scikit-learn-intelex 2024.2.0__py39-none-win_amd64.whl → 2025.1.0__py39-none-win_amd64.whl

scikit_learn_intelex-2025.1.0.data/data/Lib/site-packages/sklearnex/linear_model/tests/test_incremental_ridge.py

@@ -0,0 +1,153 @@
+# ===============================================================================
+# Copyright 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ===============================================================================
+
+from daal4py.sklearn._utils import daal_check_version
+
+if daal_check_version((2024, "P", 600)):
+    import numpy as np
+    import pytest
+    from numpy.testing import assert_allclose
+    from sklearn.exceptions import NotFittedError
+
+    from onedal.tests.utils._dataframes_support import (
+        _as_numpy,
+        _convert_to_dataframe,
+        get_dataframes_and_queues,
+    )
+    from sklearnex.linear_model import IncrementalRidge
+
+    def _compute_ridge_coefficients(X, y, alpha, fit_intercept):
+        coefficients_manual, intercept_manual = None, None
+        if fit_intercept:
+            X_mean = np.mean(X, axis=0)
+            y_mean = np.mean(y)
+            X_centered = X - X_mean
+            y_centered = y - y_mean
+
+            X_with_intercept = np.hstack([np.ones((X.shape[0], 1)), X_centered])
+            lambda_identity = alpha * np.eye(X_with_intercept.shape[1])
+            inverse_term = np.linalg.inv(
+                np.dot(X_with_intercept.T, X_with_intercept) + lambda_identity
+            )
+            xt_y = np.dot(X_with_intercept.T, y_centered)
+            coefficients_manual = np.dot(inverse_term, xt_y)
+
+            intercept_manual = y_mean - np.dot(X_mean, coefficients_manual[1:])
+            coefficients_manual = coefficients_manual[1:]
+        else:
+            lambda_identity = alpha * np.eye(X.shape[1])
+            inverse_term = np.linalg.inv(np.dot(X.T, X) + lambda_identity)
+            xt_y = np.dot(X.T, y)
+            coefficients_manual = np.dot(inverse_term, xt_y)
+
+        return coefficients_manual, intercept_manual
+
+    @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+    @pytest.mark.parametrize("batch_size", [10, 100, 1000])
+    @pytest.mark.parametrize("alpha", [0.1, 0.5, 1.0])
+    @pytest.mark.parametrize("fit_intercept", [True, False])
+    def test_inc_ridge_fit_coefficients(
+        dataframe, queue, alpha, batch_size, fit_intercept
+    ):
+        sample_size, feature_size = 1000, 50
+        X = np.random.rand(sample_size, feature_size)
+        y = np.random.rand(sample_size)
+        X_c = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+        y_c = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+
+        inc_ridge = IncrementalRidge(
+            fit_intercept=fit_intercept, alpha=alpha, batch_size=batch_size
+        )
+        inc_ridge.fit(X_c, y_c)
+
+        coefficients_manual, intercept_manual = _compute_ridge_coefficients(
+            X, y, alpha, fit_intercept
+        )
+        if fit_intercept:
+            assert_allclose(inc_ridge.intercept_, intercept_manual, rtol=1e-6, atol=1e-6)
+
+        assert_allclose(inc_ridge.coef_, coefficients_manual, rtol=1e-6, atol=1e-6)
+
+    @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+    @pytest.mark.parametrize("batch_size", [2, 5])
+    @pytest.mark.parametrize("alpha", [0.1, 0.5, 1.0])
+    def test_inc_ridge_partial_fit_coefficients(dataframe, queue, alpha, batch_size):
+        sample_size, feature_size = 1000, 50
+        X = np.random.rand(sample_size, feature_size)
+        y = np.random.rand(sample_size)
+        X_split = np.array_split(X, batch_size)
+        y_split = np.array_split(y, batch_size)
+
+        inc_ridge = IncrementalRidge(fit_intercept=False, alpha=alpha)
+
+        for batch_index in range(len(X_split)):
+            X_c = _convert_to_dataframe(
+                X_split[batch_index], sycl_queue=queue, target_df=dataframe
+            )
+            y_c = _convert_to_dataframe(
+                y_split[batch_index], sycl_queue=queue, target_df=dataframe
+            )
+            inc_ridge.partial_fit(X_c, y_c)
+
+        lambda_identity = alpha * np.eye(X.shape[1])
+        inverse_term = np.linalg.inv(np.dot(X.T, X) + lambda_identity)
+        xt_y = np.dot(X.T, y)
+        coefficients_manual = np.dot(inverse_term, xt_y)
+
+        assert_allclose(inc_ridge.coef_, coefficients_manual, rtol=1e-6, atol=1e-6)
+
+    def test_inc_ridge_score_before_fit():
+        X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
+        y = np.dot(X, np.array([1, 2])) + 3
+        inc_ridge = IncrementalRidge(alpha=0.5)
+        with pytest.raises(NotFittedError):
+            inc_ridge.score(X, y)
+
+    def test_inc_ridge_predict_before_fit():
+        X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
+        inc_ridge = IncrementalRidge(alpha=0.5)
+        with pytest.raises(NotFittedError):
+            inc_ridge.predict(X)
+
+    def test_inc_ridge_score_after_fit():
+        X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
+        y = np.dot(X, np.array([1, 2])) + 3
+        inc_ridge = IncrementalRidge(alpha=0.5)
+        inc_ridge.fit(X, y)
+        assert inc_ridge.score(X, y) >= 0.97
+
+    @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+    @pytest.mark.parametrize("fit_intercept", [True, False])
+    def test_inc_ridge_predict_after_fit(dataframe, queue, fit_intercept):
+        sample_size, feature_size = 1000, 50
+        X = np.random.rand(sample_size, feature_size)
+        y = np.random.rand(sample_size)
+        X_c = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+        y_c = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+
+        inc_ridge = IncrementalRidge(fit_intercept=fit_intercept, alpha=0.5)
+        inc_ridge.fit(X_c, y_c)
+
+        y_pred = inc_ridge.predict(X_c)
+
+        coefficients_manual, intercept_manual = _compute_ridge_coefficients(
+            X, y, 0.5, fit_intercept
+        )
+        y_pred_manual = np.dot(X, coefficients_manual)
+        if fit_intercept:
+            y_pred_manual += intercept_manual
+
+        assert_allclose(_as_numpy(y_pred), y_pred_manual, rtol=1e-6, atol=1e-6)

scikit_learn_intelex-2025.1.0.data/data/Lib/site-packages/sklearnex/linear_model/tests/test_linear.py

@@ -0,0 +1,167 @@
+# ===============================================================================
+# Copyright 2021 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ===============================================================================
+
+import numpy as np
+import pytest
+from numpy.testing import assert_allclose
+from scipy.linalg import lstsq
+from sklearn.datasets import make_regression
+
+from daal4py.sklearn._utils import daal_check_version
+from daal4py.sklearn.linear_model.tests.test_ridge import (
+    _test_multivariate_ridge_alpha_shape,
+    _test_multivariate_ridge_coefficients,
+)
+from onedal.tests.utils._dataframes_support import (
+    _as_numpy,
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+from sklearnex.tests.utils import _IS_INTEL
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+@pytest.mark.parametrize("macro_block", [None, 1024])
+@pytest.mark.parametrize("overdetermined", [False, True])
+@pytest.mark.parametrize("multi_output", [False, True])
+def test_sklearnex_import_linear(
+    dataframe, queue, dtype, macro_block, overdetermined, multi_output
+):
+    if (overdetermined or multi_output) and not daal_check_version((2025, "P", 1)):
+        pytest.skip()
+    if overdetermined and queue and queue.sycl_device.is_gpu:
+        pytest.skip()
+
+    from sklearnex.linear_model import LinearRegression
+
+    rng = np.random.default_rng(seed=123)
+    X = rng.standard_normal(size=(10, 20) if overdetermined else (20, 5))
+    y = rng.standard_normal(size=(X.shape[0], 3) if multi_output else X.shape[0])
+
+    Xi = np.c_[X, np.ones((X.shape[0], 1))]
+    expected_coefs = lstsq(Xi, y)[0]
+    expected_intercept = expected_coefs[-1]
+    expected_coefs = expected_coefs[: X.shape[1]]
+    if multi_output:
+        expected_coefs = expected_coefs.T
+
+    linreg = LinearRegression()
+    if daal_check_version((2024, "P", 0)) and macro_block is not None:
+        hparams = linreg.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+        hparams.gpu_macro_block = macro_block
+
+    X = X.astype(dtype=dtype)
+    y = y.astype(dtype=dtype)
+    y_list = y.tolist()
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    linreg.fit(X, y)
+
+    assert hasattr(linreg, "_onedal_estimator")
+    assert "sklearnex" in linreg.__module__
+
+    rtol = 1e-3 if dtype == np.float32 else 1e-5
+    assert_allclose(_as_numpy(linreg.coef_), expected_coefs, rtol=rtol)
+    assert_allclose(_as_numpy(linreg.intercept_), expected_intercept, rtol=rtol)
+
+    # check that it also works with lists
+    if isinstance(X, np.ndarray):
+        linreg_list = LinearRegression().fit(X, y_list)
+        assert_allclose(linreg_list.coef_, linreg.coef_)
+        assert_allclose(linreg_list.intercept_, linreg.intercept_)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_ridge(dataframe, queue):
+    from sklearnex.linear_model import Ridge
+
+    X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
+    y = np.dot(X, np.array([1, 2])) + 3
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    ridgereg = Ridge().fit(X, y)
+    assert "daal4py" in ridgereg.__module__
+    assert_allclose(ridgereg.intercept_, 4.5)
+    assert_allclose(ridgereg.coef_, [0.8, 1.4])
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_lasso(dataframe, queue):
+    from sklearnex.linear_model import Lasso
+
+    X = [[0, 0], [1, 1], [2, 2]]
+    y = [0, 1, 2]
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    lasso = Lasso(alpha=0.1).fit(X, y)
+    assert "daal4py" in lasso.__module__
+    assert_allclose(lasso.intercept_, 0.15)
+    assert_allclose(lasso.coef_, [0.85, 0.0])
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_elastic(dataframe, queue):
+    from sklearnex.linear_model import ElasticNet
+
+    X, y = make_regression(n_features=2, random_state=0)
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+    elasticnet = ElasticNet(random_state=0).fit(X, y)
+    assert "daal4py" in elasticnet.__module__
+    assert_allclose(elasticnet.intercept_, 1.451, atol=1e-3)
+    assert_allclose(elasticnet.coef_, [18.838, 64.559], atol=1e-3)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_reconstruct_model(dataframe, queue, dtype):
+    from sklearnex.linear_model import LinearRegression
+
+    seed = 42
+    num_samples = 3500
+    num_features, num_targets = 14, 9
+
+    gen = np.random.default_rng(seed)
+    intercept = gen.random(size=num_targets, dtype=dtype)
+    coef = gen.random(size=(num_targets, num_features), dtype=dtype).T
+
+    X = gen.random(size=(num_samples, num_features), dtype=dtype)
+    gtr = X @ coef + intercept[np.newaxis, :]
+
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+
+    linreg = LinearRegression(fit_intercept=True)
+    linreg.coef_ = coef.T
+    linreg.intercept_ = intercept
+
+    y_pred = linreg.predict(X)
+
+    tol = 1e-5 if _as_numpy(y_pred).dtype == np.float32 else 1e-7
+    assert_allclose(gtr, _as_numpy(y_pred), rtol=tol)
+
+
+def test_sklearnex_multivariate_ridge_coefs():
+    from sklearnex.linear_model import Ridge
+
+    _test_multivariate_ridge_coefficients(Ridge, random_state=0)
+
+
+def test_sklearnex_multivariate_ridge_alpha_shape():
+    from sklearnex.linear_model import Ridge
+
+    _test_multivariate_ridge_alpha_shape(Ridge, random_state=0)

{scikit_learn_intelex-2024.2.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/linear_model/tests/test_logreg.py

@@ -16,8 +16,9 @@
 
 import numpy as np
 import pytest
-from numpy.testing import assert_allclose
-from sklearn.datasets import load_breast_cancer, load_iris
+from numpy.testing import assert_allclose, assert_array_equal
+from scipy.sparse import csr_matrix
+from sklearn.datasets import load_breast_cancer, load_iris, make_classification
 from sklearn.metrics import accuracy_score
 from sklearn.model_selection import train_test_split
 
@@ -26,7 +27,9 @@ from onedal.tests.utils._dataframes_support import (
     _as_numpy,
     _convert_to_dataframe,
     get_dataframes_and_queues,
+    get_queues,
 )
+from sklearnex import config_context
 
 
 def prepare_input(X, y, dataframe, queue):
@@ -40,8 +43,7 @@ def prepare_input(X, y, dataframe, queue):
 
 
 @pytest.mark.parametrize(
-    "dataframe,queue",
-    get_dataframes_and_queues(device_filter_="cpu"),
+    "dataframe,queue", get_dataframes_and_queues(device_filter_="cpu")
 )
 def test_sklearnex_multiclass_classification(dataframe, queue):
     from sklearnex.linear_model import LogisticRegression
@@ -91,3 +93,42 @@ def test_sklearnex_binary_classification(dataframe, queue):
 
     y_pred = _as_numpy(logreg.predict(X_test))
     assert accuracy_score(y_test, y_pred) > 0.95
+
+
+if daal_check_version((2024, "P", 700)):
+
+    @pytest.mark.parametrize("queue", get_queues("gpu"))
+    @pytest.mark.parametrize("dtype", [np.float32, np.float64])
+    @pytest.mark.parametrize(
+        "dims", [(3007, 17, 0.05), (50000, 100, 0.01), (512, 10, 0.5)]
+    )
+    def test_csr(queue, dtype, dims):
+        from sklearnex.linear_model import LogisticRegression
+
+        n, p, density = dims
+
+        # Create sparse dataset for classification
+        X, y = make_classification(n, p, random_state=42)
+        X = X.astype(dtype)
+        y = y.astype(dtype)
+        np.random.seed(2007 + n + p)
+        mask = np.random.binomial(1, density, (n, p))
+        X = X * mask
+        X_sp = csr_matrix(X)
+
+        model = LogisticRegression(fit_intercept=True, solver="newton-cg")
+        model_sp = LogisticRegression(fit_intercept=True, solver="newton-cg")
+
+        with config_context(target_offload="gpu:0"):
+            model.fit(X, y)
+            pred = model.predict(X)
+            prob = model.predict_proba(X)
+            model_sp.fit(X_sp, y)
+            pred_sp = model_sp.predict(X_sp)
+            prob_sp = model_sp.predict_proba(X_sp)
+
+        rtol = 2e-4
+        assert_allclose(pred, pred_sp, rtol=rtol)
+        assert_allclose(prob, prob_sp, rtol=rtol)
+        assert_allclose(model.coef_, model_sp.coef_, rtol=rtol)
+        assert_allclose(model.intercept_, model_sp.intercept_, rtol=rtol)

{scikit_learn_intelex-2024.2.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/manifold/t_sne.py

@@ -15,3 +15,7 @@
 # ===============================================================================
 
 from daal4py.sklearn.manifold import TSNE
+from onedal._device_offload import support_input_format
+
+TSNE.fit = support_input_format(queue_param=False)(TSNE.fit)
+TSNE.fit_transform = support_input_format(queue_param=False)(TSNE.fit_transform)

{scikit_learn_intelex-2024.2.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/metrics/pairwise.py

@@ -15,3 +15,8 @@
 # ===============================================================================
 
 from daal4py.sklearn.metrics import pairwise_distances
+from onedal._device_offload import support_input_format
+
+pairwise_distances = support_input_format(freefunc=True, queue_param=False)(
+    pairwise_distances
+)

{scikit_learn_intelex-2024.2.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/metrics/ranking.py

@@ -15,3 +15,6 @@
 # ===============================================================================
 
 from daal4py.sklearn.metrics import roc_auc_score
+from onedal._device_offload import support_input_format
+
+roc_auc_score = support_input_format(freefunc=True, queue_param=False)(roc_auc_score)

{scikit_learn_intelex-2024.2.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/model_selection/split.py

@@ -15,3 +15,8 @@
 # ===============================================================================
 
 from daal4py.sklearn.model_selection import train_test_split
+from onedal._device_offload import support_input_format
+
+train_test_split = support_input_format(freefunc=True, queue_param=False)(
+    train_test_split
+)

{scikit_learn_intelex-2024.2.0.data → scikit_learn_intelex-2025.1.0.data}/data/Lib/site-packages/sklearnex/neighbors/_lof.py

@@ -17,29 +17,35 @@
 import warnings
 
 import numpy as np
-from sklearn.neighbors import LocalOutlierFactor as sklearn_LocalOutlierFactor
+from sklearn.neighbors import LocalOutlierFactor as _sklearn_LocalOutlierFactor
 from sklearn.utils.metaestimators import available_if
 from sklearn.utils.validation import check_is_fitted
 
 from daal4py.sklearn._n_jobs_support import control_n_jobs
 from daal4py.sklearn._utils import sklearn_check_version
+from sklearnex._device_offload import dispatch, wrap_output_data
+from sklearnex.neighbors.common import KNeighborsDispatchingBase
+from sklearnex.neighbors.knn_unsupervised import NearestNeighbors
 
-from .._device_offload import dispatch, wrap_output_data
-from .common import KNeighborsDispatchingBase
-from .knn_unsupervised import NearestNeighbors
+from ..utils._array_api import get_namespace
 
+if sklearn_check_version("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+    validate_data = _sklearn_LocalOutlierFactor._validate_data
 
-@control_n_jobs(decorated_methods=["fit", "kneighbors"])
-class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
+
+@control_n_jobs(decorated_methods=["fit", "kneighbors", "_kneighbors"])
+class LocalOutlierFactor(KNeighborsDispatchingBase, _sklearn_LocalOutlierFactor):
     __doc__ = (
-        sklearn_LocalOutlierFactor.__doc__
+        _sklearn_LocalOutlierFactor.__doc__
         + "\n NOTE: When X=None, methods kneighbors, kneighbors_graph, and predict will"
         + "\n only output numpy arrays. In that case, the only way to offload to gpu"
         + "\n is to use a global queue (e.g. using config_context)"
     )
     if sklearn_check_version("1.2"):
         _parameter_constraints: dict = {
-            **sklearn_LocalOutlierFactor._parameter_constraints
+            **_sklearn_LocalOutlierFactor._parameter_constraints
         }
 
     # Only certain methods should be taken from knn to prevent code
@@ -97,32 +103,37 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
                 self.negative_outlier_factor_, 100.0 * self.contamination
             )
 
+        # adoption of warning for data with duplicated samples from
+        # https://github.com/scikit-learn/scikit-learn/pull/28773
+        if sklearn_check_version("1.6"):
+            if np.min(self.negative_outlier_factor_) < -1e7 and not self.novelty:
+                warnings.warn(
+                    "Duplicate values are leading to incorrect results. "
+                    "Increase the number of neighbors for more accurate results."
+                )
+
         return self
 
     def fit(self, X, y=None):
-        self._fit_validation(X, y)
         result = dispatch(
             self,
             "fit",
             {
                 "onedal": self.__class__._onedal_fit,
-                "sklearn": sklearn_LocalOutlierFactor.fit,
+                "sklearn": _sklearn_LocalOutlierFactor.fit,
             },
             X,
             None,
         )
         return result
 
-    # Subtle order change to remove check_array and preserve dpnp and
-    # dpctl conformance. decision_function will return a dpnp or dpctl
-    # instance via kneighbors and an equivalent check_array exists in
-    # that call already in sklearn so no loss of functionality occurs
     def _predict(self, X=None):
         check_is_fitted(self)
 
         if X is not None:
+            xp, _ = get_namespace(X)
             output = self.decision_function(X) < 0
-            is_inlier = np.ones(output.shape[0], dtype=int)
+            is_inlier = xp.ones_like(output, dtype=int)
             is_inlier[output] = -1
         else:
             is_inlier = np.ones(self.n_samples_fit_, dtype=int)
@@ -134,18 +145,32 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
     # argument is given and it is a dpctl tensor or dpnp array.
     # This would cause issues in fit_predict. Also, available_if
     # is hard to unwrap, and this is the most straighforward way.
-    @available_if(sklearn_LocalOutlierFactor._check_novelty_fit_predict)
+    @available_if(_sklearn_LocalOutlierFactor._check_novelty_fit_predict)
     @wrap_output_data
     def fit_predict(self, X, y=None):
+        """Fit the model to the training set X and return the labels.
+
+        **Not available for novelty detection (when novelty is set to True).**
+        Label is 1 for an inlier and -1 for an outlier according to the LOF
+        score and the contamination parameter.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features), default=None
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        is_inlier : ndarray of shape (n_samples,)
+            Returns -1 for anomalies/outliers and 1 for inliers.
+        """
         return self.fit(X)._predict()
 
-    @available_if(sklearn_LocalOutlierFactor._check_novelty_predict)
-    @wrap_output_data
-    def predict(self, X=None):
-        return self._predict(X)
-
-    @wrap_output_data
-    def kneighbors(self, X=None, n_neighbors=None, return_distance=True):
+    def _kneighbors(self, X=None, n_neighbors=None, return_distance=True):
         check_is_fitted(self)
         if sklearn_check_version("1.0") and X is not None:
             self._check_feature_names(X, reset=False)
@@ -154,14 +179,58 @@ class LocalOutlierFactor(KNeighborsDispatchingBase, sklearn_LocalOutlierFactor):
             "kneighbors",
             {
                 "onedal": self.__class__._onedal_kneighbors,
-                "sklearn": sklearn_LocalOutlierFactor.kneighbors,
+                "sklearn": _sklearn_LocalOutlierFactor.kneighbors,
             },
             X,
             n_neighbors=n_neighbors,
             return_distance=return_distance,
         )
 
-    fit.__doc__ = sklearn_LocalOutlierFactor.fit.__doc__
-    fit_predict.__doc__ = sklearn_LocalOutlierFactor.fit_predict.__doc__
-    predict.__doc__ = sklearn_LocalOutlierFactor.predict.__doc__
-    kneighbors.__doc__ = sklearn_LocalOutlierFactor.kneighbors.__doc__
+    kneighbors = wrap_output_data(_kneighbors)
+
+    @available_if(_sklearn_LocalOutlierFactor._check_novelty_score_samples)
+    @wrap_output_data
+    def score_samples(self, X):
+        """Opposite of the Local Outlier Factor of X.
+
+        It is the opposite as bigger is better, i.e. large values correspond
+        to inliers.
+
+        **Only available for novelty detection (when novelty is set to True).**
+        The argument X is supposed to contain *new data*: if X contains a
+        point from training, it considers the later in its own neighborhood.
+        Also, the samples in X are not considered in the neighborhood of any
+        point. Because of this, the scores obtained via ``score_samples`` may
+        differ from the standard LOF scores.
+        The standard LOF scores for the training data is available via the
+        ``negative_outlier_factor_`` attribute.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples.
+
+        Returns
+        -------
+        opposite_lof_scores : ndarray of shape (n_samples,)
+            The opposite of the Local Outlier Factor of each input samples.
+            The lower, the more abnormal.
+        """
+        check_is_fitted(self)
+
+        distances_X, neighbors_indices_X = self._kneighbors(
+            X, n_neighbors=self.n_neighbors_
+        )
+
+        X_lrd = self._local_reachability_density(
+            distances_X,
+            neighbors_indices_X,
+        )
+
+        lrd_ratios_array = self._lrd[neighbors_indices_X] / X_lrd[:, np.newaxis]
+
+        return -np.mean(lrd_ratios_array, axis=1)
+
+    fit.__doc__ = _sklearn_LocalOutlierFactor.fit.__doc__
+    kneighbors.__doc__ = _sklearn_LocalOutlierFactor.kneighbors.__doc__