[CI] fix spelling mistakes in the codebase by adding codespell (#2550)

* Update .pre-commit-config.yaml

* Create .codespellrc

* Update .codespellrc

* Update daal4py_data_science.ipynb

* Update .codespellrc

* Update format.py

* Update dist_kmeans.h

* Update map_reduce_tree.h

* Update transceiver.h

* Update base.py

* Update test_n_jobs_support.py

* Update base.py

* Update _device_offload.py

* Update forest.py

* Update data_conversion.cpp

* Update _data_conversion.py

* Update dtype_conversion.cpp

* Update sycl_usm_utils.cpp

* Update common.py

* Update test_common.py

* Update _device_offload.py

* Update dbscan.cpp

* Update gen_daal4py.py

* address spelling issues

* last changes

* Update dbscan.py

* Update dbscan.py

* Update decision_forest_classification_default_dense.py

* Update decision_forest_classification_hist.py

* Update decision_forest_regression_default_dense.py

* Update decision_forest_regression_hist.py

Author: icfaust

.github/.codespellrc

@@ -0,0 +1,18 @@
+;
+; Copyright contributors to the oneDAL project
+;
+; 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.
+;
+[codespell]
+skip = *.ipynb,
+ignore-words-list = als,coo,inout,nd,ons

.github/scripts/doc_release.sh

@@ -114,7 +114,7 @@ else
         rsync -av "$version_dir/" $version/
     done
 
-    # Git only add verison folders
+    # Git only add version folders
     git add -- [0-9][0-9][0-9][0-9].[0-9]* 
     git commit -m "Initialize doc archive branch with all versions"
 fi

.pre-commit-config.yaml

@@ -42,3 +42,8 @@ repos:
                 scripts/|
                 tests/
             )
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell
+        args: ["--config", ".github/.codespellrc" ]

daal4py/sklearn/cluster/dbscan.py

@@ -36,10 +36,10 @@ def _daal_dbscan(X, eps=0.5, min_samples=5, sample_weight=None):
     ww = make2d(sample_weight) if sample_weight is not None else None
     XX = make2d(X)
 
-    fpt = getFPType(XX)
+    fpt = getFPType(XX)  # codespell:ignore fpt
     alg = daal4py.dbscan(
         method="defaultDense",
-        fptype=fpt,
+        fptype=fpt,  # codespell:ignore fpt
         epsilon=float(eps),
         minObservations=int(min_samples),
         memorySavingMode=False,

daal4py/sklearn/manifold/_t_sne.py

@@ -136,7 +136,7 @@ def _fit(self, X, skip_num_points=0):
 
         if isinstance(self._init, str) and self._init == "pca" and issparse(X):
             raise TypeError(
-                "PCA initialization is currently not suported "
+                "PCA initialization is currently not supported "
                 "with the sparse input matrix. Use "
                 'init="random" instead.'
             )

daal4py/sklearn/svm/svm.py

@@ -158,7 +158,7 @@ def _daal4py_kf(kernel, X_fptype, gamma=1.0, is_sparse=False):
         kf = daal4py.kernel_function_linear(fptype=X_fptype, method=method)
     else:
         raise ValueError(
-            "_daal4py_fit received unexpected kernel specifiction {}.".format(kernel)
+            "_daal4py_fit received unexpected kernel specification {}.".format(kernel)
         )
 
     return kf

daal4py/sklearn/tree/decision_tree.py

@@ -160,7 +160,7 @@ def fit(self, X, y, sample_weight=None, pruning_set=None):
             ignored if they would result in any single class carrying a
             negative weight in either child node.
 
-        pruning_set: None or a tuple of (X, y) corrsponding to features and
+        pruning_set: None or a tuple of (X, y) corresponding to features and
             associated labels used for tree pruning. See [1] for more details.
 
         Returns

daal4py/sklearn/utils/validation.py

@@ -89,7 +89,7 @@ def _assert_all_finite(
     num_of_types = get_number_of_types(X)
 
     # if X is heterogeneous pandas.DataFrame then
-    # covert it to a list of arrays
+    # convert it to a list of arrays
     if is_df and num_of_types > 1:
         lst = []
         for idx in X:
@@ -329,7 +329,7 @@ def is_sparse(dtype):
     has_pd_integer_array = False
     if hasattr(array, "dtypes") and hasattr(array.dtypes, "__array__"):
         # throw warning if columns are sparse. If all columns are sparse, then
-        # array.sparse exists and sparsity will be perserved (later).
+        # array.sparse exists and sparsity will be preserved (later).
         with suppress(ImportError):
             from pandas import SparseDtype
 

deselected_tests.yaml

@@ -104,7 +104,7 @@ deselected_tests:
 
   # Sklearnex RandomForestClassifier RNG is different from scikit-learn and daal4py
   # resulting in different feature importances for small number of trees (10).
-  # Issue dissappears with bigger number of trees (>=20)
+  # Issue disappears with bigger number of trees (>=20)
   - inspection/tests/test_permutation_importance.py::test_permutation_importance_correlated_feature_regression_pandas[0.5-1]
   - inspection/tests/test_permutation_importance.py::test_permutation_importance_correlated_feature_regression_pandas[0.5-2]
   - inspection/tests/test_permutation_importance.py::test_permutation_importance_correlated_feature_regression_pandas[1.0-1]

doc/sources/about_daal4py.rst

@@ -31,7 +31,7 @@ of the |onedal|, while ``sklearnex`` is a module built atop of the "oneAPI" inte
 DPC-based features such as :ref:`GPU support <oneapi_gpu>`.
 
 There is a large degree of overlap in the functionalities offered between the two modules
-``daal4py`` and ``sklearnex`` - module ``sklearnex`` should be prefered whenever possible,
+``daal4py`` and ``sklearnex`` - module ``sklearnex`` should be preferred whenever possible,
 either by using it directly or through the :ref:`patching mechanism <patching>` - but ``daal4py``
 exposes some additional functionalities from the |onedal| that ``sklearnex`` doesn't:
 
@@ -57,7 +57,7 @@ Using daal4py
 Unlike ``sklearnex``, ``daal4py``, being a lower-level interface, does not follow scikit-learn
 idioms - instead, the process for calling procedures from the ``daal4py`` interface is as follows:
 
-- Instantiate an 'algorithm' class by calling its contructor, without any data - for example:
+- Instantiate an 'algorithm' class by calling its constructor, without any data - for example:
   ``qr_algo = daal4py.qr()``.
 - Call the 'compute' method of that instantiated algorithm in order to obtain a 'result' object,
   passing it the data on which it will operate - for example: ``qr_result = qr_algo.compute(X)``.