Drop feature_evaluated_* and n_features_evaluated_ from sklearn estimators

Indeed, these characterize the analysis process, not the resulting model
itself.

Author: popescu-v

doc/samples/samples_sklearn.rst

@@ -69,7 +69,6 @@ Samples
     khc.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khc.n_features_evaluated_}")
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
@@ -196,7 +195,6 @@ Samples
     khc.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khc.n_features_evaluated_}")
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
@@ -317,7 +315,6 @@ Samples
     khc.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khc.n_features_evaluated_}")
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
@@ -549,7 +546,6 @@ Samples
     khr.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khr.n_features_evaluated_}")
     print(f"Features selected : {khr.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khr.feature_used_names_[:3]):
@@ -676,13 +672,6 @@ Samples
     khe = KhiopsEncoder(n_features=10)
     khe.fit(X, y)
 
-    # Show the feature importance info
-    print(f"Features evaluated: {khe.n_features_evaluated_}")
-    print("Top 3 evaluated features")
-    for i, feature in enumerate(khe.feature_evaluated_names_[:3]):
-        print(f"{feature} - Level: {khe.feature_evaluated_importances_[i]}")
-    print("---")
-
     # Transform the train dataset
     print("Encoded feature names:")
     print(khe.feature_names_out_)

khiops/samples/samples_sklearn.ipynb

@@ -55,7 +55,6 @@
     "khc.fit(X_train, y_train)\n",
     "\n",
     "# Show the feature importance info\n",
-    "print(f\"Features evaluated: {khc.n_features_evaluated_}\")\n",
     "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",
@@ -208,7 +207,6 @@
     "khc.fit(X_train, y_train)\n",
     "\n",
     "# Show the feature importance info\n",
-    "print(f\"Features evaluated: {khc.n_features_evaluated_}\")\n",
     "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",
@@ -355,7 +353,6 @@
     "khc.fit(X_train, y_train)\n",
     "\n",
     "# Show the feature importance info\n",
-    "print(f\"Features evaluated: {khc.n_features_evaluated_}\")\n",
     "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",
@@ -639,7 +636,6 @@
     "khr.fit(X_train, y_train)\n",
     "\n",
     "# Show the feature importance info\n",
-    "print(f\"Features evaluated: {khr.n_features_evaluated_}\")\n",
     "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",
@@ -805,13 +801,6 @@
     "khe = KhiopsEncoder(n_features=10)\n",
     "khe.fit(X, y)\n",
     "\n",
-    "# Show the feature importance info\n",
-    "print(f\"Features evaluated: {khe.n_features_evaluated_}\")\n",
-    "print(\"Top 3 evaluated features\")\n",
-    "for i, feature in enumerate(khe.feature_evaluated_names_[:3]):\n",
-    "    print(f\"{feature} - Level: {khe.feature_evaluated_importances_[i]}\")\n",
-    "print(\"---\")\n",
-    "\n",
     "# Transform the train dataset\n",
     "print(\"Encoded feature names:\")\n",
     "print(khe.feature_names_out_)\n",

khiops/samples/samples_sklearn.py

@@ -58,7 +58,6 @@ def khiops_classifier():
     khc.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khc.n_features_evaluated_}")
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
@@ -191,7 +190,6 @@ def khiops_classifier_text():
     khc.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khc.n_features_evaluated_}")
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
@@ -320,7 +318,6 @@ def khiops_classifier_multitable_snowflake():
     khc.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khc.n_features_evaluated_}")
     print(f"Features selected : {khc.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khc.feature_used_names_[:3]):
@@ -560,7 +557,6 @@ def khiops_regressor():
     khr.fit(X_train, y_train)
 
     # Show the feature importance info
-    print(f"Features evaluated: {khr.n_features_evaluated_}")
     print(f"Features selected : {khr.n_features_used_}")
     print("Top 3 used features")
     for i, feature in enumerate(khr.feature_used_names_[:3]):
@@ -705,13 +701,6 @@ def khiops_encoder_multitable_snowflake():
     khe = KhiopsEncoder(n_features=10)
     khe.fit(X, y)
 
-    # Show the feature importance info
-    print(f"Features evaluated: {khe.n_features_evaluated_}")
-    print("Top 3 evaluated features")
-    for i, feature in enumerate(khe.feature_evaluated_names_[:3]):
-        print(f"{feature} - Level: {khe.feature_evaluated_importances_[i]}")
-    print("---")
-
     # Transform the train dataset
     print("Encoded feature names:")
     print(khe.feature_names_out_)

khiops/sklearn/estimators.py

@@ -1449,59 +1449,6 @@ def _fit_training_post_process(self, ds):
         if self.model_main_dictionary_name_ is None:
             raise ValueError("No model dictionary after Khiops call")
 
-        # Extract, from the preparation reports, the number of evaluated features,
-        # their names and their levels
-        univariate_preparation_report = self.model_report_.preparation_report
-        if self.model_report_.bivariate_preparation_report is not None:
-            bivariate_preparation_report = (
-                self.model_report_.bivariate_preparation_report
-            )
-            pair_feature_evaluated_names_ = (
-                bivariate_preparation_report.get_variable_pair_names()
-            )
-            pair_feature_evaluated_levels_ = [
-                bivariate_preparation_report.get_variable_pair_statistics(*var).level
-                for var in bivariate_preparation_report.get_variable_pair_names()
-            ]
-        else:
-            pair_feature_evaluated_names_ = []
-            pair_feature_evaluated_levels_ = []
-        if self.model_report_.tree_preparation_report is not None:
-            tree_preparation_report = self.model_report_.tree_preparation_report
-            tree_feature_evaluated_names_ = tree_preparation_report.get_variable_names()
-            tree_feature_evaluated_levels_ = [
-                tree_preparation_report.get_variable_statistics(var).level
-                for var in tree_preparation_report.get_variable_names()
-            ]
-        else:
-            tree_feature_evaluated_names_ = []
-            tree_feature_evaluated_levels_ = []
-
-        feature_evaluated_names_ = (
-            univariate_preparation_report.get_variable_names()
-            + pair_feature_evaluated_names_
-            + tree_feature_evaluated_names_
-        )
-        feature_evaluated_importances_ = np.array(
-            [
-                univariate_preparation_report.get_variable_statistics(var).level
-                for var in univariate_preparation_report.get_variable_names()
-            ]
-            + pair_feature_evaluated_levels_
-            + tree_feature_evaluated_levels_
-        )
-
-        # Sort the features by level
-        combined = list(zip(feature_evaluated_names_, feature_evaluated_importances_))
-        combined.sort(key=lambda x: x[1], reverse=True)
-
-        # Set the sklearn attributes
-        self.feature_evaluated_names_ = np.array(
-            [x[0] for x in combined], dtype=np.dtype("object")
-        )
-        self.feature_evaluated_importances_ = np.array([x[1] for x in combined])
-        self.n_features_evaluated_ = len(combined)
-
     def _transform_check_dataset(self, ds):
         assert isinstance(ds, Dataset), "'ds' is not 'Dataset'"
 
@@ -1859,13 +1806,6 @@ class KhiopsClassifier(ClassifierMixin, KhiopsPredictor):
              - the ``n_pairs`` parameter must be left to its default value, 0;
              - the ``n_text_features`` parameter must be set to 0.
 
-    n_features_evaluated_ : int
-        The number of features evaluated by the classifier.
-    feature_evaluated_names_ : `ndarray <numpy.ndarray>` of shape (n_features_evaluated\_,)
-        Names of the features evaluated by the classifier.
-    feature_evaluated_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_evaluated\_,)
-        Level of the features evaluated by the classifier.
-        See below for a definition of the level.
     n_features_used_ : int
         The number of features used by the classifier.
     feature_used_names_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_, )
@@ -2294,13 +2234,6 @@ class KhiopsRegressor(RegressorMixin, KhiopsPredictor):
              - the ``n_pairs`` parameter must be left to its default value, 0;
              - the ``n_text_features`` parameter must be set to 0.
 
-    n_features_evaluated_ : int
-        The number of features evaluated by the classifier.
-    feature_evaluated_names_ : `ndarray <numpy.ndarray>` of shape (n_features_evaluated\_,)
-        Names of the features evaluated by the classifier.
-    feature_evaluated_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_evaluated\_,)
-        Level of the features evaluated by the classifier.
-        See below for a definition of the level.
     n_features_used_ : int
         The number of features used by the classifier.
     feature_used_names_ : `ndarray <numpy.ndarray>` of shape (n_features_used\_, )
@@ -2561,14 +2494,6 @@ class KhiopsEncoder(TransformerMixin, KhiopsSupervisedEstimator):
 
     Attributes
     ----------
-    n_features_evaluated_ : int
-        The number of features evaluated by the classifier.
-    feature_evaluated_names_ : `ndarray <numpy.ndarray>` of shape (n_features_evaluated\_,)
-        Names of the features evaluated by the classifier.
-    feature_evaluated_importances_ : `ndarray <numpy.ndarray>` of shape (n_features_evaluated\_,)
-        Level of the features evaluated by the classifier. The Level is  measure of the
-        predictive importance of the feature taken individually. It ranges between 0 (no
-        predictive interest) and 1 (optimal predictive importance).
     is_multitable_model_ : bool
         ``True`` if the model was fitted on a multi-table dataset.
     model_ : `.DictionaryDomain`

tests/test_estimator_attributes.py

@@ -79,68 +79,6 @@ def assert_attribute_values_ok(self, model, X, y):
 
         # Extract the features and their levels from the report
         # TODO: Eliminate this as this is the implementation
-        #       Think of a better lighter test: For example verify that the variable are
-        #       in order within the 3 feature lists (simple, pairs and trees).
-        #       Do similarly below with the selected variables.
-        univariate_preparation_report = model.model_report_.preparation_report
-        if model.model_report_.bivariate_preparation_report is not None:
-            bivariate_preparation_report = (
-                model.model_report_.bivariate_preparation_report
-            )
-            pair_feature_evaluated_names_ = (
-                bivariate_preparation_report.get_variable_pair_names()
-            )
-            pair_feature_evaluated_levels_ = [
-                [
-                    bivariate_preparation_report.get_variable_pair_statistics(
-                        var[0], var[1]
-                    ).level
-                ]
-                for var in bivariate_preparation_report.get_variable_pair_names()
-            ]
-        else:
-            pair_feature_evaluated_names_ = []
-            pair_feature_evaluated_levels_ = []
-        if model.model_report_.tree_preparation_report is not None:
-            tree_preparation_report = model.model_report_.tree_preparation_report
-            tree_feature_evaluated_names_ = tree_preparation_report.get_variable_names()
-            tree_feature_evaluated_levels_ = [
-                [tree_preparation_report.get_variable_statistics(var).level]
-                for var in tree_preparation_report.get_variable_names()
-            ]
-        else:
-            tree_feature_evaluated_names_ = []
-            tree_feature_evaluated_levels_ = []
-
-        feature_evaluated_names_report_ = (
-            univariate_preparation_report.get_variable_names()
-            + pair_feature_evaluated_names_
-            + tree_feature_evaluated_names_
-        )
-        feature_evaluated_importances_report = np.array(
-            [
-                [univariate_preparation_report.get_variable_statistics(var).level]
-                for var in univariate_preparation_report.get_variable_names()
-            ]
-            + pair_feature_evaluated_levels_
-            + tree_feature_evaluated_levels_
-        )
-
-        # Sort the features by level
-        combined = list(
-            zip(feature_evaluated_names_report_, feature_evaluated_importances_report)
-        )
-        combined.sort(key=lambda x: x[1], reverse=True)
-        feature_names = list(x[0] for x in combined)
-        feature_levels = list(x[1] for x in combined)
-
-        # Check that the features and their levels were extracted in order
-        self.assertEqual(
-            model.n_features_evaluated_, len(feature_evaluated_names_report_)
-        )
-        self.assertEqual(model.feature_evaluated_names_.tolist(), list(feature_names))
-        self.assertEqual(model.feature_evaluated_importances_.tolist(), feature_levels)
-
         modeling_report = model.model_report_.modeling_report
         # Check the selected variables for the regressor and classifier
         if not isinstance(model, KhiopsEncoder):