v1.2.0

MLJBase v1.2.0

Diff since v1.1.2

• (enhancement) Expose feature_importances in pipelines with a supporting supervised component, and in TransformedTargetModels with supporting atomic model (#963)

Merged pull requests:

• Fix some error message diagnostics (#962) (@ablaom)
• Allow Pipeline and TransformedTargetModel to support feature importances (#963) (@ablaom)
• For a 1.2.0 release (#964) (@ablaom)

v1.1.2

MLJBase v1.1.2

Diff since v1.1.1

Merged pull requests:

• Reduce sigdigits in parameter range display #948 (#958) (@adarshpalaskar1)
• Fix problem with serialization of nested models when component model overload save/restore (#960) (@ablaom)
• For a 1.1.2 release (#961) (@ablaom)

Closed issues:

• Serialized Composite Model Fails with XGBoost (#927)
• Reduce sigdigits in parameter range display (#948)

v1.1.1

MLJBase v1.1.1

Diff since v1.1.0

Merged pull requests:

• Fix Resampler update bug (#954) (@ablaom)
• For a 1.1.1 release (#955) (@ablaom)
• Bump 1.1.1 (#956) (@ablaom)
• For a 1.1.1 release - take II (#957) (@ablaom)

Closed issues:

• Update the class imbalance POC (#887)
• Post issues pointing to MLJBase 1.0 migration guide (#937)
• strategy or example for doing a stratified k-fold (#950)

v1.1.0

MLJBase v1.1.0

Diff since v1.0.1

• Arrange that calling plot(mach) on a machine mach calls plot(mach.fitresult), allowing model implementations to define plot recipes locally and have them work on machines wrapping their models (#951)

Merged pull requests:

• Remove measures from docs (#945) (@ablaom)
• CompatHelper: add new compat entry for Statistics at version 1, (keep existing compat) (#949) (@github-actions[bot])
• Forward (::Machine).fitresult to RecipesBase (#951) (@MilesCranmer)
• bump 1.1.0 (#952) (@ablaom)
• For a 1.1.0 release (#953) (@ablaom)

Closed issues:

• Measures page in documentation is empty (#944)

v1.0.1

MLJBase v1.0.1

Diff since v1.0.0

Merged pull requests:

• Rescue the orphaned docstring for evaluate (#939) (@ablaom)
• For a 1.0.1 release (#940) (@ablaom)
• purge refs to obsolete functionality (#941) (@ablaom)
• Remove redundant code (#942) (@ablaom)
• For a 1.0.1 release - Take II (#943) (@ablaom)

v1.0.0

MLJBase v1.0.0

Diff since v0.21.14

• (breaking) Remove the definition of all measures (mae, log_loss, etc), which are instead to be be loaded from StatisticalMeasures.jl. Remove completely measures previously corresponding to loss functions in LossFunctions.jl, which must now be explicitly imported and wrapped. For Julia < 1.9, make StatisticalMeasures a hard dependency and re-export it's names. For Julia 1.9 provide default measures for models using a Pkg extension, including StatisticalMeasures.jl as a weak dependency. See this migration guide for dealing with these breaking changes.

• (breaking) Remove the LossFunctions.jl dependency to close #570.

• Adapt the resampling (evaluate!) code (and a semi-duplication for model Stacks) to the new measure API set out in StatisticalMeasuresBase.jl.

• (breaking) Remove deprecated @pipeline and @from_network macros (#932)

• (breaking) Remove target as alias for transformer in TransformedTargetModel (#933)

Merged pull requests:

• Towards a 1.0.0 release (#908) (@ablaom)
• Replace built-in measures with measures in StatisticalMeasures.jl (#909) (@ablaom)
• Patch to fix StaticNetworkComposite issue (#931) (@ablaom)
• Remove deprecated code supporting @from_network and @pipeline. (#932) (@ablaom)
• Remove target as alias for transformer in TransformedTargetModel (#933) (@ablaom)
• Improve test coverage (#934) (@ablaom)
• For a 1.0.0 release (#935) (@ablaom)
• Add test for display of hyper-parameter ranges and models (#936) (@ablaom)

Closed issues:

• Add measures for multi-targets (#502)
• 1.0 checklist (#638)
• Remove target as alias for transformer in TransformedTarget(transformer=...) (#856)
• Multiclass measures with dictionary output throw errors in cross-validation using evaluate! (#915)
• Problem with StaticNetworkComposite models that have multiple inputs (#930)

v0.21.14

MLJBase v0.21.14

Diff since v0.21.13

Closed issues:

• Precompilation workload (#924)

Merged pull requests:

• improve show of confusion matrix by finding optimal column width (cw) (#923) (@Roeya)
• Preparing MLJBase to receive logger instances (#925) (@pebeto)
• bump 0.21.14 (#929) (@ablaom)

v0.21.13

MLJBase v0.21.13

Diff since v0.21.12

Merged pull requests:

• Bump version of LossFunctions.jl (#919) (@juliohm)
• bump 0.21.13 (#921) (@OkonSamuel)

v0.21.12

MLJBase v0.21.12

Diff since v0.21.11

Closed issues:

• Improve querying for measures (#529)
• Symbolic models in machines corresponding to multi-argument static transformers (#916)

Merged pull requests:

• Remove test/Project.toml and put back into [extras] (#907) (@ablaom)
• CompatHelper: add new compat entry for DelimitedFiles at version 1, (keep existing compat) (#911) (@github-actions[bot])
• Remove some orphaned code (#913) (@ablaom)
• Update README with moved MLJSerialization (#914) (@MilesCranmer)
• Fix signature in operation overloadings for machines (#917) (@ablaom)

v0.21.11

MLJBase v0.21.11

Diff since v0.21.10

Closed issues:

• Update to LossFunctions.jl v0.10 (#902)

Merged pull requests:

• Address breaking changes in LossFunctions.jl 0.10 and bump compat (#905) (@ablaom)