# Exploring Mental Health Data-clone — Data

来源：https://www.kaggle.com/competitions/exploring-mental-health-data-clone/data

采集时间：2026-10-19T16:47:33Z

The dataset for this competition (both train and test) was generated from a deep learning model trained on the [Depression Survey/Dataset for Analysis](https://www.kaggle.com/datasets/sumansharmadataworld/depression-surveydataset-for-analysis) 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.

**Notes:**
- A number of data artifacts have been left in the synthetic dataset.
- This is not a particularly difficult dataset to model. It may be interesting to focus on different ways to visualize the dataset.

## 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