Helpers

Helper functions for data manipulation.

unravel.utils.dummy_labels(dataset)

Create dummy labels to feed into GraphNeuralNetworkConverter

Parameters:

dataset (TrackingDataset)

Return type:

Dict

unravel.utils.add_dummy_label_column(dataset, by=['gameId', 'playId', 'frameId'], column_name='label', random_seed=None)

Parameters:

• dataset (DataFrame)

• by (List[str])

• column_name (str)

• random_seed (float | None)

unravel.utils.dummy_graph_ids(dataset)

Create dummy graph_ids to feed into GraphNeuralNetworkConverter

Parameters:

dataset (TrackingDataset)

Return type:

Dict

unravel.utils.add_graph_id_column(dataset, by=['game_id', 'play_id'], column_name='graph_id')

Parameters:

• dataset (DataFrame)

• by (List[str])

• column_name (str)

from unravel.utils import add_dummy_label_column

# Add random binary labels
dataset.dataset = add_dummy_label_column(dataset.dataset)

Adding Graph IDs

from unravel.utils import add_graph_id_column

# Each frame is a separate graph
dataset.dataset = add_graph_id_column(dataset.dataset, by=["frame_id"])

# Group by possession
dataset.dataset = add_graph_id_column(
    dataset.dataset,
    by=["ball_owning_team_id", "period_id"]
)