FIX avoid spurious warning in IncrementalPCA due to n_samples == n_components_

[justinschuster]

Reference Issues/PRs

Fixes #19050.

What does this implement/fix? Explain your changes.

Added conditon

if self.n_components_ not in (n_samples, n_features):

in sklearn/decompostion/_incremental_pca.py

No longer throws warning message when n_conditions are equal to n_samples.

Any other comments?

Non-regression tests:

import sklearn.decomposition as skdecomp
ipca=skdecomp.IncrementalPCA(n_components=5)
ipca.partial_fit(np.random.randn(5,7))

import sklearn.decomposition as skdecomp
ipca=skdecomp.IncrementalPCA(n_components=5)
ipca.fit(np.random.randn(5,7))

Resulted in no warnings.

[glemaitre]

Please add an entry to the change log at doc/whats_new/v*.rst. Like the other entries there, please reference this pull request with :pr: and credit yourself (and other contributors if applicable) with :user:.

Please add a non-regression test that would fail at master but pass in this PR. Basically, we should check that we don't raise the warning.

[glemaitre]

I think that a comment is required to mention that as stated by @NicolasHug: "since we already ensure that we have n_components <= (n_samples, n_features)".

[thomasjpfan]

@justinschuster Are you still interested in working on this PR?