Drop level and weight from the .feature_used_importances_ estimator attribute

The level and weight of the features characterize the analysis process,
not the resulting model itself.

Author: popescu-v

doc/samples/samples_sklearn.rst

@@ -72,7 +72,7 @@ Samples
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
     print("---")
 
     print("Top 5 used features, among those present in the dataset")
@@ -198,7 +198,7 @@ Samples
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
     print("---")
 
     # Predict the classes on the test dataset
@@ -318,7 +318,7 @@ Samples
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
     print("---")
 
     # Predict the class on the test dataset
@@ -549,7 +549,7 @@ Samples
     print(f"Features selected : {khr.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khr.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khr.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khr.feature_used_importances_[i]}")
     print("---")
 
     # Predict the values on the test dataset

khiops/samples/samples_sklearn.ipynb

@@ -58,7 +58,7 @@
     "print(f\"Features selected : {khc.n_features_used_}\")\n",
     "print(\"Top 3 used features\")\n",
     "for i, feature in enumerate(khc.feature_used_names_[:3]):\n",
-    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i][2]}\")\n",
+    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "print(\"Top 5 used features, among those present in the dataset\")\n",
@@ -210,7 +210,7 @@
     "print(f\"Features selected : {khc.n_features_used_}\")\n",
     "print(\"Top 3 used features\")\n",
     "for i, feature in enumerate(khc.feature_used_names_[:3]):\n",
-    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i][2]}\")\n",
+    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the classes on the test dataset\n",
@@ -356,7 +356,7 @@
     "print(f\"Features selected : {khc.n_features_used_}\")\n",
     "print(\"Top 3 used features\")\n",
     "for i, feature in enumerate(khc.feature_used_names_[:3]):\n",
-    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i][2]}\")\n",
+    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the class on the test dataset\n",
@@ -639,7 +639,7 @@
     "print(f\"Features selected : {khr.n_features_used_}\")\n",
     "print(\"Top 3 used features\")\n",
     "for i, feature in enumerate(khr.feature_used_names_[:3]):\n",
-    "    print(f\"{feature} - Importance: {khr.feature_used_importances_[i][2]}\")\n",
+    "    print(f\"{feature} - Importance: {khr.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the values on the test dataset\n",

khiops/samples/samples_sklearn.py

@@ -61,7 +61,7 @@ def khiops_classifier():
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
     print("---")
 
     print("Top 5 used features, among those present in the dataset")
@@ -193,7 +193,7 @@ def khiops_classifier_text():
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
     print("---")
 
     # Predict the classes on the test dataset
@@ -321,7 +321,7 @@ def khiops_classifier_multitable_snowflake():
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
     print("---")
 
     # Predict the class on the test dataset
@@ -560,7 +560,7 @@ def khiops_regressor():
     print(f"Features selected : {khr.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khr.feature_used_names_[:3]):
-        print(f"{feature} - Importance: {khr.feature_used_importances_[i][2]}")
+        print(f"{feature} - Importance: {khr.feature_used_importances_[i]}")
     print("---")
 
     # Predict the values on the test dataset

khiops/sklearn/estimators.py

@@ -1567,9 +1567,7 @@ def _fit_training_post_process(self, ds):
         for feature_name in self.feature_names_in_:
             if feature_name in feature_used_names:
                 feature_index = np.where(feature_used_names == feature_name)
-                feature_importance = self.feature_used_importances_[
-                    feature_index
-                ].ravel()[2]
+                feature_importance = self.feature_used_importances_[feature_index][0]
             else:
                 feature_importance = 0.0
             feature_importances.append(feature_importance)
@@ -1672,10 +1670,7 @@ def get_feature_used_statistics(self, modeling_report):
                 [var.name for var in modeling_report.selected_variables]
             )
             feature_used_importances_ = np.array(
-                [
-                    [var.level, var.weight, var.importance]
-                    for var in modeling_report.selected_variables
-                ]
+                [var.importance for var in modeling_report.selected_variables]
             )
         # Return empty arrays if no selected variables are available
         else:
@@ -1810,20 +1805,10 @@ class KhiopsClassifier(ClassifierMixin, KhiopsPredictor):
         The number of features used by the classifier.
     feature_used_names_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_, )
         Names of the features used by the classifier.
-    feature_used_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_, 3)
-        Level, Weight and Importance of the features used by the classifier:
-
-        - Level: A measure of the predictive importance of the feature taken
-          individually. It ranges between 0 (no predictive interest) and 1 (optimal
-          predictive importance).
-
-        - Weight: A measure of the predictive importance of the feature taken relative
-          to all features selected by the classifier. It ranges between 0 (little
-          contribution to the model) and 1 (large contribution to the model).
-
-        - Importance: Average of the exact Shapley values of each used feature
-          across the training data.
-
+    feature_used_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_,)
+        Importance of the features used by the classifier. The importance is
+        computed as the average of the exact Shapley values of each used feature
+        across the training dataset.
     is_multitable_model_ : bool
         ``True`` if the model was fitted on a multi-table dataset.
     model_ : `.DictionaryDomain`
@@ -2238,20 +2223,10 @@ class KhiopsRegressor(RegressorMixin, KhiopsPredictor):
         The number of features used by the classifier.
     feature_used_names_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_, )
         Names of the features used by the classifier.
-    feature_used_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_, 3)
-        Level, Weight and Importance of the features used by the classifier:
-
-        - Level: A measure of the predictive importance of the feature taken
-          individually. It ranges between 0 (no predictive interest) and 1 (optimal
-          predictive importance).
-
-        - Weight: A measure of the predictive importance of the feature taken relative
-          to all features selected by the classifier. It ranges between 0 (little
-          contribution to the model) and 1 (large contribution to the model).
-
-        - Importance: Average of the exact Shapley values of each used feature
-          across the training data.
-
+    feature_used_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_,)
+        Importance of the features used by the classifier. The importance is
+        computed as the average of the exact Shapley values of each used feature
+        across the training dataset.
     is_multitable_model_ : bool
         ``True`` if the model was fitted on a multi-table dataset.
     model_ : `.DictionaryDomain`

tests/test_estimator_attributes.py

@@ -9,7 +9,6 @@
 import warnings
 from os import path
 
-import numpy as np
 import pandas as pd
 
 from khiops import core as kh
@@ -89,7 +88,7 @@ def assert_attribute_values_ok(self, model, X, y):
                 for var in modeling_report.get_snb_predictor().selected_variables
             ]
             feature_used_importances_report = [
-                [var.level, var.weight, var.importance]
+                var.importance
                 for var in modeling_report.get_snb_predictor().selected_variables
             ]
 
@@ -113,7 +112,7 @@ def assert_attribute_values_ok(self, model, X, y):
                 if feature_name in feature_used_names:
                     feature_index = feature_used_names.index(feature_name)
                     feature_importances_report.append(
-                        feature_used_importances_report[feature_index][2]
+                        feature_used_importances_report[feature_index]
                     )
                 else:
                     feature_importances_report.append(0.0)