scikit-learn-intelex 2024.3.0__py38-none-win_amd64.whl → 2024.5.0__py38-none-win_amd64.whl

scikit_learn_intelex-2024.5.0.data/data/Lib/site-packages/sklearnex/linear_model/linear.py

@@ -0,0 +1,316 @@
+# ===============================================================================
+# Copyright 2023 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 logging
+from abc import ABC
+
+import numpy as np
+from sklearn.exceptions import NotFittedError
+from sklearn.linear_model import LinearRegression as sklearn_LinearRegression
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import sklearn_check_version
+
+from .._device_offload import dispatch, wrap_output_data
+from .._utils import PatchingConditionsChain, get_patch_message, register_hyperparameters
+from ..utils.validation import _assert_all_finite
+
+if sklearn_check_version("1.0") and not sklearn_check_version("1.2"):
+    from sklearn.linear_model._base import _deprecate_normalize
+
+from scipy.sparse import issparse
+from sklearn.utils.validation import check_X_y
+
+from onedal.common.hyperparameters import get_hyperparameters
+from onedal.linear_model import LinearRegression as onedal_LinearRegression
+from onedal.utils import _num_features, _num_samples
+
+
+@register_hyperparameters({"fit": get_hyperparameters("linear_regression", "train")})
+@control_n_jobs(decorated_methods=["fit", "predict"])
+class LinearRegression(sklearn_LinearRegression):
+    __doc__ = sklearn_LinearRegression.__doc__
+
+    if sklearn_check_version("1.2"):
+        _parameter_constraints: dict = {**sklearn_LinearRegression._parameter_constraints}
+
+        def __init__(
+            self,
+            fit_intercept=True,
+            copy_X=True,
+            n_jobs=None,
+            positive=False,
+        ):
+            super().__init__(
+                fit_intercept=fit_intercept,
+                copy_X=copy_X,
+                n_jobs=n_jobs,
+                positive=positive,
+            )
+
+    else:
+
+        def __init__(
+            self,
+            fit_intercept=True,
+            normalize="deprecated" if sklearn_check_version("1.0") else False,
+            copy_X=True,
+            n_jobs=None,
+            positive=False,
+        ):
+            super().__init__(
+                fit_intercept=fit_intercept,
+                normalize=normalize,
+                copy_X=copy_X,
+                n_jobs=n_jobs,
+                positive=positive,
+            )
+
+    def fit(self, X, y, sample_weight=None):
+        if sklearn_check_version("1.0"):
+            self._check_feature_names(X, reset=True)
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        # It is necessary to properly update coefs for predict if we
+        # fallback to sklearn in dispatch
+        if hasattr(self, "_onedal_estimator"):
+            del self._onedal_estimator
+
+        dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": sklearn_LinearRegression.fit,
+            },
+            X,
+            y,
+            sample_weight,
+        )
+        return self
+
+    @wrap_output_data
+    def predict(self, X):
+
+        if not hasattr(self, "coef_"):
+            msg = (
+                "This %(name)s instance is not fitted yet. Call 'fit' with "
+                "appropriate arguments before using this estimator."
+            )
+            raise NotFittedError(msg % {"name": self.__class__.__name__})
+
+        return dispatch(
+            self,
+            "predict",
+            {
+                "onedal": self.__class__._onedal_predict,
+                "sklearn": sklearn_LinearRegression.predict,
+            },
+            X,
+        )
+
+    def _test_type_and_finiteness(self, X_in):
+        X = X_in if isinstance(X_in, np.ndarray) else np.asarray(X_in)
+
+        dtype = X.dtype
+        if "complex" in str(type(dtype)):
+            return False
+
+        try:
+            _assert_all_finite(X)
+        except BaseException:
+            return False
+        return True
+
+    def _onedal_fit_supported(self, method_name, *data):
+        assert method_name == "fit"
+        assert len(data) == 3
+        X, y, sample_weight = data
+
+        class_name = self.__class__.__name__
+        patching_status = PatchingConditionsChain(
+            f"sklearn.linear_model.{class_name}.fit"
+        )
+
+        normalize_is_set = (
+            hasattr(self, "normalize")
+            and self.normalize
+            and self.normalize != "deprecated"
+        )
+        positive_is_set = hasattr(self, "positive") and self.positive
+
+        n_samples = _num_samples(X)
+        n_features = _num_features(X, fallback_1d=True)
+
+        # Check if equations are well defined
+        is_underdetermined = n_samples < (n_features + int(self.fit_intercept))
+
+        dal_ready = patching_status.and_conditions(
+            [
+                (sample_weight is None, "Sample weight is not supported."),
+                (
+                    not issparse(X) and not issparse(y),
+                    "Sparse input is not supported.",
+                ),
+                (not normalize_is_set, "Normalization is not supported."),
+                (
+                    not positive_is_set,
+                    "Forced positive coefficients are not supported.",
+                ),
+                (
+                    not is_underdetermined,
+                    "The shape of X (fitting) does not satisfy oneDAL requirements:"
+                    "Number of features + 1 >= number of samples.",
+                ),
+            ]
+        )
+        if not dal_ready:
+            return patching_status
+
+        if not patching_status.and_condition(
+            self._test_type_and_finiteness(X), "Input X is not supported."
+        ):
+            return patching_status
+
+        patching_status.and_condition(
+            self._test_type_and_finiteness(y), "Input y is not supported."
+        )
+
+        return patching_status
+
+    def _onedal_predict_supported(self, method_name, *data):
+        assert method_name == "predict"
+        assert len(data) == 1
+
+        class_name = self.__class__.__name__
+        patching_status = PatchingConditionsChain(
+            f"sklearn.linear_model.{class_name}.predict"
+        )
+
+        n_samples = _num_samples(*data)
+        model_is_sparse = issparse(self.coef_) or (
+            self.fit_intercept and issparse(self.intercept_)
+        )
+        dal_ready = patching_status.and_conditions(
+            [
+                (n_samples > 0, "Number of samples is less than 1."),
+                (not issparse(*data), "Sparse input is not supported."),
+                (not model_is_sparse, "Sparse coefficients are not supported."),
+            ]
+        )
+        if not dal_ready:
+            return patching_status
+
+        patching_status.and_condition(
+            self._test_type_and_finiteness(*data), "Input X is not supported."
+        )
+
+        return patching_status
+
+    def _onedal_supported(self, method_name, *data):
+        if method_name == "fit":
+            return self._onedal_fit_supported(method_name, *data)
+        if method_name == "predict":
+            return self._onedal_predict_supported(method_name, *data)
+        raise RuntimeError(f"Unknown method {method_name} in {self.__class__.__name__}")
+
+    _onedal_gpu_supported = _onedal_supported
+    _onedal_cpu_supported = _onedal_supported
+
+    def _initialize_onedal_estimator(self):
+        onedal_params = {"fit_intercept": self.fit_intercept, "copy_X": self.copy_X}
+        self._onedal_estimator = onedal_LinearRegression(**onedal_params)
+
+    def _onedal_fit(self, X, y, sample_weight, queue=None):
+        assert sample_weight is None
+
+        check_params = {
+            "X": X,
+            "y": y,
+            "dtype": [np.float64, np.float32],
+            "accept_sparse": ["csr", "csc", "coo"],
+            "y_numeric": True,
+            "multi_output": True,
+            "force_all_finite": False,
+        }
+        if sklearn_check_version("1.2"):
+            X, y = self._validate_data(**check_params)
+        else:
+            X, y = check_X_y(**check_params)
+
+        if sklearn_check_version("1.0") and not sklearn_check_version("1.2"):
+            self._normalize = _deprecate_normalize(
+                self.normalize,
+                default=False,
+                estimator_name=self.__class__.__name__,
+            )
+
+        self._initialize_onedal_estimator()
+        try:
+            self._onedal_estimator.fit(X, y, queue=queue)
+            self._save_attributes()
+
+        except RuntimeError:
+            logging.getLogger("sklearnex").info(
+                f"{self.__class__.__name__}.fit "
+                + get_patch_message("sklearn_after_onedal")
+            )
+
+            del self._onedal_estimator
+            super().fit(X, y)
+
+    def _onedal_predict(self, X, queue=None):
+        if sklearn_check_version("1.0"):
+            self._check_feature_names(X, reset=False)
+
+        X = self._validate_data(X, accept_sparse=False, reset=False)
+        if not hasattr(self, "_onedal_estimator"):
+            self._initialize_onedal_estimator()
+            self._onedal_estimator.coef_ = self.coef_
+            self._onedal_estimator.intercept_ = self.intercept_
+
+        res = self._onedal_estimator.predict(X, queue=queue)
+        return res
+
+    def get_coef_(self):
+        return self.coef_
+
+    def set_coef_(self, value):
+        self.__dict__["coef_"] = value
+        if hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator.coef_ = value
+            del self._onedal_estimator._onedal_model
+
+    def get_intercept_(self):
+        return self.intercept_
+
+    def set_intercept_(self, value):
+        self.__dict__["intercept_"] = value
+        if hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator.intercept_ = value
+            del self._onedal_estimator._onedal_model
+
+    def _save_attributes(self):
+        self.coef_ = property(self.get_coef_, self.set_coef_)
+        self.intercept_ = property(self.get_intercept_, self.set_intercept_)
+        self.n_features_in_ = self._onedal_estimator.n_features_in_
+        self._sparse = False
+        self.__dict__["coef_"] = self._onedal_estimator.coef_
+        self.__dict__["intercept_"] = self._onedal_estimator.intercept_
+
+    fit.__doc__ = sklearn_LinearRegression.fit.__doc__
+    predict.__doc__ = sklearn_LinearRegression.predict.__doc__

{scikit_learn_intelex-2024.3.0.data → scikit_learn_intelex-2024.5.0.data}/data/Lib/site-packages/sklearnex/linear_model/logistic_regression.py

@@ -38,19 +38,27 @@ if daal_check_version((2024, "P", 1)):
     import numpy as np
     from scipy.sparse import issparse
     from sklearn.linear_model import LogisticRegression as sklearn_LogisticRegression
+    from sklearn.metrics import accuracy_score
+    from sklearn.utils.multiclass import type_of_target
     from sklearn.utils.validation import check_X_y
 
     from daal4py.sklearn._n_jobs_support import control_n_jobs
     from daal4py.sklearn._utils import sklearn_check_version
     from onedal.linear_model import LogisticRegression as onedal_LogisticRegression
-    from onedal.utils import _num_features, _num_samples
+    from onedal.utils import _num_samples
 
     from .._device_offload import dispatch, wrap_output_data
     from .._utils import PatchingConditionsChain, get_patch_message
     from ..utils.validation import _assert_all_finite
 
     @control_n_jobs(
-        decorated_methods=["fit", "predict", "predict_proba", "predict_log_proba"]
+        decorated_methods=[
+            "fit",
+            "predict",
+            "predict_proba",
+            "predict_log_proba",
+            "score",
+        ]
     )
     class LogisticRegression(sklearn_LogisticRegression, BaseLogisticRegression):
         __doc__ = sklearn_LogisticRegression.__doc__
@@ -72,9 +80,9 @@ if daal_check_version((2024, "P", 1)):
             intercept_scaling=1,
             class_weight=None,
             random_state=None,
-            solver="lbfgs" if sklearn_check_version("0.22") else "liblinear",
+            solver="lbfgs",
             max_iter=100,
-            multi_class="auto" if sklearn_check_version("0.22") else "ovr",
+            multi_class="auto",
             verbose=0,
             warm_start=False,
             n_jobs=None,
@@ -160,6 +168,27 @@ if daal_check_version((2024, "P", 1)):
                 X,
             )
 
+        @wrap_output_data
+        def score(self, X, y, sample_weight=None):
+            if sklearn_check_version("1.0"):
+                self._check_feature_names(X, reset=False)
+            return dispatch(
+                self,
+                "score",
+                {
+                    "onedal": self.__class__._onedal_score,
+                    "sklearn": sklearn_LogisticRegression.score,
+                },
+                X,
+                y,
+                sample_weight=sample_weight,
+            )
+
+        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
+            )
+
         def _test_type_and_finiteness(self, X_in):
             X = np.asarray(X_in)
 
@@ -198,6 +227,10 @@ if daal_check_version((2024, "P", 1)):
                     (self.warm_start == False, "Warm start is not supported."),
                     (self.l1_ratio is None, "l1 ratio is not supported."),
                     (sample_weight is None, "Sample weight is not supported."),
+                    (
+                        type_of_target(y) == "binary",
+                        "Only binary classification is supported",
+                    ),
                 ]
             )
 
@@ -216,22 +249,29 @@ if daal_check_version((2024, "P", 1)):
             return patching_status
 
         def _onedal_gpu_predict_supported(self, method_name, *data):
-            assert method_name in ["predict", "predict_proba", "predict_log_proba"]
-            assert len(data) == 1
+            assert method_name in [
+                "predict",
+                "predict_proba",
+                "predict_log_proba",
+                "score",
+            ]
 
             class_name = self.__class__.__name__
             patching_status = PatchingConditionsChain(
                 f"sklearn.linear_model.{class_name}.{method_name}"
             )
 
-            n_samples = _num_samples(*data)
+            n_samples = _num_samples(data[0])
             model_is_sparse = issparse(self.coef_) or (
                 self.fit_intercept and issparse(self.intercept_)
             )
             dal_ready = patching_status.and_conditions(
                 [
                     (n_samples > 0, "Number of samples is less than 1."),
-                    (not issparse(*data), "Sparse input is not supported."),
+                    (
+                        not any([issparse(i) for i in data]),
+                        "Sparse input is not supported.",
+                    ),
                     (not model_is_sparse, "Sparse coefficients are not supported."),
                     (
                         hasattr(self, "_onedal_estimator"),
@@ -251,7 +291,7 @@ if daal_check_version((2024, "P", 1)):
         def _onedal_gpu_supported(self, method_name, *data):
             if method_name == "fit":
                 return self._onedal_gpu_fit_supported(method_name, *data)
-            if method_name in ["predict", "predict_proba", "predict_log_proba"]:
+            if method_name in ["predict", "predict_proba", "predict_log_proba", "score"]:
                 return self._onedal_gpu_predict_supported(method_name, *data)
             raise RuntimeError(
                 f"Unknown method {method_name} in {self.__class__.__name__}"
@@ -334,6 +374,7 @@ if daal_check_version((2024, "P", 1)):
         predict.__doc__ = sklearn_LogisticRegression.predict.__doc__
         predict_proba.__doc__ = sklearn_LogisticRegression.predict_proba.__doc__
         predict_log_proba.__doc__ = sklearn_LogisticRegression.predict_log_proba.__doc__
+        score.__doc__ = sklearn_LogisticRegression.score.__doc__
 
 else:
     LogisticRegression = LogisticRegression_daal4py

scikit_learn_intelex-2024.5.0.data/data/Lib/site-packages/sklearnex/linear_model/tests/test_incremental_linear.py

@@ -0,0 +1,200 @@
+# ===============================================================================
+# 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.
+# ===============================================================================
+
+import numpy as np
+import pytest
+from numpy.testing import assert_allclose
+
+from onedal.tests.utils._dataframes_support import (
+    _as_numpy,
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
+from sklearnex.linear_model import IncrementalLinearRegression
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("fit_intercept", [True, False])
+@pytest.mark.parametrize("macro_block", [None, 1024])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_fit_on_gold_data(dataframe, queue, fit_intercept, macro_block, dtype):
+    X = np.array([[1], [2]])
+    X = X.astype(dtype=dtype)
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y = np.array([1, 2])
+    y = y.astype(dtype=dtype)
+    y_df = _convert_to_dataframe(y, sycl_queue=queue, target_df=dataframe)
+
+    inclin = IncrementalLinearRegression(fit_intercept=fit_intercept)
+    if macro_block is not None:
+        hparams = inclin.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+        hparams.gpu_macro_block = macro_block
+    inclin.fit(X_df, y_df)
+
+    y_pred = inclin.predict(X_df)
+
+    tol = 2e-6 if dtype == np.float32 else 1e-7
+    assert_allclose(inclin.coef_, [1], atol=tol)
+    if fit_intercept:
+        assert_allclose(inclin.intercept_, [0], atol=tol)
+    assert_allclose(_as_numpy(y_pred), y, atol=tol)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("fit_intercept", [True, False])
+@pytest.mark.parametrize("macro_block", [None, 1024])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_partial_fit_on_gold_data(
+    dataframe, queue, fit_intercept, macro_block, dtype
+):
+    X = np.array([[1], [2], [3], [4]])
+    X = X.astype(dtype=dtype)
+    y = X + 3
+    y = y.astype(dtype=dtype)
+    X_split = np.array_split(X, 2)
+    y_split = np.array_split(y, 2)
+
+    inclin = IncrementalLinearRegression()
+    if macro_block is not None:
+        hparams = inclin.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+        hparams.gpu_macro_block = macro_block
+    for i in range(2):
+        X_split_df = _convert_to_dataframe(
+            X_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        y_split_df = _convert_to_dataframe(
+            y_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        inclin.partial_fit(X_split_df, y_split_df)
+
+    assert inclin.n_features_in_ == 1
+    tol = 2e-6 if dtype == np.float32 else 1e-7
+    assert_allclose(inclin.coef_, [[1]], atol=tol)
+    if fit_intercept:
+        assert_allclose(inclin.intercept_, 3, atol=tol)
+
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y_pred = inclin.predict(X_df)
+
+    assert_allclose(_as_numpy(y_pred), y, atol=tol)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("fit_intercept", [True, False])
+@pytest.mark.parametrize("macro_block", [None, 1024])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_partial_fit_multitarget_on_gold_data(
+    dataframe, queue, fit_intercept, macro_block, dtype
+):
+    X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])
+    X = X.astype(dtype=dtype)
+    y = np.dot(X, [1, 2]) + 3
+    y = y.astype(dtype=dtype)
+    X_split = np.array_split(X, 2)
+    y_split = np.array_split(y, 2)
+
+    inclin = IncrementalLinearRegression()
+    if macro_block is not None:
+        hparams = inclin.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+        hparams.gpu_macro_block = macro_block
+    for i in range(2):
+        X_split_df = _convert_to_dataframe(
+            X_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        y_split_df = _convert_to_dataframe(
+            y_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        inclin.partial_fit(X_split_df, y_split_df)
+
+    assert inclin.n_features_in_ == 2
+    tol = 7e-6 if dtype == np.float32 else 1e-7
+    assert_allclose(inclin.coef_, [1.0, 2.0], atol=tol)
+    if fit_intercept:
+        assert_allclose(inclin.intercept_, 3.0, atol=tol)
+
+    X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
+    y_pred = inclin.predict(X_df)
+
+    assert_allclose(_as_numpy(y_pred), y, atol=tol)
+
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+@pytest.mark.parametrize("fit_intercept", [True, False])
+@pytest.mark.parametrize("num_samples", [100, 1000])
+@pytest.mark.parametrize("num_features", [5, 10])
+@pytest.mark.parametrize("num_targets", [1, 2])
+@pytest.mark.parametrize("num_blocks", [1, 10])
+@pytest.mark.parametrize("macro_block", [None, 1024])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+def test_sklearnex_partial_fit_on_random_data(
+    dataframe,
+    queue,
+    fit_intercept,
+    num_samples,
+    num_features,
+    num_targets,
+    num_blocks,
+    macro_block,
+    dtype,
+):
+    seed = 42
+    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)
+    if fit_intercept:
+        y = X @ coef + intercept[np.newaxis, :]
+    else:
+        y = X @ coef
+
+    X_split = np.array_split(X, num_blocks)
+    y_split = np.array_split(y, num_blocks)
+
+    inclin = IncrementalLinearRegression(fit_intercept=fit_intercept)
+    if macro_block is not None:
+        hparams = inclin.get_hyperparameters("fit")
+        hparams.cpu_macro_block = macro_block
+        hparams.gpu_macro_block = macro_block
+    for i in range(num_blocks):
+        X_split_df = _convert_to_dataframe(
+            X_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        y_split_df = _convert_to_dataframe(
+            y_split[i], sycl_queue=queue, target_df=dataframe
+        )
+        inclin.partial_fit(X_split_df, y_split_df)
+
+    tol = 1e-4 if dtype == np.float32 else 1e-7
+    assert_allclose(coef, inclin.coef_.T, atol=tol)
+
+    if fit_intercept:
+        assert_allclose(intercept, inclin.intercept_, atol=tol)
+
+    X_test = gen.random(size=(num_samples, num_features), dtype=dtype)
+    if fit_intercept:
+        expected_y_pred = X_test @ coef + intercept[np.newaxis, :]
+    else:
+        expected_y_pred = X_test @ coef
+
+    X_test_df = _convert_to_dataframe(X_test, sycl_queue=queue, target_df=dataframe)
+
+    y_pred = inclin.predict(X_test_df)
+
+    assert_allclose(expected_y_pred, _as_numpy(y_pred), atol=tol)