Cleaning up the cluster tags.. Please be patient!
100%|██████████| 498/498 [00:00<00:00, 16958.79it/s]
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-13-93e777371ee0> in <module>()
     20     sys.exit()
     21 
---> 22 model.group(link_min_similarity=sim_match_percent)
     23 df_matched = model.get_matches()

6 frames
/usr/local/lib/python3.7/dist-packages/sklearn/feature_extraction/text.py in _count_vocab(self, raw_documents, fixed_vocab)
   1219             if not vocabulary:
   1220                 raise ValueError(
-> 1221                     "empty vocabulary; perhaps the documents only contain stop words"
   1222                 )
   1223 

ValueError: empty vocabulary; perhaps the documents only contain stop words

 TypeError                                 Traceback (most recent call last)
[<ipython-input-30-441ebf5fe05e>](https://localhost:8080/#) in <module>()
     10 
     11     corpus_embeddings = model.encode(corpus_sentences, batch_size=256, show_progress_bar=True, convert_to_tensor=True)
---> 12     clusters = util.community_detection(corpus_embeddings, min_community_size=min_cluster_size, threshold=cluster_accuracy, init_max_size=len(corpus_embeddings))
     13 
     14     for keyword, cluster in enumerate(clusters):

TypeError: community_detection() got an unexpected keyword argument 'init_max_size'`

NameError                                 Traceback (most recent call last)
<ipython-input-1-e0e4dd6ce4e3> in <module>()
      1 # do the grouping
      2 
----> 3 df_1_list = df_1.Keyword.tolist()  # create list from df
      4 model = PolyFuzz("TF-IDF")
      5 try:

NameError: name 'df_1' is not defined

AttributeError                            Traceback (most recent call last)
[<ipython-input-44-c0aaa49db967>](https://0oauy9fmg1cc-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20220310-060047-RC01_433765713#) in <module>()
     19 
     20 for bom, enc in codec_enc_mapping.items():
---> 21     if contents.startswith(bom):
     22         encoding_type = enc
     23         is_unicode = True

[/usr/local/lib/python3.7/dist-packages/pandas/core/generic.py](https://0oauy9fmg1cc-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20220310-060047-RC01_433765713#) in __getattr__(self, name)
   5485         ):
   5486             return self[name]
-> 5487         return object.__getattribute__(self, name)
   5488 
   5489     def __setattr__(self, name: str, value) -> None:

AttributeError: 'Series' object has no attribute 'startswith'