Merge branch 'rapidsai:branch-23.12' into branch-23.12

rapidsai · Nov 7, 2023 · 76dc2e0 · 76dc2e0
2 parents 03cec81 + 0296043
commit 76dc2e0
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/python/cuml/feature_extraction/_vectorizers.py b/python/cuml/feature_extraction/_vectorizers.py
@@ -598,7 +598,9 @@ def fit_transform(self, raw_documents, y=None):
         if self._fixed_vocabulary:
             self.vocabulary_ = self.vocabulary
         else:
-            self.vocabulary_ = tokenized_df["token"].unique().sort_values()
+            self.vocabulary_ = (
+                tokenized_df["token"].drop_duplicates().sort_values()
+            )
 
         count_df = self._count_vocab(tokenized_df)
 

diff --git a/python/cuml/preprocessing/LabelEncoder.py b/python/cuml/preprocessing/LabelEncoder.py
@@ -180,7 +180,7 @@ def fit(self, y, _classes=None):
         if _classes is not None:
             self.classes_ = _classes
         else:
-            self.classes_ = y.unique().sort_values(
+            self.classes_ = y.drop_duplicates().sort_values(
                 ignore_index=True
             )  # dedupe and sort