scikit-learn-intelex 2024.2.0__py310-none-manylinux1_x86_64.whl → 2024.4.0__py310-none-manylinux1_x86_64.whl

sklearnex/ensemble/_forest.py

@@ -25,8 +25,11 @@ from sklearn.ensemble import ExtraTreesClassifier as sklearn_ExtraTreesClassifie
 from sklearn.ensemble import ExtraTreesRegressor as sklearn_ExtraTreesRegressor
 from sklearn.ensemble import RandomForestClassifier as sklearn_RandomForestClassifier
 from sklearn.ensemble import RandomForestRegressor as sklearn_RandomForestRegressor
+from sklearn.ensemble._forest import ForestClassifier as sklearn_ForestClassifier
+from sklearn.ensemble._forest import ForestRegressor as sklearn_ForestRegressor
 from sklearn.ensemble._forest import _get_n_samples_bootstrap
 from sklearn.exceptions import DataConversionWarning
+from sklearn.metrics import accuracy_score
 from sklearn.tree import (
     DecisionTreeClassifier,
     DecisionTreeRegressor,
@@ -35,12 +38,7 @@ from sklearn.tree import (
 )
 from sklearn.tree._tree import Tree
 from sklearn.utils import check_random_state, deprecated
-from sklearn.utils.validation import (
-    check_array,
-    check_consistent_length,
-    check_is_fitted,
-    check_X_y,
-)
+from sklearn.utils.validation import check_array, check_is_fitted
 
 from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import (
@@ -52,19 +50,10 @@ from onedal.ensemble import ExtraTreesClassifier as onedal_ExtraTreesClassifier
 from onedal.ensemble import ExtraTreesRegressor as onedal_ExtraTreesRegressor
 from onedal.ensemble import RandomForestClassifier as onedal_RandomForestClassifier
 from onedal.ensemble import RandomForestRegressor as onedal_RandomForestRegressor
-
-# try catch needed for changes in structures observed in Scikit-learn around v0.22
-try:
-    from sklearn.ensemble._forest import ForestClassifier as sklearn_ForestClassifier
-    from sklearn.ensemble._forest import ForestRegressor as sklearn_ForestRegressor
-except ModuleNotFoundError:
-    from sklearn.ensemble.forest import ForestClassifier as sklearn_ForestClassifier
-    from sklearn.ensemble.forest import ForestRegressor as sklearn_ForestRegressor
-
 from onedal.primitives import get_tree_state_cls, get_tree_state_reg
 from onedal.utils import _num_features, _num_samples
+from sklearnex.utils import get_namespace
 
-from .._config import get_config
 from .._device_offload import dispatch, wrap_output_data
 from .._utils import PatchingConditionsChain
 
@@ -78,24 +67,14 @@ class BaseForest(ABC):
     _onedal_factory = None
 
     def _onedal_fit(self, X, y, sample_weight=None, queue=None):
-        if sklearn_check_version("0.24"):
-            X, y = self._validate_data(
-                X,
-                y,
-                multi_output=False,
-                accept_sparse=False,
-                dtype=[np.float64, np.float32],
-                force_all_finite=False,
-            )
-        else:
-            X, y = check_X_y(
-                X,
-                y,
-                accept_sparse=False,
-                dtype=[np.float64, np.float32],
-                multi_output=False,
-                force_all_finite=False,
-            )
+        X, y = self._validate_data(
+            X,
+            y,
+            multi_output=False,
+            accept_sparse=False,
+            dtype=[np.float64, np.float32],
+            force_all_finite=False,
+        )
 
         if sample_weight is not None:
             sample_weight = self.check_sample_weight(sample_weight, X)
@@ -173,15 +152,6 @@ class BaseForest(ABC):
 
         return self
 
-    def _fit_proba(self, X, y, sample_weight=None, queue=None):
-        params = self.get_params()
-        self.__class__(**params)
-
-        # We use stock metaestimators below, so the only way
-        # to pass a queue is using config_context.
-        cfg = get_config()
-        cfg["target_offload"] = queue
-
     def _save_attributes(self):
         if self.oob_score:
             self.oob_score_ = self._onedal_estimator.oob_score_
@@ -204,8 +174,6 @@ class BaseForest(ABC):
         self._validate_estimator()
         return self
 
-    # TODO:
-    # move to onedal modul.
     def _check_parameters(self):
         if isinstance(self.min_samples_leaf, numbers.Integral):
             if not 1 <= self.min_samples_leaf:
@@ -453,14 +421,12 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
 
         # The estimator is checked against the class attribute for conformance.
         # This should only trigger if the user uses this class directly.
-        if (
-            self.estimator.__class__ == DecisionTreeClassifier
-            and self._onedal_factory != onedal_RandomForestClassifier
+        if self.estimator.__class__ == DecisionTreeClassifier and not issubclass(
+            self._onedal_factory, onedal_RandomForestClassifier
         ):
             self._onedal_factory = onedal_RandomForestClassifier
-        elif (
-            self.estimator.__class__ == ExtraTreeClassifier
-            and self._onedal_factory != onedal_ExtraTreesClassifier
+        elif self.estimator.__class__ == ExtraTreeClassifier and not issubclass(
+            self._onedal_factory, onedal_ExtraTreesClassifier
         ):
             self._onedal_factory = onedal_ExtraTreesClassifier
 
@@ -552,18 +518,14 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
             )
 
         if patching_status.get_status():
-            if sklearn_check_version("0.24"):
-                X, y = self._validate_data(
-                    X,
-                    y,
-                    multi_output=True,
-                    accept_sparse=True,
-                    dtype=[np.float64, np.float32],
-                    force_all_finite=False,
-                )
-            else:
-                X = check_array(X, dtype=[np.float64, np.float32], force_all_finite=False)
-                y = check_array(y, ensure_2d=False, dtype=X.dtype, force_all_finite=False)
+            X, y = self._validate_data(
+                X,
+                y,
+                multi_output=True,
+                accept_sparse=True,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+            )
 
             if y.ndim == 2 and y.shape[1] == 1:
                 warnings.warn(
@@ -657,9 +619,38 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
             X,
         )
 
+    def predict_log_proba(self, X):
+        xp, _ = get_namespace(X)
+        proba = self.predict_proba(X)
+
+        if self.n_outputs_ == 1:
+            return xp.log(proba)
+
+        else:
+            for k in range(self.n_outputs_):
+                proba[k] = xp.log(proba[k])
+
+            return proba
+
+    @wrap_output_data
+    def score(self, X, y, sample_weight=None):
+        return dispatch(
+            self,
+            "score",
+            {
+                "onedal": self.__class__._onedal_score,
+                "sklearn": sklearn_ForestClassifier.score,
+            },
+            X,
+            y,
+            sample_weight=sample_weight,
+        )
+
     fit.__doc__ = sklearn_ForestClassifier.fit.__doc__
     predict.__doc__ = sklearn_ForestClassifier.predict.__doc__
     predict_proba.__doc__ = sklearn_ForestClassifier.predict_proba.__doc__
+    predict_log_proba.__doc__ = sklearn_ForestClassifier.predict_log_proba.__doc__
+    score.__doc__ = sklearn_ForestClassifier.score.__doc__
 
     def _onedal_cpu_supported(self, method_name, *data):
         class_name = self.__class__.__name__
@@ -686,7 +677,7 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
                 ]
             )
 
-        elif method_name in ["predict", "predict_proba"]:
+        elif method_name in ["predict", "predict_proba", "score"]:
             X = data[0]
 
             patching_status.and_conditions(
@@ -747,11 +738,11 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
                         or self.estimator.__class__ == DecisionTreeClassifier,
                         "ExtraTrees only supported starting from oneDAL version 2023.1",
                     ),
-                    (sample_weight is not None, "sample_weight is not supported."),
+                    (sample_weight is None, "sample_weight is not supported."),
                 ]
             )
 
-        elif method_name in ["predict", "predict_proba"]:
+        elif method_name in ["predict", "predict_proba", "score"]:
             X = data[0]
 
             patching_status.and_conditions(
@@ -803,12 +794,16 @@ class ForestClassifier(sklearn_ForestClassifier, BaseForest):
         X = check_array(X, dtype=[np.float64, np.float32], force_all_finite=False)
         check_is_fitted(self, "_onedal_estimator")
 
-        if sklearn_check_version("0.23"):
-            self._check_n_features(X, reset=False)
+        self._check_n_features(X, reset=False)
         if sklearn_check_version("1.0"):
             self._check_feature_names(X, reset=False)
         return self._onedal_estimator.predict_proba(X, queue=queue)
 
+    def _onedal_score(self, X, y, sample_weight=None, queue=None):
+        return accuracy_score(
+            y, self._onedal_predict(X, queue=queue), sample_weight=sample_weight
+        )
+
 
 class ForestRegressor(sklearn_ForestRegressor, BaseForest):
     _err = "out_of_bag_error_r2|out_of_bag_error_prediction"
@@ -843,14 +838,12 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
 
         # The splitter is checked against the class attribute for conformance
         # This should only trigger if the user uses this class directly.
-        if (
-            self.estimator.__class__ == DecisionTreeRegressor
-            and self._onedal_factory != onedal_RandomForestRegressor
+        if self.estimator.__class__ == DecisionTreeRegressor and not issubclass(
+            self._onedal_factory, onedal_RandomForestRegressor
         ):
             self._onedal_factory = onedal_RandomForestRegressor
-        elif (
-            self.estimator.__class__ == ExtraTreeRegressor
-            and self._onedal_factory != onedal_ExtraTreesRegressor
+        elif self.estimator.__class__ == ExtraTreeRegressor and not issubclass(
+            self._onedal_factory, onedal_ExtraTreesRegressor
         ):
             self._onedal_factory = onedal_ExtraTreesRegressor
 
@@ -920,18 +913,14 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
             )
 
         if patching_status.get_status():
-            if sklearn_check_version("0.24"):
-                X, y = self._validate_data(
-                    X,
-                    y,
-                    multi_output=True,
-                    accept_sparse=True,
-                    dtype=[np.float64, np.float32],
-                    force_all_finite=False,
-                )
-            else:
-                X = check_array(X, dtype=[np.float64, np.float32], force_all_finite=False)
-                y = check_array(y, ensure_2d=False, dtype=X.dtype, force_all_finite=False)
+            X, y = self._validate_data(
+                X,
+                y,
+                multi_output=True,
+                accept_sparse=True,
+                dtype=[np.float64, np.float32],
+                force_all_finite=False,
+            )
 
             if y.ndim == 2 and y.shape[1] == 1:
                 warnings.warn(
@@ -1056,7 +1045,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
                         or self.estimator.__class__ == DecisionTreeClassifier,
                         "ExtraTrees only supported starting from oneDAL version 2023.1",
                     ),
-                    (sample_weight is not None, "sample_weight is not supported."),
+                    (sample_weight is None, "sample_weight is not supported."),
                 ]
             )
 
@@ -1133,7 +1122,7 @@ class ForestRegressor(sklearn_ForestRegressor, BaseForest):
     predict.__doc__ = sklearn_ForestRegressor.predict.__doc__
 
 
-@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba"])
+@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba", "score"])
 class RandomForestClassifier(ForestClassifier):
     __doc__ = sklearn_RandomForestClassifier.__doc__
     _onedal_factory = onedal_RandomForestClassifier
@@ -1544,7 +1533,7 @@ class RandomForestRegressor(ForestRegressor):
             self.min_bin_size = min_bin_size
 
 
-@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba"])
+@control_n_jobs(decorated_methods=["fit", "predict", "predict_proba", "score"])
 class ExtraTreesClassifier(ForestClassifier):
     __doc__ = sklearn_ExtraTreesClassifier.__doc__
     _onedal_factory = onedal_ExtraTreesClassifier

sklearnex/ensemble/tests/test_forest.py

@@ -45,11 +45,7 @@ def test_sklearnex_import_rf_classifier(dataframe, queue):
     assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
 
 
-# TODO:
-# investigate failure for `dpnp.ndarrays` and `dpctl.tensors` on `GPU`
-@pytest.mark.parametrize(
-    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
-)
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_rf_regression(dataframe, queue):
     from sklearnex.ensemble import RandomForestRegressor
 
@@ -59,17 +55,17 @@ def test_sklearnex_import_rf_regression(dataframe, queue):
     rf = RandomForestRegressor(max_depth=2, random_state=0).fit(X, y)
     assert "sklearnex" in rf.__module__
     pred = _as_numpy(rf.predict([[0, 0, 0, 0]]))
-    if daal_check_version((2024, "P", 0)):
-        assert_allclose([-6.971], pred, atol=1e-2)
+
+    if queue is not None and queue.sycl_device.is_gpu:
+        assert_allclose([-0.011208], pred, atol=1e-2)
     else:
-        assert_allclose([-6.839], pred, atol=1e-2)
+        if daal_check_version((2024, "P", 0)):
+            assert_allclose([-6.971], pred, atol=1e-2)
+        else:
+            assert_allclose([-6.839], pred, atol=1e-2)
 
 
-# TODO:
-# investigate failure for `dpnp.ndarrays` and `dpctl.tensors` on `GPU`
-@pytest.mark.parametrize(
-    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
-)
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_et_classifier(dataframe, queue):
     from sklearnex.ensemble import ExtraTreesClassifier
 
@@ -90,11 +86,7 @@ def test_sklearnex_import_et_classifier(dataframe, queue):
     assert_allclose([1], _as_numpy(rf.predict([[0, 0, 0, 0]])))
 
 
-# TODO:
-# investigate failure for `dpnp.ndarrays` and `dpctl.tensors` on `GPU`
-@pytest.mark.parametrize(
-    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
-)
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 def test_sklearnex_import_et_regression(dataframe, queue):
     from sklearnex.ensemble import ExtraTreesRegressor
 
@@ -114,4 +106,8 @@ def test_sklearnex_import_et_regression(dataframe, queue):
             ]
         )
     )
-    assert_allclose([0.445], pred, atol=1e-2)
+
+    if queue is not None and queue.sycl_device.is_gpu:
+        assert_allclose([1.909769], pred, atol=1e-2)
+    else:
+        assert_allclose([0.445], pred, atol=1e-2)