10.5.0

Author: mathias-von-ottenbreit

API_REFERENCE_FOR_CLASSIFICATION.md

@@ -1,10 +1,10 @@
 # APLRClassifier
 
-## class aplr.APLRClassifier(m:int = 3000, v:float = 0.1, random_state:int = 0, n_jobs:int = 0, cv_folds:int = 5, bins:int = 300, verbosity:int = 0, 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, boosting_steps_before_interactions_are_allowed: int = 0, monotonic_constraints_ignore_interactions: bool = False, early_stopping_rounds: int = 500, num_first_steps_with_linear_effects_only: int = 0, penalty_for_non_linearity: float = 0.0, penalty_for_interactions: float = 0.0, max_terms: int = 0)
+## class aplr.APLRClassifier(m:int = 20000, v:float = 0.1, random_state:int = 0, n_jobs:int = 0, cv_folds:int = 5, bins:int = 300, verbosity:int = 0, 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, boosting_steps_before_interactions_are_allowed: int = 0, monotonic_constraints_ignore_interactions: bool = False, early_stopping_rounds: int = 500, num_first_steps_with_linear_effects_only: int = 0, penalty_for_non_linearity: float = 0.0, penalty_for_interactions: float = 0.0, max_terms: int = 0)
 
 ### Constructor parameters
 
-#### m (default = 3000)
+#### m (default = 20000)
 The maximum number of boosting steps. If validation error does not flatten out at the end of the ***m***th boosting step, then try increasing it (or alternatively increase the learning rate).
 
 #### v (default = 0.1)

API_REFERENCE_FOR_REGRESSION.md

@@ -1,10 +1,10 @@
 # APLRRegressor
 
-## class aplr.APLRRegressor(m:int = 3000, v:float = 0.1, random_state:int = 0, loss_function:str = "mse", link_function:str = "identity", n_jobs:int = 0, cv_folds:int = 5, 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[[FloatVector, FloatVector, FloatVector, FloatVector, FloatMatrix], float]] = None, calculate_custom_loss_function:Optional[Callable[[FloatVector, FloatVector, FloatVector, FloatVector, FloatMatrix], float]] = None, calculate_custom_negative_gradient_function:Optional[Callable[[FloatVector, FloatVector, FloatVector, FloatMatrix],FloatVector]] = None, calculate_custom_transform_linear_predictor_to_predictions_function:Optional[Callable[[FloatVector], FloatVector]] = None, calculate_custom_differentiate_predictions_wrt_linear_predictor_function:Optional[Callable[[FloatVector], FloatVector]] = None, boosting_steps_before_interactions_are_allowed:int = 0, monotonic_constraints_ignore_interactions:bool = False, group_mse_by_prediction_bins:int = 10, group_mse_cycle_min_obs_in_bin:int = 30, early_stopping_rounds:int = 500, num_first_steps_with_linear_effects_only:int = 0, penalty_for_non_linearity:float = 0.0, penalty_for_interactions:float = 0.0, max_terms:int = 0)
+## class aplr.APLRRegressor(m:int = 20000, v:float = 0.1, random_state:int = 0, loss_function:str = "mse", link_function:str = "identity", n_jobs:int = 0, cv_folds:int = 5, 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[[FloatVector, FloatVector, FloatVector, FloatVector, FloatMatrix], float]] = None, calculate_custom_loss_function:Optional[Callable[[FloatVector, FloatVector, FloatVector, FloatVector, FloatMatrix], float]] = None, calculate_custom_negative_gradient_function:Optional[Callable[[FloatVector, FloatVector, FloatVector, FloatMatrix],FloatVector]] = None, calculate_custom_transform_linear_predictor_to_predictions_function:Optional[Callable[[FloatVector], FloatVector]] = None, calculate_custom_differentiate_predictions_wrt_linear_predictor_function:Optional[Callable[[FloatVector], FloatVector]] = None, boosting_steps_before_interactions_are_allowed:int = 0, monotonic_constraints_ignore_interactions:bool = False, group_mse_by_prediction_bins:int = 10, group_mse_cycle_min_obs_in_bin:int = 30, early_stopping_rounds:int = 500, num_first_steps_with_linear_effects_only:int = 0, penalty_for_non_linearity:float = 0.0, penalty_for_interactions:float = 0.0, max_terms:int = 0)
 
 ### Constructor parameters
 
-#### m (default = 3000)
+#### m (default = 20000)
 The maximum number of boosting steps. If validation error does not flatten out at the end of the ***m***th boosting step, then try increasing it (or alternatively increase the learning rate).
 
 #### v (default = 0.1)

aplr/aplr.py

@@ -11,7 +11,7 @@
 class APLRRegressor:
     def __init__(
         self,
-        m: int = 3000,
+        m: int = 20000,
         v: float = 0.1,
         random_state: int = 0,
         loss_function: str = "mse",
@@ -350,7 +350,7 @@ def set_params(self, **parameters):
 class APLRClassifier:
     def __init__(
         self,
-        m: int = 3000,
+        m: int = 20000,
         v: float = 0.1,
         random_state: int = 0,
         n_jobs: int = 0,
@@ -458,6 +458,8 @@ def fit(
             predictor_penalties_for_non_linearity,
             predictor_penalties_for_interactions,
         )
+        # For sklearn
+        self.classes_ = np.arange(len(self.APLRClassifier.get_categories()))
 
     def predict_class_probabilities(
         self, X: FloatMatrix, cap_predictions_to_minmax_in_training: bool = False
@@ -525,3 +527,7 @@ def set_params(self, **parameters):
             setattr(self, parameter, value)
         self.__set_params_cpp()
         return self
+
+    # For sklearn
+    def predict_proba(self, X: FloatMatrix) -> FloatMatrix:
+        return self.predict_class_probabilities(X)

cpp/APLRClassifier.h

@@ -54,7 +54,7 @@ class APLRClassifier
     std::map<std::string, size_t> unique_term_affiliation_map;
     std::vector<std::vector<size_t>> base_predictors_in_each_unique_term_affiliation;
 
-    APLRClassifier(size_t m = 3000, double v = 0.1, uint_fast32_t random_state = std::numeric_limits<uint_fast32_t>::lowest(), size_t n_jobs = 0,
+    APLRClassifier(size_t m = 20000, double v = 0.1, uint_fast32_t random_state = std::numeric_limits<uint_fast32_t>::lowest(), size_t n_jobs = 0,
                    size_t cv_folds = 5, size_t reserved_terms_times_num_x = 100, size_t bins = 300, size_t verbosity = 0, size_t max_interaction_level = 1,
                    size_t max_interactions = 100000, size_t min_observations_in_split = 20, size_t ineligible_boosting_steps_added = 10, size_t max_eligible_terms = 5,
                    size_t boosting_steps_before_interactions_are_allowed = 0, bool monotonic_constraints_ignore_interactions = false,

cpp/APLRRegressor.h

@@ -248,7 +248,7 @@ class APLRRegressor
     VectorXd min_predictor_values_in_training;
     VectorXd max_predictor_values_in_training;
 
-    APLRRegressor(size_t m = 3000, double v = 0.1, uint_fast32_t random_state = std::numeric_limits<uint_fast32_t>::lowest(), std::string loss_function = "mse",
+    APLRRegressor(size_t m = 20000, double v = 0.1, uint_fast32_t random_state = std::numeric_limits<uint_fast32_t>::lowest(), std::string loss_function = "mse",
                   std::string link_function = "identity", size_t n_jobs = 0, size_t cv_folds = 5,
                   size_t reserved_terms_times_num_x = 100, size_t bins = 300, size_t verbosity = 0, size_t max_interaction_level = 1, size_t max_interactions = 100000,
                   size_t min_observations_in_split = 20, size_t ineligible_boosting_steps_added = 10, size_t max_eligible_terms = 5, double dispersion_parameter = 1.5,

cpp/pythonbinding.cpp

@@ -26,7 +26,7 @@ PYBIND11_MODULE(aplr_cpp, m)
                       std::function<VectorXd(const VectorXd &y, const VectorXd &predictions, const VectorXi &group, const MatrixXd &other_data)> &,
                       std::function<VectorXd(const VectorXd &linear_predictor)> &, std::function<VectorXd(const VectorXd &linear_predictor)> &,
                       int &, bool &, int &, int &, int &, int &, double &, double &, int &>(),
-             py::arg("m") = 3000, py::arg("v") = 0.1, py::arg("random_state") = 0, py::arg("loss_function") = "mse", py::arg("link_function") = "identity",
+             py::arg("m") = 20000, py::arg("v") = 0.1, py::arg("random_state") = 0, py::arg("loss_function") = "mse", py::arg("link_function") = "identity",
              py::arg("n_jobs") = 0, py::arg("cv_folds") = 5,
              py::arg("reserved_terms_times_num_x") = 100, py::arg("bins") = 300, py::arg("verbosity") = 0,
              py::arg("max_interaction_level") = 1, py::arg("max_interactions") = 100000, py::arg("min_observations_in_split") = 20,
@@ -284,7 +284,7 @@ PYBIND11_MODULE(aplr_cpp, m)
     py::class_<APLRClassifier>(m, "APLRClassifier", py::module_local())
         .def(py::init<int &, double &, int &, int &, int &, int &, int &, int &, int &, int &, int &, int &, int &, int &, bool &, int &, int &,
                       double &, double &, int &>(),
-             py::arg("m") = 3000, py::arg("v") = 0.1, py::arg("random_state") = 0, py::arg("n_jobs") = 0, py::arg("cv_folds") = 5,
+             py::arg("m") = 20000, py::arg("v") = 0.1, py::arg("random_state") = 0, py::arg("n_jobs") = 0, py::arg("cv_folds") = 5,
              py::arg("reserved_terms_times_num_x") = 100, py::arg("bins") = 300, py::arg("verbosity") = 0,
              py::arg("max_interaction_level") = 1, py::arg("max_interactions") = 100000, py::arg("min_observations_in_split") = 20,
              py::arg("ineligible_boosting_steps_added") = 10, py::arg("max_eligible_terms") = 5,

documentation/APLR 10.4.6.pdf renamed to documentation/APLR 10.5.0.pdf

@@ -47,7 +47,7 @@
     model = APLRClassifier(
         random_state=random_state,
         verbosity=2,
-        m=3000,
+        m=20000,
         v=0.1,
         # max_terms=5,  # Optionally tune this to find a trade-off between interpretability and predictiveness. May require a higher learning rate for best results.
         **params

examples/train_aplr_classification.py

@@ -50,7 +50,7 @@
     model = APLRRegressor(
         random_state=random_state,
         verbosity=2,
-        m=3000,
+        m=20000,
         v=0.1,
         loss_function=loss_function,
         link_function=link_function,

examples/train_aplr_regression.py

@@ -27,7 +27,7 @@
 
 setuptools.setup(
     name="aplr",
-    version="10.4.6",
+    version="10.5.0",
     description="Automatic Piecewise Linear Regression",
     ext_modules=[sfc_module],
     author="Mathias von Ottenbreit",