v0.7.0

MLJScikitLearnInterface v0.7.0

Diff since v0.6.1

• Update scikit learn to v1.4 by @tylerjthomas9 in #67
• Fix quoting in README shell lines by @abhro in #68
• Support Scikit-Learn v1.5, bump to v0.7 for release by @tylerjthomas9 in #69

Merged pull requests:

• Update scikit learn to v1.4 (#67) (@tylerjthomas9)
• Fix quoting in README shell lines (#68) (@abhro)
• Support Scikit-Learn v1.5, bump to v0.7 for release (#69) (@tylerjthomas9)

Closed issues:

• Fix classifiers that cannot handle only one single target class (#48)
• Naive passing of Julia class_weight dictionary does not work (#63)

v0.6.1

MLJScikitLearnInterface v0.6.1

Diff since v0.6.0

Merged pull requests:

• Allow Naive passing of Julia class_weight dictionary (#64) (@tylerjthomas9)
• Fix classifiers that cannot handle only one target class (#65) (@tylerjthomas9)

Closed issues:

• Standard LinearRegressor throws error due to unexpected keyword argument 'normalize' (#62)

v0.6.0

MLJScikitLearnInterface v0.6.0

Diff since v0.5.0

Merged pull requests:

• New models, automatically convert more fit results, and support for feature importances (#61) (@tylerjthomas9)

v0.5.0

MLJScikitLearnInterface v0.5.0

Diff since v0.4.0

Merged pull requests:

• Update README.md to avoid ScikitLearn.jl confusion (#59) (@tylerjthomas9)
• scikit-learn v1.3 support (#60) (@tylerjthomas9)

v0.4.0

MLJScikitLearnInterface v0.4.0

Diff since v0.3.0

Closed issues:

• Catch up with sckit-learn 1.0 (#40)

Merged pull requests:

• Conversion to PythonCall (#56) (@tylerjthomas9)

v0.3.0

MLJScikitLearnInterface v0.3.0

Diff since v0.2.0

Closed issues:

• Implement DBSCAN as a Static transformer? (#36)
• Problem installing python scikit-learn in CI (#42)
• Linear regressions not working with sklearn 1.2 due to normalize argument removal (#45)
• fitted_params for GaussianNBClassifier broken (#53)

Merged pull requests:

• Update README.md (#41) (@zsz00)
• add environ variable (#43) (@OkonSamuel)
• Add hack in CI to address python build issue (#44) (@ablaom)
• update code to support sklearn v1.2 (#50) (@OkonSamuel)
• Fix CI failure (#51) (@OkonSamuel)
• Add generic interface tests (#52) (@ablaom)
• For a 0.3.0 release (#54) (@ablaom)
• update fitted params for naive_bayes and linear discriminant analysis (#55) (@OkonSamuel)

v0.2.0

MLJScikitLearnInterface v0.2.0

Diff since v0.1.10

As detailed in this #38:

• Cleanup document strings
• Resolve minor issue with MLJModelInterface 0.1.4 release
• (breaking) Remove fields precompute_distances and n_jobs from KMeans as unsupported in the scikit-learn 1.0 model
• Require Julia 1.6 or higher

Closed issues:

• Issue to trigger new releases (#7)

Merged pull requests:

• Doc string cleanup (#38) (@ablaom)
• For a 0.2.0 release (#39) (@ablaom)

v0.1.10

MLJScikitLearnInterface v0.1.10

Diff since v0.1.9

Merged pull requests:

• Remove upper bound for alphas in CVRegressors (#34) (@jbrea)
• For a 0.1.10 release (#35) (@ablaom)

v0.1.9

MLJScikitLearnInterface v0.1.9

Diff since v0.1.8

Closed issues:

• Specifying kernel in GaussianProcessRegressor (#29)

Merged pull requests:

• Bump compat for MLJModelInterface; bump version (#32) (@ablaom)
• For a 0.1.9 release (#33) (@ablaom)

v0.1.8

MLJScikitLearnInterface v0.1.8

Diff since v0.1.7

Merged pull requests:

• update tagbot (#25) (@ablaom)
• Bump compatibility MLJModelInterface = "0.3.6,0.4"; adapt tests (#27) (@ablaom)
• For a 0.1.8 release (#28) (@ablaom)