wsidata.DatasetAccessor

class DatasetAccessor(obj)

Bases: object

Accessor for dataset objects.

tile_feature(feature_key, tile_key='tiles', target_key=None, target_transform=None)

Create a TileFeatureDataset from the current object.

Parameters:

feature_keystr

The key of the feature table.

tile_keystr, default: “tiles”

The key of the tile table.

target_keystr

The key of the target table.

target_transform: callable

The transformation for the target.

Returns:

TileFeatureDataset

tile_feature_graph(feature_key, tile_key='tiles', graph_key=None, target_key=None)

Create a PyTorch Geometric Data object from the graph data in WSIData.

Parameters:

feature_keystr

The key for the tile features.

tile_keystr, default: “tiles”

The key for the tiles.

graph_keystr, optional

The key for tile graph, defaults to “{tile_key}_graph”.

target_keystr, optional

The key for the target data in the observation table.

Returns:

torch_geometric.data.Data

A PyTorch Geometric Data object containing: - x: Node features (image features) - edge_index: Graph connectivity - edge_attr: Edge attributes (distances) - y: Target values (if target_key is provided)

tile_images(tile_key='tiles', target_key=None, transform=None, target_transform=None, color_norm=None, image_size=None)

Create a TileImagesDataset from the current object.

Parameters:

tile_keystr, default: “tiles”

The key of the tile table.

target_keystr

The key of the target table.

transform: callable

The transformation for the input tiles.

target_transform: callable

The transformation for the target.

color_norm: str

image_sizeint or tuple of (int, int), optional

Hint for optimal pyramid level selection via shapes2tiles(). Does not resize the output — use transform for that.

Returns:

TileImagesDataset