docs

Author: mathias-von-ottenbreit

API_REFERENCE_FOR_CLASSIFICATION.md

@@ -26,7 +26,7 @@ Specifies the maximum number of bins to discretize the data into when searching
 ***0*** does not print progress reports during fitting. ***1*** prints a summary after running the ***fit*** method. ***2*** prints a summary after each boosting step.
 
 #### max_interaction_level (default = 1)
-Specifies the maximum allowed depth of interaction terms. ***0*** means that interactions are not allowed. This hyperparameter should be tuned.
+Specifies the maximum allowed depth of interaction terms. ***0*** means that interactions are not allowed. This hyperparameter should be tuned by for example doing a grid search for best predictiveness. For best interpretability use 0 (or 1 if interactions are needed).
 
 #### max_interactions (default = 100000)
 The maximum number of interactions allowed in each underlying model. A lower value may be used to reduce computational time.

API_REFERENCE_FOR_REGRESSION.md

@@ -29,7 +29,7 @@ The number of randomly split folds to use in cross validation. The number of boo
 Specifies the maximum number of bins to discretize the data into when searching for the best split. The default value works well according to empirical results. This hyperparameter is intended for reducing computational costs. Must be greater than 1.
 
 #### max_interaction_level (default = 1)
-Specifies the maximum allowed depth of interaction terms. ***0*** means that interactions are not allowed. This hyperparameter should be tuned.
+Specifies the maximum allowed depth of interaction terms. ***0*** means that interactions are not allowed. This hyperparameter should be tuned by for example doing a grid search for best predictiveness. For best interpretability use 0 (or 1 if interactions are needed).
 
 #### max_interactions (default = 100000)
 The maximum number of interactions allowed in each underlying model. A lower value may be used to reduce computational time.

documentation/APLR 10.0.0.pdf renamed to documentation/APLR 10.1.0.pdf

@@ -38,7 +38,7 @@
 best_validation_result = np.inf
 param_grid = ParameterGrid(
     {
-        "max_interaction_level": [0, 1, 2, 3, 100],
+        "max_interaction_level": [0, 1],
         "min_observations_in_split": [1, 20, 40],
     }
 )

examples/train_aplr_classification.py

@@ -35,7 +35,7 @@
 best_validation_result = np.inf
 param_grid = ParameterGrid(
     {
-        "max_interaction_level": [0, 1, 2, 3, 100],
+        "max_interaction_level": [0, 1],
         "min_observations_in_split": [1, 20, 50, 100, 200],
     }
 )