.csv` - a sample submission in the correct format; again, predictions should be *cumulative*

## Data Source
 - This evaluation data for this competition comes from **[John Hopkins CSSE](https://github.com/CSSEGISandData/COVID-19/tree/master/csse_covid_19_data/csse_covid_19_time_series)**, which is uninvolved in the competition. 
 - See their [README](https://github.com/CSSEGISandData/COVID-19) for a description of how the data was collected.
 - They are currently updating the data daily.