# COVID19 Global Forecasting (Week 5) — Data

来源：https://www.kaggle.com/competitions/covid19-global-forecasting-week-5/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

In this challenge, you will be predicting the *daily* number of confirmed COVID19 cases in various locations across the world, as well as the number of resulting fatalities, for _future_ dates. This latest challenge includes US state county data.

## 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 *daily*

## 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.