sklearn api change fix

Author: ddangelov

docs/conf.py

@@ -29,7 +29,7 @@
 author = 'Dimo Angelov'
 
 # The full version, including alpha/beta/rc tags
-release = '1.0.27'
+release = '1.0.28'
 
 
 # -- General configuration ---------------------------------------------------

requirements.txt

@@ -1,4 +1,5 @@
 numpy>=1.20.0
+scikit-learn>=1.2.0
 pandas
 gensim>=4.0.0
 umap-learn>=0.5.1

setup.py

@@ -6,7 +6,7 @@
 setuptools.setup(
     name="top2vec",
     packages=["top2vec"],
-    version="1.0.27",
+    version="1.0.28",
     author="Dimo Angelov",
     author_email="dimo.angelov@gmail.com",
     description="Top2Vec learns jointly embedded topic, document and word vectors.",
@@ -28,6 +28,7 @@
     install_requires=[
         'numpy >= 1.20.0',
         'pandas',
+        'scikit-learn >= 1.2.0',
         'gensim >= 4.0.0',
         'umap-learn >= 0.5.1',
         'hdbscan >= 0.8.27',

top2vec/Top2Vec.py

@@ -578,7 +578,7 @@ def return_doc(doc):
             # preprocess vocabulary
             vectorizer = CountVectorizer(tokenizer=return_doc, preprocessor=return_doc)
             doc_word_counts = vectorizer.fit_transform(tokenized_corpus)
-            words = vectorizer.get_feature_names()
+            words = vectorizer.get_feature_names_out()
             word_counts = np.array(np.sum(doc_word_counts, axis=0).tolist()[0])
             vocab_inds = np.where(word_counts > min_count)[0]
 

top2vec/__init__.py

@@ -1,3 +1,3 @@
 from top2vec.Top2Vec import Top2Vec
 
-__version__ = '1.0.27'
+__version__ = '1.0.28'