scikit-learn-intelex 2023.2.1__py310-none-win_amd64.whl → 2024.0.1__py310-none-win_amd64.whl

{scikit_learn_intelex-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/__init__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# ===============================================================================
+# ==============================================================================
 # Copyright 2021 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -13,7 +13,7 @@
 # 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

{scikit_learn_intelex-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/__main__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-#===============================================================================
+# ==============================================================================
 # Copyright 2021 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -13,9 +13,10 @@
 # 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
 
 
@@ -29,27 +30,30 @@ def _main():
             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")
+        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)
+    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__')
+    runf(args.name, run_name="__main__")
 
 
 sys.exit(_main())

{scikit_learn_intelex-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/_config.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ==============================================================================
 # Copyright 2021 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,7 +12,7 @@
 # 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

{scikit_learn_intelex-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/_device_offload.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ==============================================================================
 # Copyright 2021 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,44 +12,56 @@
 # 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 ._config import get_config
-from ._utils import get_patch_message
+import logging
+import sys
 from functools import wraps
+
 import numpy as np
-import sys
-import logging
 
 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
 
-oneapi_is_available = 'daal4py.oneapi' in sys.modules
+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'''
+    """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
+            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")
+                logging.warning(
+                    "Device support is limited. "
+                    "Please install dpctl for full experience"
+                )
 
         def get_filter_string(self):
             return self._filter_string
@@ -65,23 +77,26 @@ def _get_device_info_from_daal4py():
 
 
 def _get_global_queue():
-    target = get_config()['target_offload']
+    target = get_config()["target_offload"]
     d4p_target, _ = _get_device_info_from_daal4py()
-    if d4p_target == 'host':
-        d4p_target = 'cpu'
+    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 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")
+                    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")
+                raise RuntimeError(
+                    "Cannot use target offload option "
+                    "inside daal4py.oneapi.sycl_context"
+                )
         if isinstance(target, QueueClass):
             return target
         return QueueClass(target)
@@ -95,22 +110,25 @@ def _transfer_to_host(queue, *data):
 
     host_data = []
     for item in data:
-        usm_iface = getattr(item, '__sycl_usm_array_interface__', None)
+        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__")
+                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')
+                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']
+                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)
+            item = np.ndarray(
+                shape=usm_iface["shape"], dtype=usm_iface["typestr"], buffer=buffer
+            )
             has_usm_data = True
         else:
             has_host_data = True
@@ -119,7 +137,7 @@ def _transfer_to_host(queue, *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')
+            raise RuntimeError("Input data shall be located on single target device")
 
         host_data.append(item)
     return queue, host_data
@@ -128,23 +146,32 @@ def _transfer_to_host(queue, *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
-    cpu_fallback = False
 
-    if (cpu_device and obj._onedal_cpu_supported(method_name, *data)) or \
-       (gpu_device and obj._onedal_gpu_supported(method_name, *data)):
-        return 'onedal', queue, cpu_fallback
     if cpu_device:
-        return 'sklearn', None, cpu_fallback
+        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 = get_config()['allow_fallback_to_host'] or \
-        d4p_options.get('host_offload_on_fail', False)
-
-    if gpu_device and allow_fallback:
-        if obj._onedal_cpu_supported(method_name, *data):
-            cpu_fallback = True
-            return 'onedal', None, cpu_fallback
-        return 'sklearn', None, cpu_fallback
+    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")
 
@@ -155,20 +182,24 @@ def dispatch(obj, method_name, branches, *args, **kwargs):
     q, hostvalues = _transfer_to_host(q, *kwargs.values())
     hostkwargs = dict(zip(kwargs.keys(), hostvalues))
 
-    backend, q, cpu_fallback = _get_backend(obj, q, method_name, *hostargs)
+    backend, q, patching_status = _get_backend(obj, q, method_name, *hostargs)
 
-    if backend == 'onedal':
+    if backend == "onedal":
+        patching_status.write_log(queue=q)
         return branches[backend](obj, *hostargs, **hostkwargs, queue=q)
-    if backend == 'sklearn':
+    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}')
+    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__")
+        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)
@@ -181,9 +212,12 @@ def wrap_output_data(func):
         if len(data) == 0:
             usm_iface = None
         else:
-            usm_iface = getattr(data[0], '__sycl_usm_array_interface__', None)
+            usm_iface = getattr(data[0], "__sycl_usm_array_interface__", None)
         result = func(self, *args, **kwargs)
         if usm_iface is not None:
-            return _copy_to_usm(usm_iface['syclobj'], result)
+            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-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/basic_statistics/__init__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-#===============================================================================
+# ==============================================================================
 # Copyright 2023 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -13,8 +13,8 @@
 # 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']
+__all__ = ["BasicStatistics"]

{scikit_learn_intelex-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/basic_statistics/basic_statistics.py

@@ -1,4 +1,4 @@
-#===============================================================================
+# ==============================================================================
 # Copyright 2023 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,6 +12,6 @@
 # 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-2023.2.1.data → scikit_learn_intelex-2024.0.1.data}/data/Lib/site-packages/sklearnex/cluster/__init__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-#===============================================================================
+# ===============================================================================
 # Copyright 2021 Intel Corporation
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -13,9 +13,9 @@
 # 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 .k_means import KMeans
 from .dbscan import DBSCAN
+from .k_means import KMeans
 
-__all__ = ['KMeans', 'DBSCAN']
+__all__ = ["KMeans", "DBSCAN"]