# Categorical Feature Encoding Challenge — Data

来源：https://www.kaggle.com/competitions/cat-in-the-dat/data

采集时间：2026-10-19T17:32:37Z

In this competition, you will be predicting the probability `[0, 1]` of a binary `target` column.

The data contains binary features (`bin_*`), nominal features (`nom_*`), ordinal features (`ord_*`) as well as (potentially cyclical) `day` (of the week) and `month` features. The string ordinal features `ord_{3-5}` are lexically ordered according to `string.ascii_letters`.

Since the purpose of this competition is to explore various encoding strategies, the data has been simplified in that (1) there are no missing values, and (2) <strike>the test set does not contain any unseen feature values</strike> ([See this](https://www.kaggle.com/c/cat-in-the-dat/discussion/105537)). (Of course, in real-world settings both of these factors are often important to consider!)
 
## Files

*   **train.csv** - the training set
*   **test.csv** - the test set; you must make predictions against this data
*   **sample_submission.csv** - a sample submission file in the correct format