Undeprecated byte-pair-encoding APIs

Author: davidwendt

cpp/include/nvtext/byte_pair_encoding.hpp

@@ -63,8 +63,6 @@ struct bpe_merge_pairs {
 /**
  * @brief Create a nvtext::bpe_merge_pairs from a strings column
  *
- * @deprecated Since 26.04
- *
  * The input column should contain a unique pair of strings per line separated by
  * a single space. An incorrect format or non-unique entries will result in
  * undefined behavior.
@@ -87,16 +85,14 @@ struct bpe_merge_pairs {
  * @param mr Memory resource to allocate any returned objects
  * @return A nvtext::bpe_merge_pairs object
  */
-[[deprecated]] std::unique_ptr<bpe_merge_pairs> load_merge_pairs(
+std::unique_ptr<bpe_merge_pairs> load_merge_pairs(
   cudf::strings_column_view const& merge_pairs,
   rmm::cuda_stream_view stream      = cudf::get_default_stream(),
   rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
 /**
  * @brief Byte pair encode the input strings.
  *
- * @deprecated Since 26.04
- *
  * The encoding algorithm rebuilds each string by matching substrings
  * in the `merge_pairs` table and iteratively removing the minimum ranked pair
  * until no pairs are left. Then, the separator is inserted between the remaining
@@ -121,7 +117,7 @@ struct bpe_merge_pairs {
  * @param mr Memory resource to allocate any returned objects.
  * @return An encoded column of strings.
  */
-[[deprecated]] std::unique_ptr<cudf::column> byte_pair_encoding(
+std::unique_ptr<cudf::column> byte_pair_encoding(
   cudf::strings_column_view const& input,
   bpe_merge_pairs const& merges_pairs,
   cudf::string_scalar const& separator = cudf::string_scalar(" "),

python/cudf/cudf/core/byte_pair_encoding.py

@@ -3,8 +3,6 @@
 
 from __future__ import annotations
 
-import warnings
-
 import pylibcudf as plc
 
 from cudf.core.series import Series
@@ -15,9 +13,6 @@ class BytePairEncoder:
     Given a merge pairs strings series, performs byte pair encoding on
     a strings series using the provided separator.
 
-    .. deprecated:: 26.04
-        BytePairEncoder is deprecated and will be removed in a future version.
-
     Parameters
     ----------
     merges_pairs : str
@@ -29,11 +24,6 @@ class BytePairEncoder:
     """
 
     def __init__(self, merges_pair: Series) -> None:
-        warnings.warn(
-            "BytePairEncoder is deprecated and will be removed in a future version.",
-            FutureWarning,
-            stacklevel=2,
-        )
         self.merge_pairs = plc.nvtext.byte_pair_encode.BPEMergePairs(
             merges_pair._column.plc_column
         )

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

@@ -700,11 +700,6 @@ def byte_pair_encoding(
         merge_pairs: plc.nvtext.byte_pair_encode.BPEMergePairs,
         separator: str,
     ) -> Self:
-        warnings.warn(
-            "byte_pair_encoding is deprecated and will be removed in a future version.",
-            FutureWarning,
-            stacklevel=2,
-        )
         with self.access(mode="read", scope="internal"):
             plc_column = plc.nvtext.byte_pair_encode.byte_pair_encoding(
                 self.plc_column,