Add sklearn estimators feature_importances_ attribute

CHANGELOG.md

@@ -13,7 +13,13 @@
   comments, and dictionary and variable block internal comments.
 - (`core`) Dictionary `Rule` class and supporting API for serializing `Rule` instances.
 - (`core`) New way to add a variable to a dictionary using a complete specification.
+- (`core`) New API constants for rules used in automatic variable construction:
+  - `DEFAULT_CONSTRUCTION_RULES`: names of table and entity construction rules,
+    which are applied by default
+  - `CALENDRICAL_CONSTRUCTION_RULES`: names of date, time and timestamp rules.
 - (`sklearn`) `Text` Khiops type support at the estimator level.
+- (`sklearn`) The `feature_names_in_` and `feature_importances_` Khiops
+  classifier and regressor estimator attributes.
 
 ### Changed
 - (`core`) Dictionary API (DictionaryDomain, Dictionary, MetaData), 

doc/samples/samples_sklearn.rst

@@ -69,11 +69,19 @@ 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]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+    print("Top 5 used features")
+    for i, feature in enumerate(khc.feature_used_names_[:5]):
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
+    print("---")
+
+    print("Top 5 used features, among those present in the dataset")
+    for feature, importance in sorted(
+        zip(khc.feature_names_in_, khc.feature_importances_),
+        key=lambda imp: imp[1],
+        reverse=True,
+    )[:5]:
+        print(f"{feature} - Importance: {importance}")
     print("---")
 
     # Predict the classes on the test dataset
@@ -187,11 +195,10 @@ 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]):
-        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
@@ -308,11 +315,10 @@ 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]):
-        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
@@ -540,11 +546,10 @@ 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]):
-        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
@@ -667,13 +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/core/api.py

@@ -31,18 +31,10 @@
 from khiops.core.internals.runner import get_runner
 from khiops.core.internals.task import get_task_registry
 
-# List of all available construction rules in the Khiops tool
-all_construction_rules = [
-    "Day",
-    "DecimalTime",
-    "DecimalWeekDay",
-    "DecimalYear",
-    "DecimalYearTS",
-    "GetDate",
-    "GetTime",
+# Construction rules
+DEFAULT_CONSTRUCTION_RULES = [
     "GetValue",
     "GetValueC",
-    "LocalTimestamp",
     "TableCount",
     "TableCountDistinct",
     "TableMax",
@@ -53,9 +45,37 @@
     "TableSelection",
     "TableStdDev",
     "TableSum",
+]
+"""List of construction rules that Khiops uses by default
+
+.. note::
+    These are all the multi-table rules.
+"""  # pylint: disable=pointless-string-statement
+
+CALENDRICAL_CONSTRUCTION_RULES = [
+    "Day",
+    "DecimalTime",
+    "DecimalWeekDay",
+    "DecimalYear",
+    "DecimalYearTS",
+    "GetDate",
+    "GetTime",
+    "LocalTimestamp",
     "WeekDay",
     "YearDay",
 ]
+"""List of calendrical construction rules
+
+These rules include: date, time and timestamp rules.
+
+.. note::
+    These rules are not enabled by default. The user needs to explicitly
+    select each of them via the ``construction_rules`` parameter of the
+    relevant Core API functions.
+"""  # pylint: disable=pointless-string-statement
+
+# List of all available construction rules in the Khiops tool
+ALL_CONSTRUCTION_RULES = DEFAULT_CONSTRUCTION_RULES + CALENDRICAL_CONSTRUCTION_RULES
 
 ##########################
 # Private module methods #
@@ -758,8 +778,9 @@ def train_predictor(
     max_constructed_variables : int, default 1000
         Maximum number of variables to construct.
     construction_rules : list of str, optional
-        Allowed rules for the automatic variable construction. If not set it uses all
-        possible rules.
+        Allowed rules for the automatic variable construction. If not set, Khiops
+        uses the multi-table construction rules listed in
+        `DEFAULT_CONSTRUCTION_RULES`.
     max_text_features : int, default 10000
         Maximum number of text features to construct.
     text_features : str, default "words"
@@ -1190,21 +1211,22 @@ def train_recoder(
     max_constructed_variables : int, default 100
         Maximum number of variables to construct.
     construction_rules : list of str, optional
-        Allowed rules for the automatic variable construction. If not set it uses all
-        possible rules.
+        Allowed rules for the automatic variable construction. If not set, Khiops
+        uses the multi-table construction rules listed in
+        `DEFAULT_CONSTRUCTION_RULES`.
     max_text_features : int, default 10000
         Maximum number of text features to construct.
     text_features : str, default "words"
         Type of the text features. Can be either one of:
 
-        - "words": sequences of non-space characters
-        - "ngrams": sequences of bytes
-        - "tokens": user-defined
+            - "words": sequences of non-space characters
+            - "ngrams": sequences of bytes
+            - "tokens": user-defined
 
     max_trees : int, default 10
         Maximum number of trees to construct.
     max_pairs : int, default 0
-        Maximum number of variables pairs to construct.
+        Maximum number of variable pairs to construct.
     specific_pairs : list of tuple, optional
         User-specified pairs as a list of 2-tuples of feature names. If a given tuple
         contains only one non-empty feature name, then it generates all the pairs

khiops/core/dictionary.py

@@ -733,7 +733,7 @@ def get_value(self, key):
 
         Returns
         -------
-        `Metadata`
+        `MetaData`
             Metadata value associated to the specified key. ``None`` is returned
             if the metadata key is not found.
         """
@@ -1267,7 +1267,7 @@ def get_value(self, key):
 
         Returns
         -------
-        `Metadata`
+        `MetaData`
             Metadata value associated to the specified key. ``None`` is returned
             if the metadata key is not found.
         """
@@ -1527,7 +1527,7 @@ def get_value(self, key):
 
         Returns
         -------
-        `Metadata`
+        `MetaData`
             Metadata value associated to the specified key. ``None`` is returned
             if the metadata key is not found.
         """

khiops/samples/samples.ipynb

@@ -503,7 +503,7 @@
    "metadata": {},
    "source": [
     "### `train_predictor_mt_with_specific_rules()`\n\n",
-    "Trains a multi-table predictor with specific construction rules\n\n    It is the same as `.train_predictor_mt` but with the specification of the allowed\n    variable construction rules. The list of available rules is found in the field\n    ``kh.all_construction_rules``\n    \n"
+    "Trains a multi-table predictor with specific construction rules\n\n    It is the same as `.train_predictor_mt` but with the specification of the allowed\n    variable construction rules. The list of available rules is found in the field\n    ``kh.ALL_CONSTRUCTION_RULES``\n    \n"
    ]
   },
   {

khiops/samples/samples.py

@@ -432,7 +432,7 @@ def train_predictor_mt_with_specific_rules():
 
     It is the same as `.train_predictor_mt` but with the specification of the allowed
     variable construction rules. The list of available rules is found in the field
-    ``kh.all_construction_rules``
+    ``kh.ALL_CONSTRUCTION_RULES``
     """
     # Imports
     import os

khiops/samples/samples_sklearn.ipynb

@@ -55,11 +55,19 @@
     "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(\"Top 5 used features\")\n",
+    "for i, feature in enumerate(khc.feature_used_names_[:5]):\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",
+    "for feature, importance in sorted(\n",
+    "    zip(khc.feature_names_in_, khc.feature_importances_),\n",
+    "    key=lambda imp: imp[1],\n",
+    "    reverse=True,\n",
+    ")[:5]:\n",
+    "    print(f\"{feature} - Importance: {importance}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the classes on the test dataset\n",
@@ -199,11 +207,10 @@
     "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(f\"{feature} - Importance: {khc.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the classes on the test dataset\n",
@@ -346,11 +353,10 @@
     "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(f\"{feature} - Importance: {khc.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the class on the test dataset\n",
@@ -630,11 +636,10 @@
     "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(f\"{feature} - Importance: {khr.feature_used_importances_[i]}\")\n",
     "print(\"---\")\n",
     "\n",
     "# Predict the values on the test dataset\n",
@@ -796,13 +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

@@ -58,11 +58,19 @@ 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]):
-        print(f"{feature} - Importance: {khc.feature_used_importances_[i][2]}")
+    print("Top 5 used features")
+    for i, feature in enumerate(khc.feature_used_names_[:5]):
+        print(f"{feature} - Importance: {khc.feature_used_importances_[i]}")
+    print("---")
+
+    print("Top 5 used features, among those present in the dataset")
+    for feature, importance in sorted(
+        zip(khc.feature_names_in_, khc.feature_importances_),
+        key=lambda imp: imp[1],
+        reverse=True,
+    )[:5]:
+        print(f"{feature} - Importance: {importance}")
     print("---")
 
     # Predict the classes on the test dataset
@@ -182,11 +190,10 @@ 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]):
-        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
@@ -311,11 +318,10 @@ 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]):
-        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
@@ -551,11 +557,10 @@ 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]):
-        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
@@ -696,13 +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_)