Base classes for data splitting.
Defines
BaseSplitter, the interface implemented by the train/test splitters in tuiml.evaluation.splitting (KFold, StratifiedKFold, etc.).Classes
Base class for all data splitters.
All splitters implement the
split() method that yields (train_indices, test_indices) tuples.Methods
split
(self, X: np.ndarray, y: Optional[np.ndarray]=None, groups: Optional[np.ndarray]=None) -> Iterator[Tuple[np.ndarray, np.ndarray]]
split
(self, X: np.ndarray, y: Optional[np.ndarray]=None, groups: Optional[np.ndarray]=None) -> Iterator[Tuple[np.ndarray, np.ndarray]]
Generate train/test indices.
Parameters
X
ndarray of shape (n_samples, n_features)
Training data.
y
ndarray of shape (n_samples,)
Target values.
groups
ndarray of shape (n_samples,)
Group labels for samples.
Yields
train_indices
ndarray
Indices for training set.
test_indices
ndarray
Indices for test set.
get_n_splits
(self, X: Optional[np.ndarray]=None, y: Optional[np.ndarray]=None, groups: Optional[np.ndarray]=None) -> int
get_n_splits
(self, X: Optional[np.ndarray]=None, y: Optional[np.ndarray]=None, groups: Optional[np.ndarray]=None) -> int
Get the number of splits.
Parameters
X
ndarray
Training data (needed for some splitters).
y
ndarray
Target values.
groups
ndarray
Group labels.
Returns
n_splits
int
Number of splits.