Optbinning Versions Save

Fix setup.py find_packages excluding tests/.

New features:

• Optimal binning 2D with continuous target.

Improvements:

• Set tdigest and pympler dependencies as optional. This change avoids accumulation-tree issues faced by several users. Remove dill dependency.
• New continuous binning objective function leading to improvements in regression metrics.

Bugfixes:

• Fix binning 2D minimum difference constraints.

Tutorials:

• Tutorial: optimal binning 2D with continuous target

Bugfixes:

• Fix binning process summary update (#151 ).

• Fix pandas 1.4.0 (python > 3.8) slicing issue with method at (#148).

• Fix minor typos (#147 ).

• Fix binning plot for multiple special values.

New features:

• Treatment of special codes separately for optbinning classes (#115 ).

Bugfixes:

• Various bug fixes for the OptimalBinning2D class. See #138 for instance.

Tutorials

• Tutorial: optimal binning 2D with binary target

Improvements:

• Do not store optimization solver instance as class attribute.
• Do not store logger as a class attribute.

New features:

• Binning process supports sample_weight for binary target. #124

• Binning process can fix variables not satisfying selection criteria. #123

New features:

• Optimal binning 2D with binary target.

Improvements:

• Update bin string format in binning tables.
• Simplify logic when style="actual" in binning table plots.

API changes:

• Scorecard fit method arguments changed to the usual (X, y): #111

New features:

• Counterfactual explanations for scorecard modelling.

Improvements:

• Replace pickle by dill in save and load methods.

Bugfixes:

• Parallel binning uses joblib: #103
• Fix custom metric_special and metric_missing in binning_transform_params.

New features:

• Batch and streaming binning process.

Improvements:

• Improve LocalSolver formulation for optimal binning with a binary target.

Bugfixes:

• Fix MulticlassOptimalBinning when no prebins: #94
• Fix metric_missing and metric_special defined for fitting, but not for predictions or scorecard points: #100

New features:

• Binning process can update binned variables with new optimal binning object using method update_binned_variable.

Improvements:

• Prevent large divisions to avoid overflow issues with int32 during Gini calculation.

Tutorials:

• Tutorial: FICO Explainable Machine Learning Challenge - updating binning