add conditional code for compatibility sklearn < 1.2

nairbenrekia · nairbenrekia · commit 7e7f04448c99 · 2025-03-24T12:09:39.000+01:00
diff --git a/doc/samples/samples_sklearn.rst b/doc/samples/samples_sklearn.rst
@@ -98,82 +98,6 @@ Samples
     # If you have Khiops Visualization installed you may open the report as follows
     # khc.export_report_file("report.khj")
     # kh.visualize_report("report.khj")
-.. autofunction:: khiops_classifier_boolean_target
-.. code-block:: python
-
-    # Imports
-    import os
-    import pandas as pd
-    from khiops import core as kh
-    from khiops.sklearn import KhiopsClassifier
-    from sklearn.model_selection import train_test_split
-
-    # Load the dataset into a pandas dataframe
-    adult_path = os.path.join(kh.get_samples_dir(), "Adult", "Adult.txt")
-    adult_df = pd.read_csv(adult_path, sep="\t")
-
-    # Split the whole dataframe into train and test (70%-30%)
-    adult_train_df, adult_test_df = train_test_split(
-        adult_df, test_size=0.3, random_state=1
-    )
-
-    # Split the dataset into:
-    # - the X feature table
-    # - the y target vector ("class" column)
-    X_train = adult_train_df.drop("class", axis=1)
-    X_test = adult_test_df.drop("class", axis=1)
-    y_train = adult_train_df["class"]
-    y_train.replace({"less": False, "more": True}, inplace=True)
-
-    # Create the classifier object
-    khc = KhiopsClassifier()
-
-    # Train the classifier
-    khc.fit(X_train, y_train)
-
-    # Predict the classes on the test dataset
-    y_test_pred = khc.predict(X_test)
-    print("Predicted classes (first 10):")
-    print(y_test_pred[0:10])
-    print("---")
-.. autofunction:: khiops_classifier_float_target
-.. code-block:: python
-
-    # Imports
-    import os
-    import pandas as pd
-    from khiops import core as kh
-    from khiops.sklearn import KhiopsClassifier
-    from sklearn.model_selection import train_test_split
-
-    # Load the dataset into a pandas dataframe
-    adult_path = os.path.join(kh.get_samples_dir(), "Adult", "Adult.txt")
-    adult_df = pd.read_csv(adult_path, sep="\t")
-
-    # Split the whole dataframe into train and test (70%-30%)
-    adult_train_df, adult_test_df = train_test_split(
-        adult_df, test_size=0.3, random_state=1
-    )
-
-    # Split the dataset into:
-    # - the X feature table
-    # - the y target vector ("class" column)
-    X_train = adult_train_df.drop("class", axis=1)
-    X_test = adult_test_df.drop("class", axis=1)
-    y_train = adult_train_df["class"]
-    y_train.replace({"less": 0.0, "more": 1.0}, inplace=True)
-
-    # Create the classifier object
-    khc = KhiopsClassifier()
-
-    # Train the classifier
-    khc.fit(X_train, y_train)
-
-    # Predict the classes on the test dataset
-    y_test_pred = khc.predict(X_test)
-    print("Predicted classes (first 10):")
-    print(y_test_pred[0:10])
-    print("---")
 .. autofunction:: khiops_classifier_multiclass
 .. code-block:: python
 
diff --git a/khiops/samples/samples_sklearn.ipynb b/khiops/samples/samples_sklearn.ipynb
@@ -86,108 +86,6 @@
     "# kh.visualize_report(\"report.khj\")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### `khiops_classifier_boolean_target()`\n\n",
-    "Trains a `.KhiopsClassifier` on a monotable dataframe\n    where the target is boolean\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Imports\n",
-    "import os\n",
-    "import pandas as pd\n",
-    "from khiops import core as kh\n",
-    "from khiops.sklearn import KhiopsClassifier\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "\n",
-    "# Load the dataset into a pandas dataframe\n",
-    "adult_path = os.path.join(kh.get_samples_dir(), \"Adult\", \"Adult.txt\")\n",
-    "adult_df = pd.read_csv(adult_path, sep=\"\\t\")\n",
-    "\n",
-    "# Split the whole dataframe into train and test (70%-30%)\n",
-    "adult_train_df, adult_test_df = train_test_split(\n",
-    "    adult_df, test_size=0.3, random_state=1\n",
-    ")\n",
-    "\n",
-    "# Split the dataset into:\n",
-    "# - the X feature table\n",
-    "# - the y target vector (\"class\" column)\n",
-    "X_train = adult_train_df.drop(\"class\", axis=1)\n",
-    "X_test = adult_test_df.drop(\"class\", axis=1)\n",
-    "y_train = adult_train_df[\"class\"]\n",
-    "y_train.replace({\"less\": False, \"more\": True}, inplace=True)\n",
-    "\n",
-    "# Create the classifier object\n",
-    "khc = KhiopsClassifier()\n",
-    "\n",
-    "# Train the classifier\n",
-    "khc.fit(X_train, y_train)\n",
-    "\n",
-    "# Predict the classes on the test dataset\n",
-    "y_test_pred = khc.predict(X_test)\n",
-    "print(\"Predicted classes (first 10):\")\n",
-    "print(y_test_pred[0:10])\n",
-    "print(\"---\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### `khiops_classifier_float_target()`\n\n",
-    "Trains a `.KhiopsClassifier` on a monotable dataframe\n    where the target is float\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Imports\n",
-    "import os\n",
-    "import pandas as pd\n",
-    "from khiops import core as kh\n",
-    "from khiops.sklearn import KhiopsClassifier\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "\n",
-    "# Load the dataset into a pandas dataframe\n",
-    "adult_path = os.path.join(kh.get_samples_dir(), \"Adult\", \"Adult.txt\")\n",
-    "adult_df = pd.read_csv(adult_path, sep=\"\\t\")\n",
-    "\n",
-    "# Split the whole dataframe into train and test (70%-30%)\n",
-    "adult_train_df, adult_test_df = train_test_split(\n",
-    "    adult_df, test_size=0.3, random_state=1\n",
-    ")\n",
-    "\n",
-    "# Split the dataset into:\n",
-    "# - the X feature table\n",
-    "# - the y target vector (\"class\" column)\n",
-    "X_train = adult_train_df.drop(\"class\", axis=1)\n",
-    "X_test = adult_test_df.drop(\"class\", axis=1)\n",
-    "y_train = adult_train_df[\"class\"]\n",
-    "y_train.replace({\"less\": 0.0, \"more\": 1.0}, inplace=True)\n",
-    "\n",
-    "# Create the classifier object\n",
-    "khc = KhiopsClassifier()\n",
-    "\n",
-    "# Train the classifier\n",
-    "khc.fit(X_train, y_train)\n",
-    "\n",
-    "# Predict the classes on the test dataset\n",
-    "y_test_pred = khc.predict(X_test)\n",
-    "print(\"Predicted classes (first 10):\")\n",
-    "print(y_test_pred[0:10])\n",
-    "print(\"---\")"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
diff --git a/khiops/samples/samples_sklearn.py b/khiops/samples/samples_sklearn.py
@@ -89,86 +89,6 @@ def khiops_classifier():
     # kh.visualize_report("report.khj")
 
 
-def khiops_classifier_boolean_target():
-    """Trains a `.KhiopsClassifier` on a monotable dataframe
-    where the target is boolean"""
-    # Imports
-    import os
-    import pandas as pd
-    from khiops import core as kh
-    from khiops.sklearn import KhiopsClassifier
-    from sklearn.model_selection import train_test_split
-
-    # Load the dataset into a pandas dataframe
-    adult_path = os.path.join(kh.get_samples_dir(), "Adult", "Adult.txt")
-    adult_df = pd.read_csv(adult_path, sep="\t")
-
-    # Split the whole dataframe into train and test (70%-30%)
-    adult_train_df, adult_test_df = train_test_split(
-        adult_df, test_size=0.3, random_state=1
-    )
-
-    # Split the dataset into:
-    # - the X feature table
-    # - the y target vector ("class" column)
-    X_train = adult_train_df.drop("class", axis=1)
-    X_test = adult_test_df.drop("class", axis=1)
-    y_train = adult_train_df["class"]
-    y_train.replace({"less": False, "more": True}, inplace=True)
-
-    # Create the classifier object
-    khc = KhiopsClassifier()
-
-    # Train the classifier
-    khc.fit(X_train, y_train)
-
-    # Predict the classes on the test dataset
-    y_test_pred = khc.predict(X_test)
-    print("Predicted classes (first 10):")
-    print(y_test_pred[0:10])
-    print("---")
-
-
-def khiops_classifier_float_target():
-    """Trains a `.KhiopsClassifier` on a monotable dataframe
-    where the target is float"""
-    # Imports
-    import os
-    import pandas as pd
-    from khiops import core as kh
-    from khiops.sklearn import KhiopsClassifier
-    from sklearn.model_selection import train_test_split
-
-    # Load the dataset into a pandas dataframe
-    adult_path = os.path.join(kh.get_samples_dir(), "Adult", "Adult.txt")
-    adult_df = pd.read_csv(adult_path, sep="\t")
-
-    # Split the whole dataframe into train and test (70%-30%)
-    adult_train_df, adult_test_df = train_test_split(
-        adult_df, test_size=0.3, random_state=1
-    )
-
-    # Split the dataset into:
-    # - the X feature table
-    # - the y target vector ("class" column)
-    X_train = adult_train_df.drop("class", axis=1)
-    X_test = adult_test_df.drop("class", axis=1)
-    y_train = adult_train_df["class"]
-    y_train.replace({"less": 0.0, "more": 1.0}, inplace=True)
-
-    # Create the classifier object
-    khc = KhiopsClassifier()
-
-    # Train the classifier
-    khc.fit(X_train, y_train)
-
-    # Predict the classes on the test dataset
-    y_test_pred = khc.predict(X_test)
-    print("Predicted classes (first 10):")
-    print(y_test_pred[0:10])
-    print("---")
-
-
 def khiops_classifier_multiclass():
     """Trains a multiclass `.KhiopsClassifier` on a monotable dataframe"""
     # Imports
@@ -1105,8 +1025,6 @@ def khiops_classifier_multitable_star_file():
 
 exported_samples = [
     khiops_classifier,
-    khiops_classifier_boolean_target,
-    khiops_classifier_float_target,
     khiops_classifier_multiclass,
     khiops_classifier_multitable_star,
     khiops_classifier_multitable_snowflake,
diff --git a/khiops/sklearn/dataset.py b/khiops/sklearn/dataset.py
@@ -14,6 +14,7 @@
 
 import numpy as np
 import pandas as pd
+import sklearn
 from scipy import sparse as sp
 from sklearn.utils import check_array
 from sklearn.utils.validation import column_or_1d
@@ -430,6 +431,19 @@ def write_internal_data_table(dataframe, file_path_or_stream):
     )
 
 
+def _column_or_1d_with_dtype(y, dtype=None):
+    # 'dtype' has been introduced on `column_or_1d' since Scikit-learn 1.2;
+    if sklearn.__version__ < "1.2":
+        if pd.api.types.is_string_dtype(dtype) and y.isin(["True", "False"]).all():
+            warnings.warn(
+                "'y' stores strings restricted to 'True'/'False' values: "
+                "The predict method may return a bool vector."
+            )
+        return column_or_1d(y, warn=True)
+    else:
+        return column_or_1d(y, warn=True, dtype=dtype)
+
+
 class Dataset:
     """A representation of a dataset
 
@@ -740,20 +754,20 @@ def _init_target_column(self, y):
         else:
             if hasattr(y, "dtype"):
                 if isinstance(y.dtype, pd.CategoricalDtype):
-                    y_checked = column_or_1d(
-                        y, warn=True, dtype=y.dtype.categories.dtype
+                    y_checked = _column_or_1d_with_dtype(
+                        y, dtype=y.dtype.categories.dtype
                     )
                 else:
-                    y_checked = column_or_1d(y, warn=True, dtype=y.dtype)
+                    y_checked = _column_or_1d_with_dtype(y, dtype=y.dtype)
             elif hasattr(y, "dtypes"):
                 if isinstance(y.dtypes[0], pd.CategoricalDtype):
-                    y_checked = column_or_1d(
-                        y, warn=True, dtype=y.dtypes[0].categories.dtype
+                    y_checked = _column_or_1d_with_dtype(
+                        y, dtype=y.dtypes[0].categories.dtype
                     )
                 else:
-                    y_checked = column_or_1d(y, warn=True)
+                    y_checked = _column_or_1d_with_dtype(y)
             else:
-                y_checked = column_or_1d(y, warn=True)
+                y_checked = _column_or_1d_with_dtype(y)
         # Check the target type coherence with those of X's tables
         if isinstance(
             self.main_table, (PandasTable, SparseTable, NumpyTable)
diff --git a/tests/test_sklearn_output_types.py b/tests/test_sklearn_output_types.py
@@ -195,7 +195,6 @@ def test_classifier_output_types(self):
 
                     # Check the return type of predict
                     y_pred = khc.predict(X)
-
                     self.assertTrue(
                         y_type_check(y_pred),
                         f"'{y_type_check.__name__}' was False for "
