Move file dataset deprecation warning to sklearn.estimators

doc/samples/samples_sklearn.rst

@@ -111,9 +111,8 @@ Samples
 .. code-block:: python
 
     def khiops_classifier_sparse():
-
         # Load 3 classes of the 20newsgroups dataset
-        categories = ["comp.graphics", "sci.space", "misc.forsale"]
+        categories = ["comp.graphics", "sci.space", "misc.forsale", "alt.atheism"]
         data_train, y_train = fetch_20newsgroups(
             subset="train",
             categories=categories,
@@ -125,15 +124,18 @@ Samples
             return_X_y=True,
         )
 
-        # Extract features from the training data using a sparse vectorizer
-        vectorizer = HashingVectorizer(n_features=2**10, stop_words="english")
+        # Extract features from the train and test data using a sparse vectorizer
+        vectorizer = HashingVectorizer(n_features=2048, stop_words="english")
         X_train = vectorizer.fit_transform(data_train)
-
-        # Extract features from the test data using the same vectorizer
         X_test = vectorizer.transform(data_test)
 
-        # Create the classifier object
-        khc = KhiopsClassifier()
+        # Print density of the intermediary datasets
+        print(f"X_train density: {X_train.size/(X_train.shape[0]*X_train.shape[1])}")
+        print(f"X_test density : {X_test.size/(X_test.shape[0]*X_test.shape[1])}")
+        print("---")
+
+        # Create the classifier object (no trees)
+        khc = KhiopsClassifier(n_trees=0)
 
         # Train the classifier
         khc.fit(X_train, y_train)

khiops/samples/samples_sklearn.ipynb

@@ -102,10 +102,15 @@
    "outputs": [],
    "source": [
     "def khiops_classifier_sparse():\n",
-    "    \"\"\"Trains a `.KhiopsClassifier` on a monotable sparse matrix\"\"\"\n",
+    "    \"\"\"Trains a `.KhiopsClassifier` on a monotable sparse matrix\n",
     "\n",
+    "    .. note::\n",
+    "        No intermediary dense data is used by Khiops because it supports sparse data\n",
+    "        natively.\n",
+    "\n",
+    "    \"\"\"\n",
     "    # Load 3 classes of the 20newsgroups dataset\n",
-    "    categories = [\"comp.graphics\", \"sci.space\", \"misc.forsale\"]\n",
+    "    categories = [\"comp.graphics\", \"sci.space\", \"misc.forsale\", \"alt.atheism\"]\n",
     "    data_train, y_train = fetch_20newsgroups(\n",
     "        subset=\"train\",\n",
     "        categories=categories,\n",
@@ -117,15 +122,18 @@
     "        return_X_y=True,\n",
     "    )\n",
     "\n",
-    "    # Extract features from the training data using a sparse vectorizer\n",
-    "    vectorizer = HashingVectorizer(n_features=2**10, stop_words=\"english\")\n",
+    "    # Extract features from the train and test data using a sparse vectorizer\n",
+    "    vectorizer = HashingVectorizer(n_features=2048, stop_words=\"english\")\n",
     "    X_train = vectorizer.fit_transform(data_train)\n",
-    "\n",
-    "    # Extract features from the test data using the same vectorizer\n",
     "    X_test = vectorizer.transform(data_test)\n",
     "\n",
-    "    # Create the classifier object\n",
-    "    khc = KhiopsClassifier()\n",
+    "    # Print density of the intermediary datasets\n",
+    "    print(f\"X_train density: {X_train.size/(X_train.shape[0]*X_train.shape[1])}\")\n",
+    "    print(f\"X_test density : {X_test.size/(X_test.shape[0]*X_test.shape[1])}\")\n",
+    "    print(\"---\")\n",
+    "\n",
+    "    # Create the classifier object (no trees)\n",
+    "    khc = KhiopsClassifier(n_trees=0)\n",
     "\n",
     "    # Train the classifier\n",
     "    khc.fit(X_train, y_train)\n",

khiops/samples/samples_sklearn.py

@@ -92,10 +92,15 @@ def khiops_classifier():
 
 
 def khiops_classifier_sparse():
-    """Trains a `.KhiopsClassifier` on a monotable sparse matrix"""
+    """Trains a `.KhiopsClassifier` on a monotable sparse matrix
 
+    .. note::
+        No intermediary dense data is used by Khiops because it supports sparse data
+        natively.
+
+    """
     # Load 3 classes of the 20newsgroups dataset
-    categories = ["comp.graphics", "sci.space", "misc.forsale"]
+    categories = ["comp.graphics", "sci.space", "misc.forsale", "alt.atheism"]
     data_train, y_train = fetch_20newsgroups(
         subset="train",
         categories=categories,
@@ -107,15 +112,18 @@ def khiops_classifier_sparse():
         return_X_y=True,
     )
 
-    # Extract features from the training data using a sparse vectorizer
-    vectorizer = HashingVectorizer(n_features=2**10, stop_words="english")
+    # Extract features from the train and test data using a sparse vectorizer
+    vectorizer = HashingVectorizer(n_features=2048, stop_words="english")
     X_train = vectorizer.fit_transform(data_train)
-
-    # Extract features from the test data using the same vectorizer
     X_test = vectorizer.transform(data_test)
 
-    # Create the classifier object
-    khc = KhiopsClassifier()
+    # Print density of the intermediary datasets
+    print(f"X_train density: {X_train.size/(X_train.shape[0]*X_train.shape[1])}")
+    print(f"X_test density : {X_test.size/(X_test.shape[0]*X_test.shape[1])}")
+    print("---")
+
+    # Create the classifier object (no trees)
+    khc = KhiopsClassifier(n_trees=0)
 
     # Train the classifier
     khc.fit(X_train, y_train)

khiops/sklearn/estimators.py

@@ -305,6 +305,15 @@ def fit(self, X, y=None, **kwargs):
         try:
             categorical_target = kwargs.get("categorical_target", True)
             dataset = Dataset(X, y, categorical_target=categorical_target, key=self.key)
+            if not dataset.is_in_memory():
+                warnings.warn(
+                    deprecation_message(
+                        "File-path dataset sklearn input",
+                        "11.0.0",
+                        "in-memory datasets or khiops.core API",
+                        quote=False,
+                    ),
+                )
             self._fit(dataset, computation_dir, **kwargs)
         # Undefine any attributes to pass to "not fitted"
         except:
@@ -527,8 +536,18 @@ def _transform_deploy_model(
 
     def _transform_check_dataset(self, dataset):
         """Checks the dataset before deploying a model on them"""
-        if not dataset.is_in_memory() and self.output_dir is None:
-            raise ValueError("'output_dir' is not set but dataset is file-based")
+        if not dataset.is_in_memory():
+            warnings.warn(
+                deprecation_message(
+                    "File-path dataset input",
+                    "11.0.0",
+                    "in-memory datasets or khiops.core API",
+                    quote=False,
+                ),
+                stacklevel=4,
+            )
+            if self.output_dir is None:
+                raise ValueError("'output_dir' is not set but dataset is file-based")
 
     def _transform_deployment_post_process(
         self, deployment_dataset, output_table_path, drop_key

khiops/sklearn/tables.py

@@ -619,15 +619,6 @@ def _init_tables_from_mapping(self, X, y=None, categorical_target=True):
 
         # Initialize a file dataset
         if isinstance(main_table_source, str):
-            warnings.warn(
-                deprecation_message(
-                    "File-path dataset input",
-                    "11.0.0",
-                    "dataframe-based dataset or khiops.core API",
-                    quote=False,
-                ),
-                stacklevel=4,
-            )
             # Obtain the file format parameters
             if "format" in X:
                 self.sep, self.header = X["format"]