# DataLabCup1: Predicting News Popularity — Data

来源：https://www.kaggle.com/competitions/datalabcup1-predicting-news-popularity/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## File descriptions

*   **train.csv** - the training set (contains the label - Popularity)
*   **test.csv** - the test set (you must predict the label - Popularity)
*   **sample_submission.csv** - the sample of submission format

## Data fields

*   **Id** - non-negative integer assigned uniquely to each news
*   **Page content** - the raw web page of news
*   **Popularity** - the popularity of news