scikit-learn-intelex 2024.4.0__py310-none-win_amd64.whl → 2024.6.0__py310-none-win_amd64.whl

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2024.6.0.data}/data/Lib/site-packages/sklearnex/_device_offload.py

@@ -127,8 +127,15 @@ def _transfer_to_host(queue, *data):
                 queue = usm_iface["syclobj"]
 
             buffer = as_usm_memory(item).copy_to_host()
+            order = "C"
+            if usm_iface["strides"] is not None:
+                if usm_iface["strides"][0] < usm_iface["strides"][1]:
+                    order = "F"
             item = np.ndarray(
-                shape=usm_iface["shape"], dtype=usm_iface["typestr"], buffer=buffer
+                shape=usm_iface["shape"],
+                dtype=usm_iface["typestr"],
+                buffer=buffer,
+                order=order,
             )
             has_usm_data = True
         else:

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2024.6.0.data}/data/Lib/site-packages/sklearnex/basic_statistics/tests/test_incremental_basic_statistics.py

@@ -165,7 +165,7 @@ def test_partial_fit_multiple_options_on_random_data(
             expected_sum(X),
         )
 
-    tol = 1e-5 if res_mean.dtype == np.float32 else 1e-7
+    tol = 3e-4 if res_mean.dtype == np.float32 else 1e-7
     assert_allclose(gtr_mean, res_mean, atol=tol)
     assert_allclose(gtr_max, res_max, atol=tol)
     assert_allclose(gtr_sum, res_sum, atol=tol)
@@ -208,7 +208,6 @@ def test_partial_fit_all_option_on_random_data(
 
     for option in options_and_tests:
         result_option, function, tols = option
-        print(result_option)
         fp32tol, fp64tol = tols
         res = getattr(result, result_option)
         if weighted:
@@ -301,7 +300,7 @@ def test_fit_single_option_on_random_data(
 @pytest.mark.parametrize("column_count", [10, 100])
 @pytest.mark.parametrize("weighted", [True, False])
 @pytest.mark.parametrize("dtype", [np.float32, np.float64])
-def test_partial_fit_multiple_options_on_random_data(
+def test_fit_multiple_options_on_random_data(
     dataframe, queue, num_batches, row_count, column_count, weighted, dtype
 ):
     seed = 77
@@ -375,7 +374,6 @@ def test_fit_all_option_on_random_data(
 
     for option in options_and_tests:
         result_option, function, tols = option
-        print(result_option)
         fp32tol, fp64tol = tols
         res = getattr(result, result_option)
         if weighted:

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2024.6.0.data}/data/Lib/site-packages/sklearnex/cluster/dbscan.py

@@ -85,6 +85,9 @@ class DBSCAN(sklearn_DBSCAN, BaseDBSCAN):
         self.n_jobs = n_jobs
 
     def _onedal_fit(self, X, y, sample_weight=None, queue=None):
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(X, force_all_finite=False)
+
         onedal_params = {
             "eps": self.eps,
             "min_samples": self.min_samples,

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2024.6.0.data}/data/Lib/site-packages/sklearnex/cluster/tests/test_dbscan.py

@@ -18,16 +18,18 @@ import numpy as np
 import pytest
 from numpy.testing import assert_allclose
 
+from onedal.tests.utils._dataframes_support import (
+    _convert_to_dataframe,
+    get_dataframes_and_queues,
+)
 
-# TODO:
-# adding this parameterized testing
-# somehow breaks other test with preview module patch:
-# sklearnex/tests/test_monkeypatch.py::test_preview_namespace.
-# @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
-def test_sklearnex_import_dbscan():
+
+@pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
+def test_sklearnex_import_dbscan(dataframe, queue):
     from sklearnex.cluster import DBSCAN
 
     X = np.array([[1, 2], [2, 2], [2, 3], [8, 7], [8, 8], [25, 80]])
+    X = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
     dbscan = DBSCAN(eps=3, min_samples=2).fit(X)
     assert "sklearnex" in dbscan.__module__
 

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2024.6.0.data}/data/Lib/site-packages/sklearnex/conftest.py

@@ -19,7 +19,8 @@ import logging
 
 import pytest
 
-from sklearnex import patch_sklearn, unpatch_sklearn
+from daal4py.sklearn._utils import sklearn_check_version
+from sklearnex import config_context, patch_sklearn, unpatch_sklearn
 
 
 def pytest_configure(config):
@@ -61,3 +62,12 @@ def with_sklearnex():
     patch_sklearn()
     yield
     unpatch_sklearn()
+
+
+@pytest.fixture
+def with_array_api():
+    if sklearn_check_version("1.2"):
+        with config_context(array_api_dispatch=True):
+            yield
+    else:
+        yield

scikit_learn_intelex-2024.6.0.data/data/Lib/site-packages/sklearnex/covariance/incremental_covariance.py

@@ -0,0 +1,317 @@
+# ===============================================================================
+# 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 numbers
+import warnings
+
+import numpy as np
+from scipy import linalg
+from sklearn.base import BaseEstimator
+from sklearn.covariance import EmpiricalCovariance as sklearn_EmpiricalCovariance
+from sklearn.utils import check_array, gen_batches
+
+from daal4py.sklearn._n_jobs_support import control_n_jobs
+from daal4py.sklearn._utils import daal_check_version, sklearn_check_version
+from onedal._device_offload import support_usm_ndarray
+from onedal.covariance import (
+    IncrementalEmpiricalCovariance as onedal_IncrementalEmpiricalCovariance,
+)
+from sklearnex import config_context
+
+from .._device_offload import dispatch, wrap_output_data
+from .._utils import PatchingConditionsChain, register_hyperparameters
+from ..metrics import pairwise_distances
+
+if sklearn_check_version("1.2"):
+    from sklearn.utils._param_validation import Interval
+
+
+@control_n_jobs(decorated_methods=["partial_fit", "fit", "_onedal_finalize_fit"])
+class IncrementalEmpiricalCovariance(BaseEstimator):
+    """
+    Incremental estimator for covariance.
+    Allows to compute empirical covariance estimated by maximum
+    likelihood method if data are splitted into batches.
+
+    Parameters
+    ----------
+    store_precision : bool, default=False
+        Specifies if the estimated precision is stored.
+
+    assume_centered : bool, default=False
+        If True, data are not centered before computation.
+        Useful when working with data whose mean is almost, but not exactly
+        zero.
+        If False (default), data are centered before computation.
+
+    batch_size : int, default=None
+        The number of samples to use for each batch. Only used when calling
+        ``fit``. If ``batch_size`` is ``None``, then ``batch_size``
+        is inferred from the data and set to ``5 * n_features``, to provide a
+        balance between approximation accuracy and memory consumption.
+
+    copy : bool, default=True
+        If False, X will be overwritten. ``copy=False`` can be used to
+        save memory but is unsafe for general use.
+
+    Attributes
+    ----------
+    location_ : ndarray of shape (n_features,)
+        Estimated location, i.e. the estimated mean.
+
+    covariance_ : ndarray of shape (n_features, n_features)
+        Estimated covariance matrix
+
+    n_samples_seen_ : int
+        The number of samples processed by the estimator. Will be reset on
+        new calls to fit, but increments across ``partial_fit`` calls.
+
+    batch_size_ : int
+        Inferred batch size from ``batch_size``.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit` `partial_fit`.
+    """
+
+    _onedal_incremental_covariance = staticmethod(onedal_IncrementalEmpiricalCovariance)
+
+    if sklearn_check_version("1.2"):
+        _parameter_constraints: dict = {
+            "store_precision": ["boolean"],
+            "assume_centered": ["boolean"],
+            "batch_size": [Interval(numbers.Integral, 1, None, closed="left"), None],
+            "copy": ["boolean"],
+        }
+
+    get_precision = sklearn_EmpiricalCovariance.get_precision
+    error_norm = wrap_output_data(sklearn_EmpiricalCovariance.error_norm)
+    score = wrap_output_data(sklearn_EmpiricalCovariance.score)
+
+    def __init__(
+        self, *, store_precision=False, assume_centered=False, batch_size=None, copy=True
+    ):
+        self.assume_centered = assume_centered
+        self.store_precision = store_precision
+        self.batch_size = batch_size
+        self.copy = copy
+
+    def _onedal_supported(self, method_name, *data):
+        patching_status = PatchingConditionsChain(
+            f"sklearn.covariance.{self.__class__.__name__}.{method_name}"
+        )
+        return patching_status
+
+    def _onedal_finalize_fit(self):
+        assert hasattr(self, "_onedal_estimator")
+        self._onedal_estimator.finalize_fit()
+        self._need_to_finalize = False
+
+        if not daal_check_version((2024, "P", 400)) and self.assume_centered:
+            location = self._onedal_estimator.location_[None, :]
+            self._onedal_estimator.covariance_ += np.dot(location.T, location)
+            self._onedal_estimator.location_ = np.zeros_like(np.squeeze(location))
+        if self.store_precision:
+            self.precision_ = linalg.pinvh(
+                self._onedal_estimator.covariance_, check_finite=False
+            )
+        else:
+            self.precision_ = None
+
+    @property
+    def covariance_(self):
+        if hasattr(self, "_onedal_estimator"):
+            if self._need_to_finalize:
+                self._onedal_finalize_fit()
+            return self._onedal_estimator.covariance_
+        else:
+            raise AttributeError(
+                f"'{self.__class__.__name__}' object has no attribute 'covariance_'"
+            )
+
+    @property
+    def location_(self):
+        if hasattr(self, "_onedal_estimator"):
+            if self._need_to_finalize:
+                self._onedal_finalize_fit()
+            return self._onedal_estimator.location_
+        else:
+            raise AttributeError(
+                f"'{self.__class__.__name__}' object has no attribute 'location_'"
+            )
+
+    def _onedal_partial_fit(self, X, queue=None, check_input=True):
+
+        first_pass = not hasattr(self, "n_samples_seen_") or self.n_samples_seen_ == 0
+
+        # finite check occurs on onedal side
+        if check_input:
+            if sklearn_check_version("1.2"):
+                self._validate_params()
+
+            if sklearn_check_version("1.0"):
+                X = self._validate_data(
+                    X,
+                    dtype=[np.float64, np.float32],
+                    reset=first_pass,
+                    copy=self.copy,
+                    force_all_finite=False,
+                )
+            else:
+                X = check_array(
+                    X,
+                    dtype=[np.float64, np.float32],
+                    copy=self.copy,
+                    force_all_finite=False,
+                )
+
+        onedal_params = {
+            "method": "dense",
+            "bias": True,
+            "assume_centered": self.assume_centered,
+        }
+        if not hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator = self._onedal_incremental_covariance(**onedal_params)
+        try:
+            if first_pass:
+                self.n_samples_seen_ = X.shape[0]
+                self.n_features_in_ = X.shape[1]
+            else:
+                self.n_samples_seen_ += X.shape[0]
+
+            self._onedal_estimator.partial_fit(X, queue)
+        finally:
+            self._need_to_finalize = True
+
+        return self
+
+    def partial_fit(self, X, y=None, check_input=True):
+        """
+        Incremental fit with X. All of X is processed as a single batch.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        check_input : bool, default=True
+            Run check_array on X.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        return dispatch(
+            self,
+            "partial_fit",
+            {
+                "onedal": self.__class__._onedal_partial_fit,
+                "sklearn": None,
+            },
+            X,
+            check_input=check_input,
+        )
+
+    def fit(self, X, y=None):
+        """
+        Fit the model with X, using minibatches of size batch_size.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+
+        return dispatch(
+            self,
+            "fit",
+            {
+                "onedal": self.__class__._onedal_fit,
+                "sklearn": None,
+            },
+            X,
+        )
+
+    def _onedal_fit(self, X, queue=None):
+        self.n_samples_seen_ = 0
+        if hasattr(self, "_onedal_estimator"):
+            self._onedal_estimator._reset()
+
+        if sklearn_check_version("1.2"):
+            self._validate_params()
+
+        # finite check occurs on onedal side
+        if sklearn_check_version("1.0"):
+            X = self._validate_data(
+                X, dtype=[np.float64, np.float32], copy=self.copy, force_all_finite=False
+            )
+        else:
+            X = check_array(
+                X, dtype=[np.float64, np.float32], copy=self.copy, force_all_finite=False
+            )
+            self.n_features_in_ = X.shape[1]
+
+        self.batch_size_ = self.batch_size if self.batch_size else 5 * self.n_features_in_
+
+        if X.shape[0] == 1:
+            warnings.warn(
+                "Only one sample available. You may want to reshape your data array"
+            )
+
+        for batch in gen_batches(X.shape[0], self.batch_size_):
+            X_batch = X[batch]
+            self._onedal_partial_fit(X_batch, queue=queue, check_input=False)
+
+        self._onedal_finalize_fit()
+
+        return self
+
+    # expose sklearnex pairwise_distances if mahalanobis distance eventually supported
+    @wrap_output_data
+    def mahalanobis(self, X):
+        if sklearn_check_version("1.0"):
+            self._validate_data(X, reset=False, copy=self.copy)
+        else:
+            check_array(X, copy=self.copy)
+
+        precision = self.get_precision()
+        with config_context(assume_finite=True):
+            # compute mahalanobis distances
+            dist = pairwise_distances(
+                X, self.location_[np.newaxis, :], metric="mahalanobis", VI=precision
+            )
+
+        return np.reshape(dist, (len(X),)) ** 2
+
+    _onedal_cpu_supported = _onedal_supported
+    _onedal_gpu_supported = _onedal_supported
+
+    mahalanobis.__doc__ = sklearn_EmpiricalCovariance.mahalanobis.__doc__
+    error_norm.__doc__ = sklearn_EmpiricalCovariance.error_norm.__doc__
+    score.__doc__ = sklearn_EmpiricalCovariance.score.__doc__

{scikit_learn_intelex-2024.4.0.data → scikit_learn_intelex-2024.6.0.data}/data/Lib/site-packages/sklearnex/covariance/tests/test_incremental_covariance.py

@@ -17,6 +17,10 @@
 import numpy as np
 import pytest
 from numpy.testing import assert_allclose
+from sklearn.covariance.tests.test_covariance import (
+    test_covariance,
+    test_EmpiricalCovariance_validates_mahalanobis,
+)
 
 from onedal.tests.utils._dataframes_support import (
     _convert_to_dataframe,
@@ -26,13 +30,14 @@ from onedal.tests.utils._dataframes_support import (
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
 @pytest.mark.parametrize("dtype", [np.float32, np.float64])
-def test_sklearnex_partial_fit_on_gold_data(dataframe, queue, dtype):
+@pytest.mark.parametrize("assume_centered", [True, False])
+def test_sklearnex_partial_fit_on_gold_data(dataframe, queue, dtype, assume_centered):
     from sklearnex.covariance import IncrementalEmpiricalCovariance
 
     X = np.array([[0, 1], [0, 1]])
     X = X.astype(dtype)
     X_split = np.array_split(X, 2)
-    inccov = IncrementalEmpiricalCovariance()
+    inccov = IncrementalEmpiricalCovariance(assume_centered=assume_centered)
 
     for i in range(2):
         X_split_df = _convert_to_dataframe(
@@ -40,8 +45,12 @@ def test_sklearnex_partial_fit_on_gold_data(dataframe, queue, dtype):
         )
         result = inccov.partial_fit(X_split_df)
 
-    expected_covariance = np.array([[0, 0], [0, 0]])
-    expected_means = np.array([0, 1])
+    if assume_centered:
+        expected_covariance = np.array([[0, 0], [0, 1]])
+        expected_means = np.array([0, 0])
+    else:
+        expected_covariance = np.array([[0, 0], [0, 0]])
+        expected_means = np.array([0, 1])
 
     assert_allclose(expected_covariance, result.covariance_)
     assert_allclose(expected_means, result.location_)
@@ -49,7 +58,7 @@ def test_sklearnex_partial_fit_on_gold_data(dataframe, queue, dtype):
     X = np.array([[1, 2], [3, 6]])
     X = X.astype(dtype)
     X_split = np.array_split(X, 2)
-    inccov = IncrementalEmpiricalCovariance()
+    inccov = IncrementalEmpiricalCovariance(assume_centered=assume_centered)
 
     for i in range(2):
         X_split_df = _convert_to_dataframe(
@@ -57,8 +66,12 @@ def test_sklearnex_partial_fit_on_gold_data(dataframe, queue, dtype):
         )
         result = inccov.partial_fit(X_split_df)
 
-    expected_covariance = np.array([[1, 2], [2, 4]])
-    expected_means = np.array([2, 4])
+    if assume_centered:
+        expected_covariance = np.array([[5, 10], [10, 20]])
+        expected_means = np.array([0, 0])
+    else:
+        expected_covariance = np.array([[1, 2], [2, 4]])
+        expected_means = np.array([2, 4])
 
     assert_allclose(expected_covariance, result.covariance_)
     assert_allclose(expected_means, result.location_)
@@ -87,9 +100,9 @@ def test_sklearnex_fit_on_gold_data(dataframe, queue, batch_size, dtype):
 
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
-@pytest.mark.parametrize("num_batches", [2, 4, 6, 8, 10])
-@pytest.mark.parametrize("row_count", [100, 1000, 2000])
-@pytest.mark.parametrize("column_count", [10, 100, 200])
+@pytest.mark.parametrize("num_batches", [2, 10])
+@pytest.mark.parametrize("row_count", [100, 1000])
+@pytest.mark.parametrize("column_count", [10, 100])
 @pytest.mark.parametrize("dtype", [np.float32, np.float64])
 def test_sklearnex_partial_fit_on_random_data(
     dataframe, queue, num_batches, row_count, column_count, dtype
@@ -117,12 +130,13 @@ def test_sklearnex_partial_fit_on_random_data(
 
 
 @pytest.mark.parametrize("dataframe,queue", get_dataframes_and_queues())
-@pytest.mark.parametrize("num_batches", [2, 4, 6, 8, 10])
-@pytest.mark.parametrize("row_count", [100, 1000, 2000])
-@pytest.mark.parametrize("column_count", [10, 100, 200])
+@pytest.mark.parametrize("num_batches", [2, 10])
+@pytest.mark.parametrize("row_count", [100, 1000])
+@pytest.mark.parametrize("column_count", [10, 100])
 @pytest.mark.parametrize("dtype", [np.float32, np.float64])
+@pytest.mark.parametrize("assume_centered", [True, False])
 def test_sklearnex_fit_on_random_data(
-    dataframe, queue, num_batches, row_count, column_count, dtype
+    dataframe, queue, num_batches, row_count, column_count, dtype, assume_centered
 ):
     from sklearnex.covariance import IncrementalEmpiricalCovariance
 
@@ -132,12 +146,35 @@ def test_sklearnex_fit_on_random_data(
     X = X.astype(dtype)
     X_df = _convert_to_dataframe(X, sycl_queue=queue, target_df=dataframe)
     batch_size = row_count // num_batches
-    inccov = IncrementalEmpiricalCovariance(batch_size=batch_size)
+    inccov = IncrementalEmpiricalCovariance(
+        batch_size=batch_size, assume_centered=assume_centered
+    )
 
     result = inccov.fit(X_df)
 
-    expected_covariance = np.cov(X.T, bias=1)
-    expected_means = np.mean(X, axis=0)
+    if assume_centered:
+        expected_covariance = np.dot(X.T, X) / X.shape[0]
+        expected_means = np.zeros_like(X[0])
+    else:
+        expected_covariance = np.cov(X.T, bias=1)
+        expected_means = np.mean(X, axis=0)
 
     assert_allclose(expected_covariance, result.covariance_, atol=1e-6)
     assert_allclose(expected_means, result.location_, atol=1e-6)
+
+
+# Monkeypatch IncrementalEmpiricalCovariance into relevant sklearn.covariance tests
+@pytest.mark.allow_sklearn_fallback
+@pytest.mark.parametrize(
+    "sklearn_test",
+    [
+        test_covariance,
+        test_EmpiricalCovariance_validates_mahalanobis,
+    ],
+)
+def test_IncrementalEmpiricalCovariance_against_sklearn(monkeypatch, sklearn_test):
+    from sklearnex.covariance import IncrementalEmpiricalCovariance
+
+    class_name = ".".join([sklearn_test.__module__, "EmpiricalCovariance"])
+    monkeypatch.setattr(class_name, IncrementalEmpiricalCovariance)
+    sklearn_test()