Added
* `tslearn` estimators are now automatically tested to match `sklearn`
requirements "as much as possible" (cf. `tslearn` needs in
terms of data format, _etc._)
* `cdist_dtw` and `cdist_gak` now have a `n_jobs` parameter to parallelize
distance computations using `joblib.Parallel`
* `n_jobs` is also available as a prameter in
`silhouette_score`, `TimeSeriesKMeans`, `KNeighborsTimeSeries`,
`KNeighborsTimeSeriesClassifier`, `TimeSeriesSVC`,
`TimeSeriesSVR` and `GlobalAlignmentKernelKMeans`
Changed
* Faster DTW computations using `numba`
* `tslearn` estimators can be used in conjunction with `sklearn` pipelines and
cross-validation tools, even (for those concerned) with variable-length data
* doctests have been reduced to those necessary for documentation purposes, the
other tests being moved to `tests/*.py`
* The list of authors for the `tslearn` bibliographic reference has been
updated to include Johann Faouzi and Gilles Van de Wiele
* In `TimeSeriesScalerMinMax`, `min` and `max` parameters are now deprecated
in favor of `value_range`. Will be removed in v0.4
* In `TimeSeriesKMeans` and `silhouette_score`, `'gamma_sdtw'` is now
deprecated as a key for `metric_params` in favor of `gamma`. Will be removed