stability-selection

stability-selection copied to clipboard

Improve documentation of RandomizedLasso and LogisticRegression

1

thuijskens

Different estimators have different penalty param names, and also have different meanings: - `alpha` param in Lasso is a regularization strength (for bigger values of `alpha` regularization strength is ascending)...

a-n-ermakov

Support for max_features

2

#26 implementation Backward compatible with previous version

a-n-ermakov

`max_features` param can be usable on 2 steps of pipeline: - when fitting model with bootstrap subsamples (`SelectFromModel()` invocation) - when calculating final features mask inside of `get_support()` function

a-n-ermakov

thuijskens

thuijskens

thuijskens

thuijskens

Maintenance code, support for sci kit-learn version 1.2.2.

1

I have changed the project source code to support version 1.2.2 of scikit-learn. I hope to get your review and support.

TonyEinstein