tslearn.utils.from_cesium_dataset

tslearn.utils.from_cesium_dataset(X)

Transform a cesium-compatible dataset into a tslearn dataset.

Parameters:

X: list of cesium TimeSeries

cesium-formatted dataset (cf. link)

Returns:

array, shape=(n_ts, sz, d)

tslearn-formatted dataset.

Notes

Conversion from/to cesium format requires cesium to be installed.

Examples

>>> from cesium.time_series import TimeSeries
>>> cesium_ds = [TimeSeries(m=numpy.array([1, 2, 3, 4]))]
>>> tslearn_arr = from_cesium_dataset(cesium_ds)
>>> tslearn_arr.shape
(1, 4, 1)
>>> cesium_ds = [
...     TimeSeries(m=numpy.array([[1, 2, 3, 4],
...                               [5, 6, 7, 8]]))
... ]
>>> tslearn_arr = from_cesium_dataset(cesium_ds)
>>> tslearn_arr.shape
(1, 4, 2)