# TantusData Summer Challenge: Authorship Comparison — Data

来源：https://www.kaggle.com/competitions/authorship-comparison/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set of pairs 
*   **test_texts.csv** - the test text contents with corresponding ids
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

**train.csv**
*   `author ` - author id
*   `content ` - corresponding text content

**test.csv**
*   `prediction_id` - id of prediction to use in submission file
*   `content_id_1` - id of first content from the pair corresponding to **test_texts.csv**
*   `content_id_2` - id of second content from the pair corresponding to **test_texts.csv**

**test_texts.csv**
*   `content_id` - id
*   `content` - corresponding text content

**sample_submission.csv**
*   `prediction_id` - predicted pair id
*   `label` - target column to predict. 1 for matching author and 0 otherwise.

There are no additional authors in test set other than those from the training set.