# DataMining_2025Spring_Homework1 — Data

来源：https://www.kaggle.com/competitions/data-mining-2025-spring-homework-1/data

采集时间：2026-10-19T07:12:51Z


The training set and test set are provided in the [AnnData](https://anndata.readthedocs.io/en/stable/index.html) (`.h5ad`) format, a widely used data structure for single-cell data. In this format:
- Rows represent cells, and columns represent features (i.e., genome bins).
- The cell type annotations for each cell are stored in `adata.obs['cell_type']`.
- The training and test sets contain NaN values. Participants should take appropriate measures to handle these missing values effectively.

## Files

*   **train_adata.h5ad** - the training set with cell type annotations
*   **test_adata_noLabel.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
    0, IT-L23
    1, IT-L23
    2, ODC
```
    etc, where ID is the obs_names of single-cell data.