spell check fixes (NVIDIA#10865)

Ran spell check on comments on public facing APIs and fixed them.

Authors:
  - Karthikeyan (https://github.com/karthikeyann)

Approvers:
  - GALI PREM SAGAR (https://github.com/galipremsagar)
  - David Wendt (https://github.com/davidwendt)
  - Nghia Truong (https://github.com/ttnghia)

URL: rapidsai/cudf#10865

cpp/include/cudf/copying.hpp

@@ -979,7 +979,7 @@ bool has_nonempty_nulls(column_view const& input);
  *
  * @param input The column which is (and whose descendants are) to be checked for
  * non-empty null rows
- * @return true If either the column or its decendants have null rows
+ * @return true If either the column or its descendants have null rows
  * @return false If neither the column nor its descendants have null rows
  */
 bool may_have_nonempty_nulls(column_view const& input);
@@ -1009,7 +1009,7 @@ bool may_have_nonempty_nulls(column_view const& input);
  *
  * The purge operation only applies directly to LIST and STRING columns, but it
  * applies indirectly to STRUCT columns as well, since LIST and STRUCT columns
- * may have child/decendant columns that are LIST or STRING.
+ * may have child/descendant columns that are LIST or STRING.
  *
  * @param input The column whose null rows are to be checked and purged
  * @param mr Device memory resource used to allocate the returned column's device memory
@@ -1045,7 +1045,7 @@ std::unique_ptr<column> purge_nonempty_nulls(
  *
  * The purge operation only applies directly to LIST and STRING columns, but it
  * applies indirectly to STRUCT columns as well, since LIST and STRUCT columns
- * may have child/decendant columns that are LIST or STRING.
+ * may have child/descendant columns that are LIST or STRING.
  *
  * @param input The column whose null rows are to be checked and purged
  * @param mr Device memory resource used to allocate the returned column's device memory
@@ -1081,7 +1081,7 @@ std::unique_ptr<column> purge_nonempty_nulls(
  *
  * The purge operation only applies directly to LIST and STRING columns, but it
  * applies indirectly to STRUCT columns as well, since LIST and STRUCT columns
- * may have child/decendant columns that are LIST or STRING.
+ * may have child/descendant columns that are LIST or STRING.
  *
  * @param input The column whose null rows are to be checked and purged
  * @param mr Device memory resource used to allocate the returned column's device memory

cpp/include/cudf/datetime.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -272,7 +272,7 @@ std::unique_ptr<cudf::column> days_in_month(
 /**
  * @brief  Returns the quarter of the date
  *
- * `output[i]` will be a value from {1, 2, 3, 4} corresponding to the quater of month given by
+ * `output[i]` will be a value from {1, 2, 3, 4} corresponding to the quarter of month given by
  * `column[i]`. It will be null if the input row at `column[i]` is null.
  *
  * @throw cudf::logic_error if input column datatype is not a TIMESTAMP

cpp/include/cudf/io/parquet.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2021, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -1082,7 +1082,7 @@ class parquet_chunked_writer {
    * @param[in] partitions Optional partitions to divide the table into. If specified, must be same
    * size as number of sinks.
    *
-   * @throws cudf::logic_error If the number of partitions is not the smae as number of sinks
+   * @throws cudf::logic_error If the number of partitions is not the same as number of sinks
    * @return returns reference of the class object
    */
   parquet_chunked_writer& write(table_view const& table,

cpp/include/cudf/io/text/data_chunk_source.hpp

@@ -47,7 +47,7 @@ class device_data_chunk {
  *
  * The data chunk reader API encapsulates the idea of statefully traversing and loading a data
  * source. A data source may be a file, a region of device memory, or a region of host memory.
- * Reading data from these data sources efficiently requires different strategies dependings on the
+ * Reading data from these data sources efficiently requires different strategies depending on the
  * type of data source, type of compression, capabilities of the host and device, the data's
  * destination. Whole-file decompression should be hidden behind this interface.
  */

cpp/include/cudf/join.hpp

@@ -872,7 +872,7 @@ std::unique_ptr<rmm::device_uvector<size_type>> conditional_left_anti_join(
  *
  * If the provided predicate returns NULL for a pair of rows
  * (left, right), that pair is not included in the output. It is the user's
- * responsiblity to choose a suitable compare_nulls value AND use appropriate
+ * responsibility to choose a suitable compare_nulls value AND use appropriate
  * null-safe operators in the expression.
  *
  * If the provided output size or per-row counts are incorrect, behavior is undefined.
@@ -932,7 +932,7 @@ mixed_inner_join(
  *
  * If the provided predicate returns NULL for a pair of rows
  * (left, right), that pair is not included in the output. It is the user's
- * responsiblity to choose a suitable compare_nulls value AND use appropriate
+ * responsibility to choose a suitable compare_nulls value AND use appropriate
  * null-safe operators in the expression.
  *
  * If the provided output size or per-row counts are incorrect, behavior is undefined.
@@ -992,7 +992,7 @@ mixed_left_join(
  *
  * If the provided predicate returns NULL for a pair of rows
  * (left, right), that pair is not included in the output. It is the user's
- * responsiblity to choose a suitable compare_nulls value AND use appropriate
+ * responsibility to choose a suitable compare_nulls value AND use appropriate
  * null-safe operators in the expression.
  *
  * If the provided output size or per-row counts are incorrect, behavior is undefined.
@@ -1044,7 +1044,7 @@ mixed_full_join(
  * evaluates to true on the conditional tables.
  *
  * If the provided predicate returns NULL for a pair of rows (left, right), the
- * left row is not included in the output. It is the user's responsiblity to
+ * left row is not included in the output. It is the user's responsibility to
  * choose a suitable compare_nulls value AND use appropriate null-safe
  * operators in the expression.
  *
@@ -1096,7 +1096,7 @@ std::unique_ptr<rmm::device_uvector<size_type>> mixed_left_semi_join(
  * conditional tables.
  *
  * If the provided predicate returns NULL for a pair of rows (left, right), the
- * left row is not included in the output. It is the user's responsiblity to
+ * left row is not included in the output. It is the user's responsibility to
  * choose a suitable compare_nulls value AND use appropriate null-safe
  * operators in the expression.
  *
@@ -1148,7 +1148,7 @@ std::unique_ptr<rmm::device_uvector<size_type>> mixed_left_anti_join(
  * conditional tables.
  *
  * If the provided predicate returns NULL for a pair of rows (left, right),
- * that pair is not included in the output. It is the user's responsiblity to
+ * that pair is not included in the output. It is the user's responsibility to
  * choose a suitable compare_nulls value AND use appropriate null-safe
  * operators in the expression.
  *
@@ -1191,7 +1191,7 @@ std::pair<std::size_t, std::unique_ptr<rmm::device_uvector<size_type>>> mixed_in
  * conditional tables.
  *
  * If the provided predicate returns NULL for a pair of rows (left, right),
- * that pair is not included in the output. It is the user's responsiblity to
+ * that pair is not included in the output. It is the user's responsibility to
  * choose a suitable compare_nulls value AND use appropriate null-safe
  * operators in the expression.
  *
@@ -1234,7 +1234,7 @@ std::pair<std::size_t, std::unique_ptr<rmm::device_uvector<size_type>>> mixed_le
  * conditional tables.
  *
  * If the provided predicate returns NULL for a pair of rows (left, right),
- * that pair is not included in the output. It is the user's responsiblity to
+ * that pair is not included in the output. It is the user's responsibility to
  * choose a suitable compare_nulls value AND use appropriate null-safe
  * operators in the expression.
  *
@@ -1275,7 +1275,7 @@ std::pair<std::size_t, std::unique_ptr<rmm::device_uvector<size_type>>> mixed_le
  * left anti join between the specified tables.
  *
  * If the provided predicate returns NULL for a pair of rows (left, right),
- * that pair is not included in the output. It is the user's responsiblity to
+ * that pair is not included in the output. It is the user's responsibility to
  * choose a suitable compare_nulls value AND use appropriate null-safe
  * operators in the expression.
  *

cpp/include/cudf/lists/gather.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -45,8 +45,8 @@ namespace lists {
  * @throws cudf::logic_error if gather_map is not list column of an index type.
  *
  * If indices in `gather_map_list` are outside the range `[-n, n)`, where `n` is the number of
- * elements in corresponding row of the source column, the behaviour is as follows:
- *   1. If `bounds_policy` is set to `DONT_CHECK`, the behaviour is undefined.
+ * elements in corresponding row of the source column, the behavior is as follows:
+ *   1. If `bounds_policy` is set to `DONT_CHECK`, the behavior is undefined.
  *   2. If `bounds_policy` is set to `NULLIFY`, the corresponding element in the list row
  *      is set to null in the output column.
  *

cpp/include/cudf/strings/convert/convert_lists.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -49,7 +49,7 @@ namespace strings {
  * @throw cudf::logic_error if the input column is not a LIST type with a STRING child.
  *
  * @param input Lists column to format.
- * @param na_rep Replacment string for null elements.
+ * @param na_rep Replacement string for null elements.
  * @param separators Strings to use for enclosing list components and separating elements.
  * @param mr Device memory resource used to allocate the returned column's device memory.
  * @return New strings column.

cpp/include/cudf_test/tdigest_utilities.cuh

@@ -436,7 +436,7 @@ void tdigest_merge_simple(Func op, MergeFunc merge_op)
 
   int const delta = 1000;
 
-  // generate seperate digests
+  // generate separate digests
   std::vector<std::unique_ptr<column>> parts;
   auto iter = thrust::make_counting_iterator(0);
   std::transform(

cpp/src/binaryop/compiled/binary_ops.cu

@@ -39,7 +39,7 @@ namespace {
 /**
  * @brief Converts scalar to column_view with single element.
  *
- * @return pair with column_view and column containing any auxilary data to create column_view from
+ * @return pair with column_view and column containing any auxiliary data to create column_view from
  * scalar
  */
 struct scalar_as_column_view {
@@ -91,7 +91,7 @@ scalar_as_column_view::return_type scalar_as_column_view::operator()<cudf::strin
  * @param scal    scalar to convert
  * @param stream  CUDA stream used for device memory operations and kernel launches.
  * @param mr      Device memory resource used to allocate the returned column's device memory
- * @return        pair with column_view and column containing any auxilary data to create
+ * @return        pair with column_view and column containing any auxiliary data to create
  * column_view from scalar
  */
 auto scalar_to_column_view(

cpp/src/io/json/reader_impl.cu

@@ -285,7 +285,7 @@ rmm::device_uvector<uint64_t> find_record_starts(json_reader_options const& read
     find_all_from_set(h_data, chars_to_find, 1, find_result_ptr, stream);
   }
 
-  // Previous call stores the record pinput_file.typeositions as encountered by all threads
+  // Previous call stores the record positions as encountered by all threads
   // Sort the record positions as subsequent processing may require filtering
   // certain rows or other processing on specific records
   thrust::sort(rmm::exec_policy(stream), rec_starts.begin(), rec_starts.end());

cpp/src/io/orc/orc.h

@@ -173,7 +173,7 @@ int constexpr encode_field_number(int field_number) noexcept
   return encode_field_number_base<T>(field_number);
 }
 
-// containters change the field number encoding
+// containers change the field number encoding
 template <typename T,
           std::enable_if_t<std::is_same_v<T, std::vector<typename T::value_type>>>* = nullptr>
 int constexpr encode_field_number(int field_number) noexcept

cpp/src/io/statistics/typed_statistics_chunk.cuh

@@ -231,7 +231,7 @@ get_untyped_chunk(const typed_statistics_chunk<T, include_aggregate>& chunk)
   stat.has_minmax = chunk.has_minmax;
   stat.has_sum    = [&]() {
     if (!chunk.has_minmax) return false;
-    // invalidate the sum if overlow or underflow is possible
+    // invalidate the sum if overflow or underflow is possible
     if constexpr (std::is_floating_point_v<E> or std::is_integral_v<E>) {
       return std::numeric_limits<E>::max() / chunk.non_nulls >=
                static_cast<E>(chunk.maximum_value) and

cpp/src/reductions/scan/scan_inclusive.cu

@@ -159,7 +159,7 @@ struct scan_functor<Op, cudf::struct_view> {
                                         rmm::cuda_stream_view stream,
                                         rmm::mr::device_memory_resource* mr)
   {
-    // Create a gather map contaning indices of the prefix min/max elements.
+    // Create a gather map containing indices of the prefix min/max elements.
     auto gather_map = rmm::device_uvector<size_type>(input.size(), stream);
     auto const binop_generator =
       cudf::reduction::detail::comparison_binop_generator::create<Op>(input, stream);

cpp/src/strings/json/json_path.cu

@@ -509,7 +509,7 @@ struct path_operator {
   //    - you cannot retrieve a subscripted field (eg [5]) from an object.
   //    - you cannot retrieve a field by name (eg  .book) from an array.
   //    - you -can- use .* for both arrays and objects
-  // a value of NONE imples any type accepted
+  // a value of NONE implies any type accepted
   json_element_type expected_type{NONE};  // the expected type of the element we're working with
   string_view name;                       // name to match against (if applicable)
   int index{-1};                          // index for subscript operator

cpp/src/strings/regex/regcomp.h

@@ -99,7 +99,7 @@ class reprog {
    * of this object
    *
    * @param pattern Regex pattern encoded as UTF-8
-   * @param flags For interpretting certain `pattern` characters
+   * @param flags For interpreting certain `pattern` characters
    * @return Instance of reprog
    */
   static reprog create_from(std::string_view pattern, regex_flags const flags);

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``