cudf python spell check fixes

python/cudf/cudf/core/column/string.py

@@ -135,7 +135,7 @@ def __init__(self, parent):
     def htoi(self) -> SeriesOrIndex:
         """
         Returns integer value represented by each hex string.
-        String is interpretted to have hex (base-16) characters.
+        String is interpreted to have hex (base-16) characters.
 
         Returns
         -------

python/cudf/cudf/core/column/timedelta.py

@@ -343,7 +343,7 @@ def sum(
         dtype: Dtype = None,
     ) -> pd.Timedelta:
         return pd.Timedelta(
-            # Since sum isn't overriden in Numerical[Base]Column, mypy only
+            # Since sum isn't overridden in Numerical[Base]Column, mypy only
             # sees the signature from Reducible (which doesn't have the extra
             # parameters from ColumnBase._reduce) so we have to ignore this.
             self.as_numerical.sum(  # type: ignore

python/cudf/cudf/core/cut.py

@@ -49,7 +49,7 @@ def cut(
     labels : array or False, default None
         Specifies the labels for the returned bins. Must be the same
         length as the resulting bins. If False, returns only integer
-        indicators of thebins. If True,raises an error. When ordered=False,
+        indicators of the bins. If True,raises an error. When ordered=False,
         labels must be provided.
     retbins : bool, default False
         Whether to return the bins or not.

python/cudf/cudf/core/dataframe.py

@@ -267,7 +267,7 @@ def _getitem_tuple_arg(self, arg):
                 tmp_arg = arg
                 if is_scalar(arg[0]):
                     # If a scalar, there is possibility of having duplicates.
-                    # Join would get all the duplicates. So, coverting it to
+                    # Join would get all the duplicates. So, converting it to
                     # an array kind.
                     tmp_arg = ([tmp_arg[0]], tmp_arg[1])
                 if len(tmp_arg[0]) == 0:
@@ -1099,7 +1099,7 @@ def __setattr__(self, key, col):
 
         except RuntimeError as e:
             # TODO: This allows setting properties that are marked as forbidden
-            # for internal usage. It is necesary because the __getattribute__
+            # for internal usage. It is necessary because the __getattribute__
             # call in the try block will trigger the error. We should see if
             # setting these variables can also always be disabled
             if "External-only API" not in str(e):
@@ -1613,7 +1613,7 @@ def _concat(
 
         # Get a list of the combined index and table column indices
         indices = list(range(functools.reduce(max, map(len, columns))))
-        # The position of the first table colum in each
+        # The position of the first table column in each
         # combined index + table columns list
         first_data_column_position = len(indices) - len(names)
 
@@ -1786,7 +1786,7 @@ def _clean_nulls_from_dataframe(self, df):
     def _get_renderable_dataframe(self):
         """
         takes rows and columns from pandas settings or estimation from size.
-        pulls quadrents based off of some known parameters then style for
+        pulls quadrants based off of some known parameters then style for
         multiindex as well producing an efficient representative string
         for printing with the dataframe.
         """
@@ -2909,7 +2909,7 @@ def rename(
         Difference from pandas:
             * Not supporting: level
 
-        Rename will not overwite column names. If a list with duplicates is
+        Rename will not overwrite column names. If a list with duplicates is
         passed, column names will be postfixed with a number.
 
         Examples
@@ -4506,7 +4506,7 @@ def from_pandas(cls, dataframe, nan_as_null=None):
         Parameters
         ----------
         dataframe : Pandas DataFrame object
-            A Pandads DataFrame object which has to be converted
+            A Pandas DataFrame object which has to be converted
             to cuDF DataFrame.
         nan_as_null : bool, Default True
             If ``True``, converts ``np.nan`` values to ``null`` values.

python/cudf/cudf/core/frame.py

@@ -1615,9 +1615,9 @@ def replace(
         4    <NA>
         dtype: object
 
-        If there is a mimatch in types of the values in
+        If there is a mismatch in types of the values in
         ``to_replace`` & ``value`` with the actual series, then
-        cudf exhibits different behaviour with respect to pandas
+        cudf exhibits different behavior with respect to pandas
         and the pairs are ignored silently:
 
         >>> s = cudf.Series(['b', 'a', 'a', 'b', 'a'])
@@ -2044,7 +2044,7 @@ def searchsorted(
             na_position=na_position,
         )
 
-        # Retrun result as cupy array if the values is non-scalar
+        # Return result as cupy array if the values is non-scalar
         # If values is scalar, result is expected to be scalar.
         result = cupy.asarray(outcol.data_array_view)
         if scalar_flag:

python/cudf/cudf/core/indexed_frame.py

@@ -1889,7 +1889,7 @@ def first(self, offset):
         Parameters
         ----------
         offset: str
-            The offset length of the data that will be selected. For intance,
+            The offset length of the data that will be selected. For instance,
             '1M' will display all rows having their index within the first
             month.
 

python/cudf/cudf/core/join/join.py

@@ -70,7 +70,7 @@ def __init__(
             Boolean flag indicating the left index column or columns
             are to be used as join keys in order.
         right_index : bool
-            Boolean flag indicating the right index column or coumns
+            Boolean flag indicating the right index column or columns
             are to be used as join keys in order.
         lhs_is_index : bool
             ``lhs`` is a ``BaseIndex``

python/cudf/cudf/core/multiindex.py

@@ -188,7 +188,7 @@ def names(self, value):
             # we reconstruct self._data with the names as keys.
             # If they are not unique, the keys of self._data
             # and self._names will be different, which can lead
-            # to unexpected behaviour in some cases. This is
+            # to unexpected behavior in some cases. This is
             # definitely buggy, but we can't disallow non-unique
             # names either...
             self._data = self._data.__class__._create_unsafe(
@@ -343,7 +343,7 @@ def copy(
         deep : Bool (default False)
             If True, `._data`, `._levels`, `._codes` will be copied. Ignored if
             `levels` or `codes` are specified.
-        name : object, optional (defulat None)
+        name : object, optional (default None)
             To keep consistent with `Index.copy`, should not be used.
 
         Returns

python/cudf/cudf/core/reshape.py

@@ -395,7 +395,7 @@ def concat(objs, axis=0, join="outer", ignore_index=False, sort=None):
                 axis=axis,
                 join=join,
                 ignore_index=ignore_index,
-                # Explicitly cast rather than relying on None being falsy.
+                # Explicitly cast rather than relying on None being false.
                 sort=bool(sort),
             )
         return result

python/cudf/cudf/core/series.py

@@ -1311,7 +1311,7 @@ def has_nulls(self):
         Returns
         -------
         out : bool
-            If Series has atleast one null value, return True, if not
+            If Series has at least one null value, return True, if not
             return False.
 
         Examples
@@ -1447,7 +1447,7 @@ def drop_duplicates(self, keep="first", inplace=False, ignore_index=False):
         5     hippo
         Name: animal, dtype: object
 
-        With the `keep` parameter, the selection behaviour of duplicated
+        With the `keep` parameter, the selection behavior of duplicated
         values can be changed. The value 'first' keeps the first
         occurrence for each set of duplicated entries.
         The default value of keep is 'first'. Note that order of
@@ -3934,7 +3934,7 @@ def is_quarter_start(self):
         Returns
         -------
         Series
-        Booleans indicating if dates are the begining of a quarter
+        Booleans indicating if dates are the beginning of a quarter
 
         Examples
         --------
@@ -4305,7 +4305,7 @@ def strftime(self, date_format, *args, **kwargs):
 
 class TimedeltaProperties:
     """
-    Accessor object for timedeltalike properties of the Series values.
+    Accessor object for timedelta-like properties of the Series values.
 
     Returns
     -------

python/cudf/cudf/core/subword_tokenizer.py

@@ -183,7 +183,7 @@ def __call__(
 
             truncation = False
             warning_msg = (
-                "When truncation is not True, the behaviour currently differs "
+                "When truncation is not True, the behavior currently differs "
                 "from HuggingFace as cudf always returns overflowing tokens"
             )
             warnings.warn(warning_msg)
@@ -207,7 +207,7 @@ def __call__(
             raise NotImplementedError(error_msg)
 
         stride = max_length - stride
-        # behaviour varies from subword_tokenize but maps with huggingface
+        # behavior varies from subword_tokenize but maps with huggingface
 
         input_ids, attention_mask, metadata = cpp_subword_tokenize(
             text._column,

python/cudf/cudf/io/parquet.py

@@ -307,7 +307,7 @@ def _process_dataset(
             path = file_fragment.path
 
             # Extract hive-partition keys, and make sure they
-            # are orederd the same as they are in `partition_categories`
+            # are ordered the same as they are in `partition_categories`
             if partition_categories:
                 raw_keys = ds._get_partition_keys(
                     file_fragment.partition_expression

python/cudf/cudf/testing/_utils.py

@@ -349,8 +349,8 @@ def assert_column_memory_eq(
     """Assert the memory location and size of `lhs` and `rhs` are equivalent.
 
     Both data pointer and mask pointer are checked. Also recursively check for
-    children to the same contarints. Also fails check if the number of children
-    mismatches at any level.
+    children to the same constraints. Also fails check if the number of
+    children mismatches at any level.
     """
     assert lhs.base_data_ptr == rhs.base_data_ptr
     assert lhs.base_mask_ptr == rhs.base_mask_ptr

python/cudf/cudf/utils/docutils.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2018, NVIDIA CORPORATION.
+# Copyright (c) 2018-2022, NVIDIA CORPORATION.
 
 """
 Helper functions for parameterized docstring
@@ -20,7 +20,7 @@ def _only_spaces(s):
 def docfmt(**kwargs):
     """Format docstring.
 
-    Simliar to saving the result of ``__doc__.format(**kwargs)`` as the
+    Similiar to saving the result of ``__doc__.format(**kwargs)`` as the
     function's docstring.
     """
     kwargs = {k: v.lstrip() for k, v in kwargs.items()}

python/dask_cudf/dask_cudf/io/parquet.py

@@ -386,7 +386,7 @@ def read_parquet(path, columns=None, **kwargs):
     """Read parquet files into a Dask DataFrame
 
     Calls ``dask.dataframe.read_parquet`` with ``engine=CudfEngine``
-    to cordinate the execution of ``cudf.read_parquet``, and to
+    to coordinate the execution of ``cudf.read_parquet``, and to
     ultimately create a ``dask_cudf.DataFrame`` collection.
 
     See the ``dask.dataframe.read_parquet`` documentation for