Add new sklearn attributes to supervised estimators (#190)

Author: nairbenrekia

CHANGELOG.md

@@ -6,6 +6,11 @@
   - Example: 10.2.1.4 is the 5th version that supports khiops 10.2.1.
 - Internals: Changes in *Internals* sections are unlikely to be of interest for data scientists.
 
+## 10.2.2.4 - 2024-08-05
+
+## Added
+- (`sklearn`) Sklearn's attributes for supervised estimators.
+
 ## 10.2.2.3 - 2024-08-02
 
 ### Fixed

doc/samples/samples_sklearn.rst

@@ -68,6 +68,14 @@ Samples
     # Train the 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]):
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+    print("---")
+
     # Predict the classes on the test dataset
     y_test_pred = khc.predict(X_test)
     print("Predicted classes (first 10):")
@@ -273,6 +281,14 @@ Samples
     khc = KhiopsClassifier(n_trees=0)
     khc.fit(X, y)
 
+    # 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]):
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+    print("---")
+
     # Predict the class on the test dataset
     y_pred = khc.predict(X)
     print("Predicted classes (first 10):")
@@ -420,6 +436,14 @@ Samples
     # Train the 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]):
+        print(f"{feature} - Importance: {khr.feature_used_importances_[i][2]}")
+    print("---")
+
     # Predict the values on the test dataset
     y_test_pred = khr.predict(X_test)
     print("Predicted values for 'age' (first 10):")
@@ -561,6 +585,13 @@ 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][0]}")
+    print("---")
+
     # Transform the train dataset
     print("Encoded feature names:")
     print(khe.feature_names_out_)

khiops/samples/samples_sklearn.ipynb

@@ -54,6 +54,14 @@
     "# Train the classifier\n",
     "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",
+    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i][2]}\")\n",
+    "print(\"---\")\n",
+    "\n",
     "# Predict the classes on the test dataset\n",
     "y_test_pred = khc.predict(X_test)\n",
     "print(\"Predicted classes (first 10):\")\n",
@@ -298,6 +306,14 @@
     "khc = KhiopsClassifier(n_trees=0)\n",
     "khc.fit(X, y)\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",
+    "    print(f\"{feature} - Importance: {khc.feature_used_importances_[i][2]}\")\n",
+    "print(\"---\")\n",
+    "\n",
     "# Predict the class on the test dataset\n",
     "y_pred = khc.predict(X)\n",
     "print(\"Predicted classes (first 10):\")\n",
@@ -484,6 +500,14 @@
     "# Train the regressor\n",
     "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",
+    "    print(f\"{feature} - Importance: {khr.feature_used_importances_[i][2]}\")\n",
+    "print(\"---\")\n",
+    "\n",
     "# Predict the values on the test dataset\n",
     "y_test_pred = khr.predict(X_test)\n",
     "print(\"Predicted values for 'age' (first 10):\")\n",
@@ -664,6 +688,13 @@
     "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][0]}\")\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

@@ -57,6 +57,14 @@ def khiops_classifier():
     # Train the 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]):
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+    print("---")
+
     # Predict the classes on the test dataset
     y_test_pred = khc.predict(X_test)
     print("Predicted classes (first 10):")
@@ -273,6 +281,14 @@ def khiops_classifier_multitable_snowflake():
     khc = KhiopsClassifier(n_trees=0)
     khc.fit(X, y)
 
+    # 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]):
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+    print("---")
+
     # Predict the class on the test dataset
     y_pred = khc.predict(X)
     print("Predicted classes (first 10):")
@@ -423,6 +439,14 @@ def khiops_regressor():
     # Train the 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]):
+        print(f"{feature} - Importance: {khr.feature_used_importances_[i][2]}")
+    print("---")
+
     # Predict the values on the test dataset
     y_test_pred = khr.predict(X_test)
     print("Predicted values for 'age' (first 10):")
@@ -581,6 +605,13 @@ 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][0]}")
+    print("---")
+
     # Transform the train dataset
     print("Encoded feature names:")
     print(khe.feature_names_out_)