scikit-learn-intelex 2025.1.0__py310-none-manylinux_2_28_x86_64.whl

onedal/utils/validation.py

@@ -0,0 +1,440 @@
+# ==============================================================================
+# 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 warnings
+from collections.abc import Sequence
+from numbers import Integral
+
+import numpy as np
+from scipy import sparse as sp
+
+if np.lib.NumpyVersion(np.__version__) >= np.lib.NumpyVersion("2.0.0a0"):
+    # numpy_version >= 2.0
+    from numpy.exceptions import VisibleDeprecationWarning
+else:
+    # numpy_version < 2.0
+    from numpy import VisibleDeprecationWarning
+
+from sklearn.preprocessing import LabelEncoder
+from sklearn.utils.validation import check_array
+
+from daal4py.sklearn.utils.validation import _assert_all_finite
+
+
+class DataConversionWarning(UserWarning):
+    """Warning used to notify implicit data conversions happening in the code."""
+
+
+def _is_arraylike(x):
+    """Returns whether the input is array-like."""
+    return hasattr(x, "__len__") or hasattr(x, "shape") or hasattr(x, "__array__")
+
+
+def _is_arraylike_not_scalar(array):
+    """Return True if array is array-like and not a scalar"""
+    return _is_arraylike(array) and not np.isscalar(array)
+
+
+def _column_or_1d(y, warn=False):
+    y = np.asarray(y)
+
+    # TODO: Convert this kind of arrays to a table like in daal4py
+    if not y.flags.aligned and not y.flags.writeable:
+        y = np.array(y.tolist())
+
+    shape = np.shape(y)
+    if len(shape) == 1:
+        return np.ravel(y)
+    if len(shape) == 2 and shape[1] == 1:
+        if warn:
+            warnings.warn(
+                "A column-vector y was passed when a 1d array was"
+                " expected. Please change the shape of y to "
+                "(n_samples, ), for example using ravel().",
+                DataConversionWarning,
+                stacklevel=2,
+            )
+        return np.ravel(y)
+
+    raise ValueError(
+        "y should be a 1d array, " "got an array of shape {} instead.".format(shape)
+    )
+
+
+def _compute_class_weight(class_weight, classes, y):
+    if set(y) - set(classes):
+        raise ValueError("classes should include all valid labels that can " "be in y")
+    if class_weight is None or len(class_weight) == 0:
+        weight = np.ones(classes.shape[0], dtype=np.float64, order="C")
+    elif class_weight == "balanced":
+        y_ = _column_or_1d(y)
+        classes, _ = np.unique(y_, return_inverse=True)
+
+        le = LabelEncoder()
+        y_ind = le.fit_transform(y_)
+        if not all(np.in1d(classes, le.classes_)):
+            raise ValueError("classes should have valid labels that are in y")
+
+        y_bin = np.bincount(y_ind).astype(np.float64)
+        weight = len(y_) / (len(le.classes_) * y_bin)
+    else:
+        # user-defined dictionary
+        weight = np.ones(classes.shape[0], dtype=np.float64, order="C")
+        if not isinstance(class_weight, dict):
+            raise ValueError(
+                "class_weight must be dict, 'balanced', or None,"
+                " got: %r" % class_weight
+            )
+        for c in class_weight:
+            i = np.searchsorted(classes, c)
+            if i >= len(classes) or classes[i] != c:
+                raise ValueError("Class label {} not present.".format(c))
+            weight[i] = class_weight[c]
+
+    return weight
+
+
+def _validate_targets(y, class_weight, dtype):
+    y_ = _column_or_1d(y, warn=True)
+    _check_classification_targets(y)
+    classes, y = np.unique(y_, return_inverse=True)
+    class_weight_res = _compute_class_weight(class_weight, classes=classes, y=y_)
+
+    if len(classes) < 2:
+        raise ValueError(
+            "The number of classes has to be greater than one; got %d"
+            " class" % len(classes)
+        )
+
+    return np.asarray(y, dtype=dtype, order="C"), class_weight_res, classes
+
+
+def _check_array(
+    array,
+    dtype="numeric",
+    accept_sparse=False,
+    order=None,
+    copy=False,
+    force_all_finite=True,
+    ensure_2d=True,
+    accept_large_sparse=True,
+):
+    if force_all_finite:
+        if sp.issparse(array):
+            if hasattr(array, "data"):
+                _assert_all_finite(array.data)
+                force_all_finite = False
+        else:
+            _assert_all_finite(array)
+            force_all_finite = False
+    array = check_array(
+        array=array,
+        dtype=dtype,
+        accept_sparse=accept_sparse,
+        order=order,
+        copy=copy,
+        force_all_finite=force_all_finite,
+        ensure_2d=ensure_2d,
+        accept_large_sparse=accept_large_sparse,
+    )
+
+    if sp.issparse(array):
+        return array
+
+    # TODO: Convert this kind of arrays to a table like in daal4py
+    if not array.flags.aligned and not array.flags.writeable:
+        array = np.array(array.tolist())
+
+    # TODO: If data is not contiguous copy to contiguous
+    # Need implemeted numpy table in oneDAL
+    if not array.flags.c_contiguous and not array.flags.f_contiguous:
+        array = np.ascontiguousarray(array, array.dtype)
+    return array
+
+
+def _check_X_y(
+    X,
+    y,
+    dtype="numeric",
+    accept_sparse=False,
+    order=None,
+    copy=False,
+    force_all_finite=True,
+    ensure_2d=True,
+    accept_large_sparse=True,
+    y_numeric=False,
+    accept_2d_y=False,
+):
+    if y is None:
+        raise ValueError("y cannot be None")
+
+    X = _check_array(
+        X,
+        accept_sparse=accept_sparse,
+        dtype=dtype,
+        order=order,
+        copy=copy,
+        force_all_finite=force_all_finite,
+        ensure_2d=ensure_2d,
+        accept_large_sparse=accept_large_sparse,
+    )
+
+    if not accept_2d_y:
+        y = _column_or_1d(y, warn=True)
+    else:
+        y = np.ascontiguousarray(y)
+
+    if y_numeric and y.dtype.kind == "O":
+        y = y.astype(np.float64)
+    if force_all_finite:
+        _assert_all_finite(y)
+
+    lengths = [X.shape[0], y.shape[0]]
+    uniques = np.unique(lengths)
+    if len(uniques) > 1:
+        raise ValueError(
+            "Found input variables with inconsistent numbers of"
+            " samples: %r" % [int(length) for length in lengths]
+        )
+
+    return X, y
+
+
+def _check_classification_targets(y):
+    y_type = _type_of_target(y)
+    if y_type not in [
+        "binary",
+        "multiclass",
+        "multiclass-multioutput",
+        "multilabel-indicator",
+        "multilabel-sequences",
+    ]:
+        raise ValueError("Unknown label type: %r" % y_type)
+
+
+def _type_of_target(y):
+    is_sequence, is_array = isinstance(y, Sequence), hasattr(y, "__array__")
+    is_not_string, is_sparse = not isinstance(y, str), sp.issparse(y)
+    valid = (is_sequence or is_array or is_sparse) and is_not_string
+
+    if not valid:
+        raise ValueError(
+            "Expected array-like (array or non-string sequence), " "got %r" % y
+        )
+
+    sparse_pandas = y.__class__.__name__ in ["SparseSeries", "SparseArray"]
+    if sparse_pandas:
+        raise ValueError("y cannot be class 'SparseSeries' or 'SparseArray'")
+
+    if _is_multilabel(y):
+        return "multilabel-indicator"
+
+    # DeprecationWarning will be replaced by ValueError, see NEP 34
+    # https://numpy.org/neps/nep-0034-infer-dtype-is-object.html
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", VisibleDeprecationWarning)
+        try:
+            y = np.asarray(y)
+        except VisibleDeprecationWarning:
+            # dtype=object should be provided explicitly for ragged arrays,
+            # see NEP 34
+            y = np.asarray(y, dtype=object)
+
+    # The old sequence of sequences format
+    try:
+        if (
+            not hasattr(y[0], "__array__")
+            and isinstance(y[0], Sequence)
+            and not isinstance(y[0], str)
+        ):
+            raise ValueError(
+                "You appear to be using a legacy multi-label data"
+                " representation. Sequence of sequences are no"
+                " longer supported; use a binary array or sparse"
+                " matrix instead - the MultiLabelBinarizer"
+                " transformer can convert to this format."
+            )
+    except IndexError:
+        pass
+
+    # Invalid inputs
+    if y.ndim > 2 or (y.dtype == object and len(y) and not isinstance(y.flat[0], str)):
+        return "unknown"  # [[[1, 2]]] or [obj_1] and not ["label_1"]
+
+    if y.ndim == 2 and y.shape[1] == 0:
+        return "unknown"  # [[]]
+
+    if y.ndim == 2 and y.shape[1] > 1:
+        suffix = "-multioutput"  # [[1, 2], [1, 2]]
+    else:
+        suffix = ""  # [1, 2, 3] or [[1], [2], [3]]
+
+    # check float and contains non-integer float values
+    if y.dtype.kind == "f" and np.any(y != y.astype(int)):
+        # [.1, .2, 3] or [[.1, .2, 3]] or [[1., .2]] and not [1., 2., 3.]
+        _assert_all_finite(y)
+        return "continuous" + suffix
+
+    if (len(np.unique(y)) > 2) or (y.ndim >= 2 and len(y[0]) > 1):
+        return "multiclass" + suffix  # [1, 2, 3] or [[1., 2., 3]] or [[1, 2]]
+    return "binary"  # [1, 2] or [["a"], ["b"]]
+
+
+def _is_integral_float(y):
+    return y.dtype.kind == "f" and np.all(y.astype(int) == y)
+
+
+def _is_multilabel(y):
+    if hasattr(y, "__array__") or isinstance(y, Sequence):
+        # DeprecationWarning will be replaced by ValueError, see NEP 34
+        # https://numpy.org/neps/nep-0034-infer-dtype-is-object.html
+        with warnings.catch_warnings():
+            warnings.simplefilter("error", VisibleDeprecationWarning)
+            try:
+                y = np.asarray(y)
+            except VisibleDeprecationWarning:
+                # dtype=object should be provided explicitly for ragged arrays,
+                # see NEP 34
+                y = np.array(y, dtype=object)
+
+    if not (hasattr(y, "shape") and y.ndim == 2 and y.shape[1] > 1):
+        return False
+
+    if sp.issparse(y):
+        if isinstance(y, (sp.dok_matrix, sp.lil_matrix)):
+            y = y.tocsr()
+        return (
+            len(y.data) == 0
+            or np.unique(y.data).size == 1
+            and (y.dtype.kind in "biu" or _is_integral_float(np.unique(y.data)))
+        )
+    labels = np.unique(y)
+
+    return len(labels) < 3 and (y.dtype.kind in "biu" or _is_integral_float(labels))
+
+
+def _check_n_features(self, X, reset):
+    try:
+        n_features = _num_features(X)
+    except TypeError as e:
+        if not reset and hasattr(self, "n_features_in_"):
+            raise ValueError(
+                "X does not contain any features, but "
+                f"{self.__class__.__name__} is expecting "
+                f"{self.n_features_in_} features"
+            ) from e
+        # If the number of features is not defined and reset=True,
+        # then we skip this check
+        return
+
+    if reset:
+        self.n_features_in_ = n_features
+        return
+
+    if not hasattr(self, "n_features_in_"):
+        # Skip this check if the expected number of expected input features
+        # was not recorded by calling fit first. This is typically the case
+        # for stateless transformers.
+        return
+
+    if n_features != self.n_features_in_:
+        raise ValueError(
+            f"X has {n_features} features, but {self.__class__.__name__} "
+            f"is expecting {self.n_features_in_} features as input."
+        )
+
+
+def _num_features(X, fallback_1d=False):
+    if X is None:
+        raise ValueError("Expected array-like (array or non-string sequence), got None")
+    type_ = type(X)
+    if type_.__module__ == "builtins":
+        type_name = type_.__qualname__
+    else:
+        type_name = f"{type_.__module__}.{type_.__qualname__}"
+    message = "Unable to find the number of features from X of type " f"{type_name}"
+    if not hasattr(X, "__len__") and not hasattr(X, "shape"):
+        if not hasattr(X, "__array__"):
+            raise ValueError(message)
+        # Only convert X to a numpy array if there is no cheaper, heuristic
+        # option.
+        X = np.asarray(X)
+
+    if hasattr(X, "shape"):
+        ndim_thr = 1 if fallback_1d else 2
+        if not hasattr(X.shape, "__len__") or len(X.shape) < ndim_thr:
+            message += f" with shape {X.shape}"
+            raise ValueError(message)
+        if len(X.shape) <= 1:
+            return 1
+        else:
+            return X.shape[-1]
+
+    try:
+        first_sample = X[0]
+    except IndexError:
+        raise ValueError("Passed empty data.")
+
+    # Do not consider an array-like of strings or dicts to be a 2D array
+    if isinstance(first_sample, (str, bytes, dict)):
+        message += f" where the samples are of type " f"{type(first_sample).__qualname__}"
+        raise ValueError(message)
+
+    try:
+        # If X is a list of lists, for instance, we assume that all nested
+        # lists have the same length without checking or converting to
+        # a numpy array to keep this function call as cheap as possible.
+        if (not fallback_1d) or hasattr(first_sample, "__len__"):
+            return len(first_sample)
+        else:
+            return 1
+    except Exception as err:
+        raise ValueError(message) from err
+
+
+def _num_samples(x):
+    message = "Expected sequence or array-like, got %s" % type(x)
+    if hasattr(x, "fit") and callable(x.fit):
+        # Don't get num_samples from an ensembles length!
+        raise TypeError(message)
+
+    if not hasattr(x, "__len__") and not hasattr(x, "shape"):
+        if hasattr(x, "__array__"):
+            x = np.asarray(x)
+        else:
+            raise TypeError(message)
+
+    if hasattr(x, "shape") and x.shape is not None:
+        if len(x.shape) == 0:
+            raise TypeError(
+                "Singleton array %r cannot be considered a valid collection." % x
+            )
+    # Check that shape is returning an integer or default to len
+    # Dask dataframes may not return numeric shape[0] value
+    if hasattr(x, "shape") and isinstance(x.shape[0], Integral):
+        return x.shape[0]
+
+    try:
+        return len(x)
+    except TypeError as type_error:
+        raise TypeError(message) from type_error
+
+
+def _is_csr(x):
+    """Return True if x is scipy.sparse.csr_matrix or scipy.sparse.csr_array"""
+    return isinstance(x, sp.csr_matrix) or (
+        hasattr(sp, "csr_array") and isinstance(x, sp.csr_array)
+    )

scikit_learn_intelex-2025.1.0.dist-info/LICENSE.txt

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+  "License" shall mean the terms and conditions for use, reproduction,
+  and distribution as defined by Sections 1 through 9 of this document.
+
+  "Licensor" shall mean the copyright owner or entity authorized by
+  the copyright owner that is granting the License.
+
+  "Legal Entity" shall mean the union of the acting entity and all
+  other entities that control, are controlled by, or are under common
+  control with that entity. For the purposes of this definition,
+  "control" means (i) the power, direct or indirect, to cause the
+  direction or management of such entity, whether by contract or
+  otherwise, or (ii) ownership of fifty percent (50%) or more of the
+  outstanding shares, or (iii) beneficial ownership of such entity.
+
+  "You" (or "Your") shall mean an individual or Legal Entity
+  exercising permissions granted by this License.
+
+  "Source" form shall mean the preferred form for making modifications,
+  including but not limited to software source code, documentation
+  source, and configuration files.
+
+  "Object" form shall mean any form resulting from mechanical
+  transformation or translation of a Source form, including but
+  not limited to compiled object code, generated documentation,
+  and conversions to other media types.
+
+  "Work" shall mean the work of authorship, whether in Source or
+  Object form, made available under the License, as indicated by a
+  copyright notice that is included in or attached to the work
+  (an example is provided in the Appendix below).
+
+  "Derivative Works" shall mean any work, whether in Source or Object
+  form, that is based on (or derived from) the Work and for which the
+  editorial revisions, annotations, elaborations, or other modifications
+  represent, as a whole, an original work of authorship. For the purposes
+  of this License, Derivative Works shall not include works that remain
+  separable from, or merely link (or bind by name) to the interfaces of,
+  the Work and Derivative Works thereof.
+
+  "Contribution" shall mean any work of authorship, including
+  the original version of the Work and any modifications or additions
+  to that Work or Derivative Works thereof, that is intentionally
+  submitted to Licensor for inclusion in the Work by the copyright owner
+  or by an individual or Legal Entity authorized to submit on behalf of
+  the copyright owner. For the purposes of this definition, "submitted"
+  means any form of electronic, verbal, or written communication sent
+  to the Licensor or its representatives, including but not limited to
+  communication on electronic mailing lists, source code control systems,
+  and issue tracking systems that are managed by, or on behalf of, the
+  Licensor for the purpose of discussing and improving the Work, but
+  excluding communication that is conspicuously marked or otherwise
+  designated in writing by the copyright owner as "Not a Contribution."
+
+  "Contributor" shall mean Licensor and any individual or Legal Entity
+  on behalf of whom a Contribution has been received by Licensor and
+  subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+  this License, each Contributor hereby grants to You a perpetual,
+  worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+  copyright license to reproduce, prepare Derivative Works of,
+  publicly display, publicly perform, sublicense, and distribute the
+  Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+  this License, each Contributor hereby grants to You a perpetual,
+  worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+  (except as stated in this section) patent license to make, have made,
+  use, offer to sell, sell, import, and otherwise transfer the Work,
+  where such license applies only to those patent claims licensable
+  by such Contributor that are necessarily infringed by their
+  Contribution(s) alone or by combination of their Contribution(s)
+  with the Work to which such Contribution(s) was submitted. If You
+  institute patent litigation against any entity (including a
+  cross-claim or counterclaim in a lawsuit) alleging that the Work
+  or a Contribution incorporated within the Work constitutes direct
+  or contributory patent infringement, then any patent licenses
+  granted to You under this License for that Work shall terminate
+  as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+  Work or Derivative Works thereof in any medium, with or without
+  modifications, and in Source or Object form, provided that You
+  meet the following conditions:
+
+  (a) You must give any other recipients of the Work or
+      Derivative Works a copy of this License; and
+
+  (b) You must cause any modified files to carry prominent notices
+      stating that You changed the files; and
+
+  (c) You must retain, in the Source form of any Derivative Works
+      that You distribute, all copyright, patent, trademark, and
+      attribution notices from the Source form of the Work,
+      excluding those notices that do not pertain to any part of
+      the Derivative Works; and
+
+  (d) If the Work includes a "NOTICE" text file as part of its
+      distribution, then any Derivative Works that You distribute must
+      include a readable copy of the attribution notices contained
+      within such NOTICE file, excluding those notices that do not
+      pertain to any part of the Derivative Works, in at least one
+      of the following places: within a NOTICE text file distributed
+      as part of the Derivative Works; within the Source form or
+      documentation, if provided along with the Derivative Works; or,
+      within a display generated by the Derivative Works, if and
+      wherever such third-party notices normally appear. The contents
+      of the NOTICE file are for informational purposes only and
+      do not modify the License. You may add Your own attribution
+      notices within Derivative Works that You distribute, alongside
+      or as an addendum to the NOTICE text from the Work, provided
+      that such additional attribution notices cannot be construed
+      as modifying the License.
+
+  You may add Your own copyright statement to Your modifications and
+  may provide additional or different license terms and conditions
+  for use, reproduction, or distribution of Your modifications, or
+  for any such Derivative Works as a whole, provided Your use,
+  reproduction, and distribution of the Work otherwise complies with
+  the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+  any Contribution intentionally submitted for inclusion in the Work
+  by You to the Licensor shall be under the terms and conditions of
+  this License, without any additional terms or conditions.
+  Notwithstanding the above, nothing herein shall supersede or modify
+  the terms of any separate license agreement you may have executed
+  with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+  names, trademarks, service marks, or product names of the Licensor,
+  except as required for reasonable and customary use in describing the
+  origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+  agreed to in writing, Licensor provides the Work (and each
+  Contributor provides its Contributions) on an "AS IS" BASIS,
+  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+  implied, including, without limitation, any warranties or conditions
+  of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+  PARTICULAR PURPOSE. You are solely responsible for determining the
+  appropriateness of using or redistributing the Work and assume any
+  risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+  whether in tort (including negligence), contract, or otherwise,
+  unless required by applicable law (such as deliberate and grossly
+  negligent acts) or agreed to in writing, shall any Contributor be
+  liable to You for damages, including any direct, indirect, special,
+  incidental, or consequential damages of any character arising as a
+  result of this License or out of the use or inability to use the
+  Work (including but not limited to damages for loss of goodwill,
+  work stoppage, computer failure or malfunction, or any and all
+  other commercial damages or losses), even if such Contributor
+  has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+  the Work or Derivative Works thereof, You may choose to offer,
+  and charge a fee for, acceptance of support, warranty, indemnity,
+  or other liability obligations and/or rights consistent with this
+  License. However, in accepting such obligations, You may act only
+  on Your own behalf and on Your sole responsibility, not on behalf
+  of any other Contributor, and only if You agree to indemnify,
+  defend, and hold each Contributor harmless for any liability
+  incurred by, or claims asserted against, such Contributor by reason
+  of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
+
+ APPENDIX: How to apply the Apache License to your work.
+
+  To apply the Apache License to your work, attach the following
+  boilerplate notice, with the fields enclosed by brackets "[]"
+  replaced with your own identifying information. (Don't include
+  the brackets!)  The text should be enclosed in the appropriate
+  comment syntax for the file format. We also recommend that a
+  file or class name and description of purpose be included on the
+  same "printed page" as the copyright notice for easier
+  identification within third-party archives.
+ Copyright 2017, The TensorFlow Authors.
+
+ 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.
+
+* Other names and brands may be claimed as the property of others.