added new loss_function and validation_tuning_metric

Author: mathias-von-ottenbreit

API_REFERENCE_FOR_REGRESSION.md

@@ -1,6 +1,6 @@
 # APLRRegressor
 
-## class aplr.APLRRegressor(m:int=1000, v:float=0.1, random_state:int=0, loss_function:str="mse", link_function:str="identity", n_jobs:int=0, validation_ratio:float=0.2, bins:int=300, max_interaction_level:int=1, max_interactions:int=100000, min_observations_in_split:int=20, ineligible_boosting_steps_added:int=10, max_eligible_terms:int=5, verbosity:int=0, dispersion_parameter:float=1.5, validation_tuning_metric:str="default", quantile:float=0.5, calculate_custom_validation_error_function:Optional[Callable[[npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike], float]]=None, calculate_custom_loss_function:Optional[Callable[[npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike], float]]=None, calculate_custom_negative_gradient_function:Optional[Callable[[npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike], npt.ArrayLike]]=None, calculate_custom_transform_linear_predictor_to_predictions_function:Optional[Callable[[npt.ArrayLike], npt.ArrayLike]]=None, calculate_custom_differentiate_predictions_wrt_linear_predictor_function:Optional[Callable[[npt.ArrayLike], npt.ArrayLike]]=None, boosting_steps_before_pruning_is_done: int = 0, boosting_steps_before_interactions_are_allowed: int = 0, monotonic_constraints_ignore_interactions: bool = False)
+## class aplr.APLRRegressor(m:int=1000, v:float=0.1, random_state:int=0, loss_function:str="mse", link_function:str="identity", n_jobs:int=0, validation_ratio:float=0.2, bins:int=300, max_interaction_level:int=1, max_interactions:int=100000, min_observations_in_split:int=20, ineligible_boosting_steps_added:int=10, max_eligible_terms:int=5, verbosity:int=0, dispersion_parameter:float=1.5, validation_tuning_metric:str="default", quantile:float=0.5, calculate_custom_validation_error_function:Optional[Callable[[npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike], float]]=None, calculate_custom_loss_function:Optional[Callable[[npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike], float]]=None, calculate_custom_negative_gradient_function:Optional[Callable[[npt.ArrayLike, npt.ArrayLike, npt.ArrayLike, npt.ArrayLike], npt.ArrayLike]]=None, calculate_custom_transform_linear_predictor_to_predictions_function:Optional[Callable[[npt.ArrayLike], npt.ArrayLike]]=None, calculate_custom_differentiate_predictions_wrt_linear_predictor_function:Optional[Callable[[npt.ArrayLike], npt.ArrayLike]]=None, boosting_steps_before_pruning_is_done: int = 0, boosting_steps_before_interactions_are_allowed: int = 0, monotonic_constraints_ignore_interactions: bool = False, group_mse_cycle_bins: int = 10)
 
 ### Constructor parameters
 
@@ -14,7 +14,7 @@ The learning rate. Must be greater than zero and not more than one. The higher t
 Used to randomly split training observations into training and validation if ***validation_set_indexes*** is not specified when fitting.
 
 #### loss_function (default = "mse")
-Determines the loss function used. Allowed values are "mse", "binomial", "poisson", "gamma", "tweedie", "group_mse", "mae", "quantile", "negative_binomial", "cauchy", "weibull" and "custom_function". This is used together with ***link_function***. When ***loss_function*** is "group_mse" then the "group" argument in the ***fit*** method must be provided. In the latter case APLR will try to minimize group MSE when training the model. The ***loss_function*** "quantile" is used together with the ***quantile*** constructor parameter. When ***loss_function*** is "custom_function" then the constructor parameters ***calculate_custom_loss_function*** and ***calculate_custom_negative_gradient_function***, both described below, must be provided.
+Determines the loss function used. Allowed values are "mse", "binomial", "poisson", "gamma", "tweedie", "group_mse", "group_mse_cycle","mae", "quantile", "negative_binomial", "cauchy", "weibull" and "custom_function". This is used together with ***link_function***. When ***loss_function*** is "group_mse" then the "group" argument in the ***fit*** method must be provided. In the latter case APLR will try to minimize group MSE when training the model. When using "group_mse_cycle", ***group_mse_cycle_bins*** controls the maximum amount of groups. For a description of "group_mse_cycle" see ***group_mse_cycle_bins***. The ***loss_function*** "quantile" is used together with the ***quantile*** constructor parameter. When ***loss_function*** is "custom_function" then the constructor parameters ***calculate_custom_loss_function*** and ***calculate_custom_negative_gradient_function***, both described below, must be provided.
 
 #### link_function (default = "identity")
 Determines how the linear predictor is transformed to predictions. Allowed values are "identity", "logit", "log" and "custom_function". For an ordinary regression model use ***loss_function*** "mse" and ***link_function*** "identity". For logistic regression use ***loss_function*** "binomial" and ***link_function*** "logit". For a multiplicative model use the "log" ***link_function***. The "log" ***link_function*** often works best with a "poisson", "gamma", "tweedie", "negative_binomial" or "weibull" ***loss_function***, depending on the data. The ***loss_function*** "poisson", "gamma", "tweedie", "negative_binomial" or "weibull" should only be used with the "log" ***link_function***. Inappropriate combinations of ***loss_function*** and ***link_function*** may result in a warning message when fitting the model and/or a poor model fit. Please note that values other than "identity" typically require a significantly higher ***m*** (or ***v***) in order to converge. When ***link_function*** is "custom_function" then the constructor parameters ***calculate_custom_transform_linear_predictor_to_predictions_function*** and ***calculate_custom_differentiate_predictions_wrt_linear_predictor_function***, both described below, must be provided.
@@ -50,7 +50,7 @@ Limits 1) the number of terms already in the model that can be considered as int
 Specifies the variance power when ***loss_function*** is "tweedie". Specifies a dispersion parameter when ***loss_function*** is "negative_binomial", "cauchy" or "weibull". 
 
 #### validation_tuning_metric (default = "default")
-Specifies which metric to use for validating the model and tuning ***m***. Available options are "default" (using the same methodology as when calculating the training error), "mse", "mae", "negative_gini", "rankability", "group_mse" and "custom_function". The default is often a choice that fits well with respect to the ***loss_function*** chosen. However, if you want to use ***loss_function*** or ***dispersion_parameter*** as tuning parameters then the default is not suitable. "rankability" uses a methodology similar to the one described in https://towardsdatascience.com/how-to-calculate-roc-auc-score-for-regression-models-c0be4fdf76bb except that the metric is inverted and can be weighted by sample weights. "group_mse" requires that the "group" argument in the ***fit*** method is provided. For "custom_function" see ***calculate_custom_validation_error_function*** below.
+Specifies which metric to use for validating the model and tuning ***m***. Available options are "default" (using the same methodology as when calculating the training error), "mse", "mae", "negative_gini", "rankability", "group_mse", "group_mse_by_prediction" and "custom_function". The default is often a choice that fits well with respect to the ***loss_function*** chosen. However, if you want to use ***loss_function*** or ***dispersion_parameter*** as tuning parameters then the default is not suitable. "rankability" uses a methodology similar to the one described in https://towardsdatascience.com/how-to-calculate-roc-auc-score-for-regression-models-c0be4fdf76bb except that the metric is inverted and can be weighted by sample weights. "group_mse" requires that the "group" argument in the ***fit*** method is provided. "group_mse_by_prediction" groups predictions by up to ***group_mse_cycle_bins*** groups and calculates groupwise mse. For "custom_function" see ***calculate_custom_validation_error_function*** below.
 
 #### quantile (default = 0.5)
 Specifies the quantile to use when ***loss_function*** is "quantile".
@@ -111,6 +111,10 @@ Specifies how many boosting steps to wait before searching for interactions. If
 #### monotonic_constraints_ignore_interactions (default = False)
 See ***monotonic_constraints*** in the ***fit*** method.
 
+#### group_mse_cycle_bins (default = 10)
+When ***loss_function*** equals ***group_mse_cycle*** then ***group_mse_cycle_bins*** specifies the maximum amount of groups. The loss function ***group_mse_cycle*** groups by the first predictor in ***X*** in the first boosting step, then by the second predictor in ***X*** in the second boosting step, etc. So in each boosting step the predictor to group by is changed. If ***validation_tuning_metric*** is "default" then "group_mse_by_prediction" will be used as ***validation_tuning_metric***.
+
+
 ## Method: fit(X:npt.ArrayLike, y:npt.ArrayLike, sample_weight:npt.ArrayLike = np.empty(0), X_names:List[str]=[], validation_set_indexes:List[int]=[], prioritized_predictors_indexes:List[int]=[], monotonic_constraints:List[int]=[], group:npt.ArrayLike = np.empty(0), interaction_constraints:List[List[int]]=[], other_data: npt.ArrayLike = np.empty([0, 0]))
 
 ***This method fits the model to data.***

aplr/aplr.py

@@ -63,6 +63,7 @@ def __init__(
         boosting_steps_before_pruning_is_done: int = 0,
         boosting_steps_before_interactions_are_allowed: int = 0,
         monotonic_constraints_ignore_interactions: bool = False,
+        group_mse_cycle_bins: int = 10,
     ):
         self.m = m
         self.v = v
@@ -103,6 +104,7 @@ def __init__(
         self.monotonic_constraints_ignore_interactions = (
             monotonic_constraints_ignore_interactions
         )
+        self.group_mse_cycle_bins = group_mse_cycle_bins
 
         # Creating aplr_cpp and setting parameters
         self.APLRRegressor = aplr_cpp.APLRRegressor()
@@ -153,6 +155,7 @@ def __set_params_cpp(self):
         self.APLRRegressor.monotonic_constraints_ignore_interactions = (
             self.monotonic_constraints_ignore_interactions
         )
+        self.APLRRegressor.group_mse_cycle_bins = self.group_mse_cycle_bins
 
     def fit(
         self,
@@ -267,6 +270,7 @@ def get_params(self, deep=True):
             "boosting_steps_before_pruning_is_done": self.boosting_steps_before_pruning_is_done,
             "boosting_steps_before_interactions_are_allowed": self.boosting_steps_before_interactions_are_allowed,
             "monotonic_constraints_ignore_interactions": self.monotonic_constraints_ignore_interactions,
+            "group_mse_cycle_bins": self.group_mse_cycle_bins,
         }
 
     # For sklearn