# Binary Machine Learning Contest — Data

来源：https://www.kaggle.com/competitions/binary-machine-learning-contest/data

采集时间：2026-10-19T09:26:09Z

The dataset for this competition (both train and test) was generated from a deep learning model trained on the UCI [Mushroom](https://archive.ics.uci.edu/dataset/73/mushroom) dataset. Feature distributions are close to, but not exactly the same, as the original. Feel free to use the original dataset as part of this competition, both to explore differences as well as to see whether incorporating the original in training improves model performance.

**Note:** Unlike many previous Tabular Playground datasets, data artifacts _have not_ been cleaned up. There are categorical values in the dataset that are not found in the original. It is up to the competitors how to handle this.

## Files

*   **train.csv** - the training dataset; `class` is the binary target (either `e` or `p`)
*   **test.csv** - the test dataset; your objective is to predict target `class` for each row
*   **sample_submission.csv** - a sample submission file in the correct format