default value and documentation

Author: mathias-von-ottenbreit

API_REFERENCE_FOR_CLASSIFICATION.md

@@ -1,14 +1,14 @@
 # APLRClassifier
 
-## class aplr.APLRClassifier(m:int=3000, v:float=0.3, 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)
+## 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)
 
 ### Constructor parameters
 
 #### m (default = 3000)
 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 = 0.3)
-The learning rate. Must be greater than zero and not more than one. The higher the faster the algorithm learns and the lower ***m*** is required. If the algorithm learns too fast (requires few boosting steps to converge) then try lowering the learning rate. Computational costs can be reduced by increasing the learning rate while simultaneously decreasing ***m***, potentially at the expense of predictiveness.
+#### v (default = 0.1)
+The learning rate. Must be greater than zero and not more than one. The higher the faster the algorithm learns and the lower ***m*** is required. However, empirical evidence suggests that ***v <= 0.1*** gives better results. If the algorithm learns too fast (requires few boosting steps to converge) then try lowering the learning rate. Computational costs can be reduced by increasing the learning rate while simultaneously decreasing ***m***, potentially at the expense of predictiveness.
 
 #### random_state (default = 0)
 Used to randomly split training observations into cv_folds if ***cv_observations*** is not specified when fitting.

aplr/aplr.py

@@ -300,7 +300,7 @@ class APLRClassifier:
     def __init__(
         self,
         m: int = 3000,
-        v: float = 0.3,
+        v: float = 0.1,
         random_state: int = 0,
         n_jobs: int = 0,
         cv_folds: int = 5,

cpp/APLRClassifier.h

@@ -46,7 +46,7 @@ class APLRClassifier
     bool monotonic_constraints_ignore_interactions;
     size_t early_stopping_rounds;
 
-    APLRClassifier(size_t m = 3000, double v = 0.3, uint_fast32_t random_state = std::numeric_limits<uint_fast32_t>::lowest(), size_t n_jobs = 0,
+    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,
                    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/pythonbinding.cpp

@@ -233,7 +233,7 @@ 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 &>(),
-             py::arg("m") = 3000, py::arg("v") = 0.3, py::arg("random_state") = 0, py::arg("n_jobs") = 0, py::arg("cv_folds") = 5,
+             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("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 9.3.0.pdf

@@ -45,7 +45,7 @@
 best_model = None
 for params in param_grid:
     model = APLRClassifier(
-        random_state=random_state, verbosity=2, m=1000, v=0.3, **params
+        random_state=random_state, verbosity=2, m=3000, v=0.1, **params
     )
     model.fit(
         data_train[predictors].values, data_train[response].values, X_names=predictors

documentation/APLR 9.4.0.pdf

@@ -21,7 +21,7 @@
 
 setuptools.setup(
     name="aplr",
-    version="9.3.0",
+    version="9.4.0",
     description="Automatic Piecewise Linear Regression",
     ext_modules=[sfc_module],
     author="Mathias von Ottenbreit",