Add facilities to group data

We could add factories for `GroupedDataset` which group by categorical feature, or by label, e.g.
```python
data = GroupedDataset.by_label(dataset)
data2 = GroupedDataset.by_feature(dataset, feature_name)
data3 = GroupedDataset.by_feature(dataset, feature_name, bins=10) # For continuous features
data4 = GroupedDataset.by_cluster(dataset, clustering_model, ...) # maybe?
```

Look for existing dataset classes in pyDVL to understand the structure. The new GroupedDataset likely needs to be implemented as a subclass or wrapper. Check how grouping by categorical features, labels, or bins is handled elsewhere in the codebase. Start by examining the dataset module and see if there are tests for similar functionality to understand the expected interface.

索引モデルが issue の本文から書いたものです。