tslearn.utils.to_sklearn_dataset¶

tslearn.utils.to_sklearn_dataset(dataset, dtype=<class 'float'>, return_dim=False)[source]¶

Transforms a time series dataset so that it fits the format used in sklearn estimators.

Parameters:

datasetarray-like: The dataset of time series to be transformed.
dtypedata type (default: float64): Data type for the returned dataset.
return_dimboolean (optional, default: False): Whether the dimensionality (third dimension should be returned together with the transformed dataset).

Returns:

numpy.ndarray of shape (n_ts, sz * d): The transformed dataset of time series.
int (optional, if return_dim=True): The dimensionality of the original tslearn dataset (third dimension)

See also

to_time_series_dataset: Transforms a time series dataset to tslearn
format.

Examples

>>> to_sklearn_dataset([[1, 2]], return_dim=True)
(array([[1., 2.]]), 1)
>>> to_sklearn_dataset([[1, 2], [1, 4, 3]])
array([[ 1.,  2., nan],
       [ 1.,  4.,  3.]])