0.10.4

• Changed to Cython implementation for the loss functions and impurity measures of CSLogitClassifier, CSBoostClassifier, CSTreeClassifier, and CSForestClassifier. This improves the training time and memory efficiency of these models significantly. Training time speedups observed were up to 300x for CSTreeClassifier and CSForestClassifier, 30x for CSLogitClassifier, and 1.5x for CSBoostClassifier depending on the dataset size and parameters.
• Changed arguments to CSTreeClassifier, CSForestClassifier, and CSBaggingClassifier to be in line with scikit-learn's decision tree and ensemble models.
• CSForestClassifier, and CSBaggingClassifier no longer support stacking combination method. Use StackingClassifier instead for stacking.
• Extracted the construction of the cost matrix into a separate class CostMatrix away from Metric to allow reusing the cost matrix in custom metrics.
• ProfLogitClassifier no longer uses the EMPC metric by default. Users now need to explicitely pass a loss to the model.
• CSLogitClassifier no longer accepts any callable as loss function. Users now need to pass a Metric instance for a custom loss function.
• savings_score and expected_savings_score now accept two more baseline options 'one' and 'zero' to always predict the positive and negative class, respectively.
• Metrics with with the Savings strategy now also accepts baseline options like savings_score and expected_savings_score.
• Models which use a Metric instance as their loss function with the Cost or Savings strategy as their loss function now are pickleable. The MaxProfit strategy will be updated to be pickleable in a future release.
• Models which use a Metric instance as their loss function can now request arguments necessary for the metric to be passed during the fit method through Metadata Routing.
• Fix CSLogitClassifier not properly calculating gradient penalty.
• Fix default values not being properly when using aliases in CostMatrix.
• Fix Metric throwing errors when certain terms cancelled out.

0.10.3

• Fix build issue on Windows.

0.9.0

• Added optimal_threshold and optimal_rate methods to calculate the optimal threshold(s) and optimal predicted positive rate for a given metric. This is useful for determining the best decision threshold and predicted positive rate for a cost-sensitive or value-driven model.

• CSTreeClassifier, CSForestClassifier, andCSBaggingClassifier can now take a Metric instance as their criterion to optimize.

• CSThresholdClassifier can now take a Metric instance to choose the optimal decision threshold.

• RobustCSClassifier can now take estimators with aMetric instance as the loss function or criterion.RobustCSClassifier will treat any cost marked as outlier sensitive. This can be done by using the mark_outlier_sensitive method.

• Allow savings metrics to be used in CSBoostClassifier andCSLogitClassifier as the objective function. Internally, the expected cost loss is used to train the model, since the expected savings score is just a transformation of the expected cost loss.

• kind argument to Metric has been replaced by strategy. The Metric class now takes a MetricStrategy instance. This change allows for more flexibility in defining the metric strategy.
  The currently available strategies are:

  • MaxProfit for the expected maximum profit score
  • Cost for the expected cost loss
  • Savings for the expected savings score

• Fix error when importing Empulse without any optional dependencies installed.

• Fix CSLogitClassifier not properly using the gradient when using a custom loss function from Metric.

• Fix models throwing errors when differently shaped costs are passed to the fit or predict method.

• Fix sympy distribution parameters not being properly translated to scipy distribution parameters when using the MaxProfit strategy (formerly kind='max profit') with the quasi monte-carlo integration method.

0.8.0

• CSBoostClassifier, CSLogitClassifier, and ProfLogitClassifier can now take a Metric instance as their loss function.
  Internally, the metric instance is converted to the appropriate loss function for the model.
  For more information, read the User Guide.
• Type hints are now available for all functions and classes.
• Add support for more than one stochastic variable when building maximum profit metrics with Metric
• Allow Metric to be used as a context manager.
  This ensures the metric is always built after defining the cost-benefit elements.
• Fix datasets not properly being packaged together with the package
• Fix RobustCSClassifier when array-like parameters are passed to fit method.
• Fix boosting models being biased towards the positive class.

Full Changelog: 0.7.0...0.8.0

0.7.0

• Add CSTreeClassifier, CSForestClassifier,
  and CSBaggingClassifier to support cost-sensitive decision tree and ensemble models
• Add support for scikit-learn 1.5.2 (previously Empulse only supported scikit-learn 1.6.0 and above).
• Removed the emp_score and emp functions from the metrics module.
  Use the Metric class instead to define custom expected maximum profit measures.
  For more information, read the User Guide.
• Removed numba as a dependency for Empulse. This will reduce the installation time and the size of the package.
• Fix Metric when defining stochastic variable with fixed values.
• Fix Metric when stochastic variable has infinite bounds.
• Fix CSThresholdClassifier
  when costs of predicting positive and negative classes are equal.
• Fix documentation linking issues to sklearn

Full Changelog: 0.6.0...0.7.0

0.6.0

• Add Metric to easily build your own value-driven and cost-sensitive metrics

• Add support for LightGBM and Catboost models in CSBoostClassifier and
  B2BoostClassifier

• make_objective_churn and make_objective_acquisition
  now take a model argument to calculate the objective for either XGBoost, LightGBM or Catboost models.

• XGBoost is now an optional dependency together with LightGBM and Catboost. To install the package with
  XGBoost, LightGBM and Catboost support, use the following command: pip install empulse[optional]

• Renamed y_pred_baseline and y_proba_baseline to baseline in savings_score
  and expected_savings_score. It now accepts the following arguments:

  • If 'zero_one', the baseline model is a naive model that predicts all zeros or all ones
    depending on which is better.
  • If 'prior', the baseline model is a model that predicts the prior probability of
    the majority or minority class depending on which is better (not available for savings score).
  • If array-like, target probabilities of the baseline model.

• Add parameter validation for all models and samplers

• Make all arguments of dataset loaders keyword-only

• Update the descriptions attached to each dataset to match information found in the user guide

• Improve type hints for functions and classes

Full Changelog: 0.5.2...0.6.0

0.5.2

• Allow savings_score and expected_savings_score
  to calculate the savings score over the baseline model instead of a naive model,
  by setting the y_pred_baseline and y_proba_baseline parameters, respectively.
• Reworked the user guide documentation to better explain the usage of value-driven
  and cost-sensitive models, samplers and metrics
• CSLogitClassifier and ProfLogitClassifier
  by default do not perform soft-thresholding on the regression coefficients.
  This can be enabled by setting the soft_threshold parameter to True.
• Prevent division by zero errors in expected_cost_loss

Full Changelog: 0.5.1...0.5.2

0.5.1

• Fix documentation build issue

Full Changelog: 0.5.0...0.5.1

0.5.0

• Added supported for python 3.13
• Added cost-sensitive models
  • CSLogitClassifier
  • CSBoostClassifier
  • RobustCSClassifier
  • CSThresholdClassifier
• Added cost-sensitive metrics
  • cost_loss
  • expected_cost_loss
  • expected_log_cost_loss
  • savings_score
  • expected_savings_score
• Added cost-sensitive sampler
  • CostSensitiveSampler
• Added datasets module
• rename metric arguments which expect target score from y_pred to y_score and
  target probabilities from y_pred to y_proba.
• Allow all cost-sensitive models and samplers to accept cost parameters during initialization

Full Changelog: 0.4.6...0.5.0

0.4.6

Full Changelog: 0.4.0...0.4.6