scikit-learn-intelex 2024.0.1__py312-none-win_amd64.whl

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/__init__.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from . import utils
+from ._config import config_context, get_config, set_config
+from .dispatcher import (
+    get_patch_map,
+    get_patch_names,
+    is_patched_instance,
+    patch_sklearn,
+    sklearn_is_patched,
+    unpatch_sklearn,
+)
+
+__all__ = [
+    "basic_statistics",
+    "cluster",
+    "config_context",
+    "decomposition",
+    "ensemble",
+    "get_config",
+    "get_patch_map",
+    "get_patch_names",
+    "is_patched_instance",
+    "linear_model",
+    "manifold",
+    "metrics",
+    "neighbors",
+    "patch_sklearn",
+    "set_config",
+    "sklearn_is_patched",
+    "sklearn_is_patchedget_patch_map",
+    "svm",
+    "unpatch_sklearn",
+    "utils",
+]
+
+
+from onedal import _is_dpc_backend
+
+if _is_dpc_backend:
+    __all__.append("spmd")
+
+
+from ._utils import set_sklearn_ex_verbose
+
+set_sklearn_ex_verbose()

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/__main__.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+# ==============================================================================
+# 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 sys
+
+from sklearnex import patch_sklearn
+
+
+def _main():
+    import argparse
+
+    parser = argparse.ArgumentParser(
+        prog="python -m sklearnex",
+        description="""
+            Run your Python script with Intel(R) Extension for
+            scikit-learn, optimizing solvers of
+            scikit-learn with Intel(R) oneAPI Data Analytics Library.
+            """,
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+
+    parser.add_argument(
+        "-m", action="store_true", dest="module", help="Executes following as a module"
+    )
+    parser.add_argument("name", help="Script or module name")
+    parser.add_argument("args", nargs=argparse.REMAINDER, help="Command line arguments")
+    args = parser.parse_args()
+
+    try:
+        import sklearn
+
+        patch_sklearn()
+    except ImportError:
+        print("Scikit-learn could not be imported. Nothing to patch")
+
+    sys.argv = [args.name] + args.args
+    if "_" + args.name in globals():
+        return globals()["_" + args.name](*args.args)
+    import runpy
+
+    runf = runpy.run_module if args.module else runpy.run_path
+    runf(args.name, run_name="__main__")
+
+
+sys.exit(_main())

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/_config.py

@@ -0,0 +1,110 @@
+# ==============================================================================
+# 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 threading
+from contextlib import contextmanager
+
+from sklearn import get_config as skl_get_config
+from sklearn import set_config as skl_set_config
+
+_default_global_config = {
+    "target_offload": "auto",
+    "allow_fallback_to_host": False,
+}
+
+_threadlocal = threading.local()
+
+
+def _get_sklearnex_threadlocal_config():
+    if not hasattr(_threadlocal, "global_config"):
+        _threadlocal.global_config = _default_global_config.copy()
+    return _threadlocal.global_config
+
+
+def get_config():
+    """Retrieve current values for configuration set by :func:`set_config`
+    Returns
+    -------
+    config : dict
+        Keys are parameter names that can be passed to :func:`set_config`.
+    See Also
+    --------
+    config_context : Context manager for global configuration.
+    set_config : Set global configuration.
+    """
+    sklearn = skl_get_config()
+    sklearnex = _get_sklearnex_threadlocal_config().copy()
+    return {**sklearn, **sklearnex}
+
+
+def set_config(target_offload=None, allow_fallback_to_host=None, **sklearn_configs):
+    """Set global configuration
+    Parameters
+    ----------
+    target_offload : string or dpctl.SyclQueue, default=None
+        The device primarily used to perform computations.
+        If string, expected to be "auto" (the execution context
+        is deduced from input data location),
+        or SYCL* filter selector string. Global default: "auto".
+    allow_fallback_to_host : bool, default=None
+        If True, allows to fallback computation to host device
+        in case particular estimator does not support the selected one.
+        Global default: False.
+    See Also
+    --------
+    config_context : Context manager for global configuration.
+    get_config : Retrieve current values of the global configuration.
+    """
+    skl_set_config(**sklearn_configs)
+
+    local_config = _get_sklearnex_threadlocal_config()
+
+    if target_offload is not None:
+        local_config["target_offload"] = target_offload
+    if allow_fallback_to_host is not None:
+        local_config["allow_fallback_to_host"] = allow_fallback_to_host
+
+
+@contextmanager
+def config_context(**new_config):
+    """Context manager for global scikit-learn configuration
+    Parameters
+    ----------
+    target_offload : string or dpctl.SyclQueue, default=None
+        The device primarily used to perform computations.
+        If string, expected to be "auto" (the execution context
+        is deduced from input data location),
+        or SYCL* filter selector string. Global default: "auto".
+    allow_fallback_to_host : bool, default=None
+        If True, allows to fallback computation to host device
+        in case particular estimator does not support the selected one.
+        Global default: False.
+    Notes
+    -----
+    All settings, not just those presently modified, will be returned to
+    their previous values when the context manager is exited.
+    See Also
+    --------
+    set_config : Set global scikit-learn configuration.
+    get_config : Retrieve current values of the global configuration.
+    """
+    old_config = get_config()
+    set_config(**new_config)
+
+    try:
+        yield
+    finally:
+        set_config(**old_config)

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/_device_offload.py

@@ -0,0 +1,223 @@
+# ==============================================================================
+# 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 logging
+import sys
+from functools import wraps
+
+import numpy as np
+
+try:
+    from dpctl import SyclQueue
+    from dpctl.memory import MemoryUSMDevice, as_usm_memory
+    from dpctl.tensor import usm_ndarray
+
+    dpctl_available = True
+except ImportError:
+    dpctl_available = False
+
+try:
+    import dpnp
+
+    dpnp_available = True
+except ImportError:
+    dpnp_available = False
+
+from ._config import get_config
+from ._utils import get_patch_message
+
+oneapi_is_available = "daal4py.oneapi" in sys.modules
+if oneapi_is_available:
+    from daal4py.oneapi import _get_device_name_sycl_ctxt, _get_sycl_ctxt_params
+
+
+class DummySyclQueue:
+    """This class is designed to act like dpctl.SyclQueue
+    to allow device dispatching in scenarios when dpctl is not available"""
+
+    class DummySyclDevice:
+        def __init__(self, filter_string):
+            self._filter_string = filter_string
+            self.is_cpu = "cpu" in filter_string
+            self.is_gpu = "gpu" in filter_string
+            # TODO: check for possibility of fp64 support
+            # on other devices in this dummy class
+            self.has_aspect_fp64 = self.is_cpu
+
+            if not (self.is_cpu):
+                logging.warning(
+                    "Device support is limited. "
+                    "Please install dpctl for full experience"
+                )
+
+        def get_filter_string(self):
+            return self._filter_string
+
+    def __init__(self, filter_string):
+        self.sycl_device = self.DummySyclDevice(filter_string)
+
+
+def _get_device_info_from_daal4py():
+    if oneapi_is_available:
+        return _get_device_name_sycl_ctxt(), _get_sycl_ctxt_params()
+    return None, dict()
+
+
+def _get_global_queue():
+    target = get_config()["target_offload"]
+    d4p_target, _ = _get_device_info_from_daal4py()
+    if d4p_target == "host":
+        d4p_target = "cpu"
+
+    QueueClass = DummySyclQueue if not dpctl_available else SyclQueue
+
+    if target != "auto":
+        if d4p_target is not None and d4p_target != target:
+            if not isinstance(target, str):
+                if d4p_target not in target.sycl_device.get_filter_string():
+                    raise RuntimeError(
+                        "Cannot use target offload option "
+                        "inside daal4py.oneapi.sycl_context"
+                    )
+            else:
+                raise RuntimeError(
+                    "Cannot use target offload option "
+                    "inside daal4py.oneapi.sycl_context"
+                )
+        if isinstance(target, QueueClass):
+            return target
+        return QueueClass(target)
+    if d4p_target is not None:
+        return QueueClass(d4p_target)
+    return None
+
+
+def _transfer_to_host(queue, *data):
+    has_usm_data, has_host_data = False, False
+
+    host_data = []
+    for item in data:
+        usm_iface = getattr(item, "__sycl_usm_array_interface__", None)
+        if usm_iface is not None:
+            if not dpctl_available:
+                raise RuntimeError(
+                    "dpctl need to be installed to work "
+                    "with __sycl_usm_array_interface__"
+                )
+            if queue is not None:
+                if queue.sycl_device != usm_iface["syclobj"].sycl_device:
+                    raise RuntimeError(
+                        "Input data shall be located " "on single target device"
+                    )
+            else:
+                queue = usm_iface["syclobj"]
+
+            buffer = as_usm_memory(item).copy_to_host()
+            item = np.ndarray(
+                shape=usm_iface["shape"], dtype=usm_iface["typestr"], buffer=buffer
+            )
+            has_usm_data = True
+        else:
+            has_host_data = True
+
+        mismatch_host_item = usm_iface is None and item is not None and has_usm_data
+        mismatch_usm_item = usm_iface is not None and has_host_data
+
+        if mismatch_host_item or mismatch_usm_item:
+            raise RuntimeError("Input data shall be located on single target device")
+
+        host_data.append(item)
+    return queue, host_data
+
+
+def _get_backend(obj, queue, method_name, *data):
+    cpu_device = queue is None or queue.sycl_device.is_cpu
+    gpu_device = queue is not None and queue.sycl_device.is_gpu
+
+    if cpu_device:
+        patching_status = obj._onedal_cpu_supported(method_name, *data)
+        if patching_status.get_status():
+            return "onedal", queue, patching_status
+        else:
+            return "sklearn", None, patching_status
+
+    _, d4p_options = _get_device_info_from_daal4py()
+    allow_fallback_to_host = get_config()["allow_fallback_to_host"] or d4p_options.get(
+        "host_offload_on_fail", False
+    )
+
+    if gpu_device:
+        patching_status = obj._onedal_gpu_supported(method_name, *data)
+        if patching_status.get_status():
+            return "onedal", queue, patching_status
+        else:
+            if allow_fallback_to_host:
+                patching_status = obj._onedal_cpu_supported(method_name, *data)
+                if patching_status.get_status():
+                    return "onedal", None, patching_status
+                else:
+                    return "sklearn", None, patching_status
+            else:
+                return "sklearn", None, patching_status
+
+    raise RuntimeError("Device support is not implemented")
+
+
+def dispatch(obj, method_name, branches, *args, **kwargs):
+    q = _get_global_queue()
+    q, hostargs = _transfer_to_host(q, *args)
+    q, hostvalues = _transfer_to_host(q, *kwargs.values())
+    hostkwargs = dict(zip(kwargs.keys(), hostvalues))
+
+    backend, q, patching_status = _get_backend(obj, q, method_name, *hostargs)
+
+    if backend == "onedal":
+        patching_status.write_log(queue=q)
+        return branches[backend](obj, *hostargs, **hostkwargs, queue=q)
+    if backend == "sklearn":
+        patching_status.write_log()
+        return branches[backend](obj, *hostargs, **hostkwargs)
+    raise RuntimeError(
+        f"Undefined backend {backend} in " f"{obj.__class__.__name__}.{method_name}"
+    )
+
+
+def _copy_to_usm(queue, array):
+    if not dpctl_available:
+        raise RuntimeError(
+            "dpctl need to be installed to work " "with __sycl_usm_array_interface__"
+        )
+    mem = MemoryUSMDevice(array.nbytes, queue=queue)
+    mem.copy_from_host(array.tobytes())
+    return usm_ndarray(array.shape, array.dtype, buffer=mem)
+
+
+def wrap_output_data(func):
+    @wraps(func)
+    def wrapper(self, *args, **kwargs):
+        data = (*args, *kwargs.values())
+        if len(data) == 0:
+            usm_iface = None
+        else:
+            usm_iface = getattr(data[0], "__sycl_usm_array_interface__", None)
+        result = func(self, *args, **kwargs)
+        if usm_iface is not None:
+            result = _copy_to_usm(usm_iface["syclobj"], result)
+            if dpnp_available and isinstance(data[0], dpnp.ndarray):
+                result = dpnp.array(result, copy=False)
+        return result
+
+    return wrapper

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/_utils.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python
+# ===============================================================================
+# 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 logging
+import os
+import sys
+import warnings
+
+from daal4py.sklearn._utils import (
+    PatchingConditionsChain as daal4py_PatchingConditionsChain,
+)
+from daal4py.sklearn._utils import daal_check_version
+
+
+class PatchingConditionsChain(daal4py_PatchingConditionsChain):
+    def get_status(self):
+        return self.patching_is_enabled
+
+    def write_log(self, queue=None):
+        if self.patching_is_enabled:
+            self.logger.info(
+                f"{self.scope_name}: {get_patch_message('onedal', queue=queue)}"
+            )
+        else:
+            self.logger.debug(
+                f"{self.scope_name}: debugging for the patch is enabled to track"
+                " the usage of Intel® oneAPI Data Analytics Library (oneDAL)"
+            )
+            for message in self.messages:
+                self.logger.debug(
+                    f"{self.scope_name}: patching failed with cause - {message}"
+                )
+            self.logger.info(f"{self.scope_name}: {get_patch_message('sklearn')}")
+
+
+def set_sklearn_ex_verbose():
+    log_level = os.environ.get("SKLEARNEX_VERBOSE")
+
+    logger = logging.getLogger("sklearnex")
+    logging_channel = logging.StreamHandler()
+    logging_formatter = logging.Formatter("%(levelname)s:%(name)s: %(message)s")
+    logging_channel.setFormatter(logging_formatter)
+    logger.addHandler(logging_channel)
+
+    try:
+        if log_level is not None:
+            logger.setLevel(log_level)
+    except Exception:
+        warnings.warn(
+            'Unknown level "{}" for logging.\n'
+            'Please, use one of "CRITICAL", "ERROR", '
+            '"WARNING", "INFO", "DEBUG".'.format(log_level)
+        )
+
+
+def get_patch_message(s, queue=None):
+    if s == "onedal":
+        message = "running accelerated version on "
+        if queue is not None:
+            if queue.sycl_device.is_gpu:
+                message += "GPU"
+            elif queue.sycl_device.is_cpu:
+                message += "CPU"
+            else:
+                raise RuntimeError("Unsupported device")
+        else:
+            message += "CPU"
+    elif s == "sklearn":
+        message = "fallback to original Scikit-learn"
+    elif s == "sklearn_after_onedal":
+        message = "failed to run accelerated version, fallback to original Scikit-learn"
+    else:
+        raise ValueError(
+            f"Invalid input - expected one of 'onedal','sklearn',"
+            f" 'sklearn_after_onedal', got {s}"
+        )
+    return message
+
+
+def get_sklearnex_version(rule):
+    return daal_check_version(rule)

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/basic_statistics/__init__.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from .basic_statistics import BasicStatistics
+
+__all__ = ["BasicStatistics"]

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/basic_statistics/basic_statistics.py

@@ -0,0 +1,17 @@
+# ==============================================================================
+# 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.
+# ==============================================================================
+
+from onedal.basic_statistics import BasicStatistics

scikit_learn_intelex-2024.0.1.data/data/Lib/site-packages/sklearnex/cluster/__init__.py

@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+# ===============================================================================
+# 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.
+# ===============================================================================
+
+from .dbscan import DBSCAN
+from .k_means import KMeans
+
+__all__ = ["KMeans", "DBSCAN"]