traja.trajectory.train_test_split

traja.trajectory.train_test_split(trajectories: list, train_size: float = 0.7, val_size: float = 0.15, test_size: float = 0.15, shuffle: bool = True, random_state: int | None = None) → Tuple[list, list, list][source]

Split trajectories into train, validation, and test sets for deep learning.

Parameters:

  • trajectories (list) – List of TrajaDataFrame trajectories

  • train_size (float) – Proportion for training set. Default 0.7.

  • val_size (float) – Proportion for validation set. Default 0.15.

  • test_size (float) – Proportion for test set. Default 0.15.

  • shuffle (bool) – Whether to shuffle before splitting. Default True.

  • random_state (int, optional) – Random seed for reproducibility.

Returns:

(train_trajectories, val_trajectories, test_trajectories)

Return type:

tuple

Raises:

ValueError – If sizes don’t sum to 1.0

Example

>>> import traja
>>> # Create sample trajectories
>>> trajs = [traja.generate(n=100) for _ in range(50)]
>>> train, val, test = traja.trajectory.train_test_split(trajs)
>>> len(train), len(val), len(test)
(35, 7, 8)

Note

Essential for training and evaluating deep learning models on trajectory data.