add cat_penalty develop parameter

interpretml · Jan 3, 2025 · ccd5db5 · ccd5db5
1 parent e3aa1b2
commit ccd5db5
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/python/interpret-core/interpret/develop.py b/python/interpret-core/interpret/develop.py
@@ -21,6 +21,7 @@
     "cat_smooth": math.inf,  # math.inf means use only the gradient for sorting
     "max_cat_threshold": 9223372036854775807,
     "cat_include": 0.75,
+    "cat_penalty": 0.0,
     "purify_boosting": False,
     "purify_result": False,
     "randomize_initial_feature_order": True,

diff --git a/python/interpret-core/interpret/glassbox/_ebm/_boost.py b/python/interpret-core/interpret/glassbox/_ebm/_boost.py
@@ -199,6 +199,11 @@ def boost(
                         max_leaves=max_leaves,
                         monotone_constraints=term_monotone,
                     )
+
+                    if contains_nominals and len(term_features[term_idx]) == 1:
+                        # penalize nominals a bit because they benefit from sorting categories
+                        avg_gain *= 1.0 - develop.get_option("cat_penalty")
+
                     gainkey = (-avg_gain, native.generate_seed(rng), term_idx)
                     if not make_progress:
                         if bestkey is None or gainkey < bestkey: