charavelg

Hi, thanks for the feedback Support of scikit-learn 1.7 is planned but next release will probably support scikit-learn 1.6 only, with hopefully FutureWarning not poping up anymore.

Support of scikit learn 1.7 is tracked in #549

Would you mind sharing some code and data? It would be useful to investigate your problem. Also, note that the tslearn.barycenters package provides a dtw_barycenter_averaging_petitjean implementation.

According to the error message the fitted dataset has shape (100, 100) which is different from the expected (100, 10, 5). Could you please check X['q_tensor'] shape before and after...

I think the tslearn.preprocessing.TimeSeriesResampler is a good canditate to host this feature. It currently only performs linear resampling with a given target size but probably can be extended to include...

Thanks for contributing!!! Unfortunately, it seems that UCR UEA datasets are not currently available, hence the failing CI. Not sure why though.

It's on azure pipelines but the problem should be fixed with #563 . I relaunched it. wait and see :)

Do you refer to https://scipy.github.io/devdocs/reference/generated/scipy.sparse.coo_array.html#coo-array ? Most of the metrics do not support sparse inputs though. Can you elaborate on your intended usage, where in tslearn do you expect to...

Would you mind elaboring a little? A title is far from enough even though it is a starting point. You could point to relevant documentation, explain your needs, ect. Hope...

When using numba prerelease (0.63.0b1) with [numpy prerelease ](https://pypi.anaconda.org/scientific-python-nightly-wheels/simple/numpy/2.4.0.dev0/numpy-2.4.0.dev0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl) , it seems[ trapz has been removed](https://github.com/numpy/numpy/commit/e4d64414394cbb2ae62e0f61c3230ba88f537090) from numpy (was deprecated since 2.0). Importing numba arraymath module raises `AttributeError("module 'numpy' has...