# Data Mining — Data

来源：https://www.kaggle.com/competitions/data-mining-hw-2025-spring/data

采集时间：2026-10-19T10:42:54Z


###What files do I need?  
train.h5ad & test.h5ad
###What should I expect the data format to be?  
The data is provided in the [AnnData](https://anndata.readthedocs.io/en/stable/index.html) (`.h5ad`) format, a widely used data structure for single-cell genomics. In this format:
- Rows represent cells, and columns represent features (i.e., peaks).
- The cell type annotations for each cell are stored in `adata.obs['cell_type']`.
###What am I predicting?  
The cell type of each cell in the test set.

## Files

*   **train.h5ad** - the training set with cell type annotations
*   **test.h5ad** - the test set without cell type annotations
*   **sample_submission.csv** - a sample submission file in the correct format
For each ID in the test set, you must predict a cell type for the TARGET variable. The file should contain a header and have the following format:

```python
    ID,TARGET
    2,HSC
    5,LMPP
    6,LMPP
```