KeyError: 21021

[MayZ7]

Hi,

I had this error message when trying to reduce my topic size. Any suggestion on that? Thanks!

reduced_topic=model.hierarchical_topic_reduction(num_topics=30),

File ~/miniconda3/envs/py310/lib/python3.10/site-packages/pandas/core/indexes/base.py:3081, in Index.get_loc(self, key, method, tolerance)
3080 try:
-> 3081 return self._engine.get_loc(casted_key)
3082 except KeyError as err:

File pandas/_libs/index.pyx:70, in pandas._libs.index.IndexEngine.get_loc()

File pandas/_libs/index.pyx:101, in pandas._libs.index.IndexEngine.get_loc()

File pandas/_libs/hashtable_class_helper.pxi:1625, in pandas._libs.hashtable.Int64HashTable.get_item()

File pandas/_libs/hashtable_class_helper.pxi:1632, in pandas._libs.hashtable.Int64HashTable.get_item()

KeyError: 21021

The above exception was the direct cause of the following exception:

KeyError Traceback (most recent call last)
Cell In[10], line 2
1 ##reduce the number of topics generated from Top2Vec if the machine autormatically generates to many topcis##
----> 2 reduced_topic=model.hierarchical_topic_reduction(num_topics=30)

File ~/miniconda3/envs/py310/lib/python3.10/site-packages/top2vec/Top2Vec.py:1882, in Top2Vec.hierarchical_topic_reduction(self, num_topics)
1878 doc_top = self._calculate_documents_topic(topic_vectors=top_vecs,
1879 document_vectors=self.document_vectors,
1880 dist=False)
1881 topic_sizes = pd.Series(doc_top).value_counts()
-> 1882 top_sizes = [topic_sizes[i] for i in range(0, len(topic_sizes))]
1884 else:
1885 smallest_size = top_sizes.pop(smallest)

File ~/miniconda3/envs/py310/lib/python3.10/site-packages/top2vec/Top2Vec.py:1882, in (.0)
1878 doc_top = self._calculate_documents_topic(topic_vectors=top_vecs,
1879 document_vectors=self.document_vectors,
1880 dist=False)
1881 topic_sizes = pd.Series(doc_top).value_counts()
-> 1882 top_sizes = [topic_sizes[i] for i in range(0, len(topic_sizes))]
1884 else:
1885 smallest_size = top_sizes.pop(smallest)

File ~/miniconda3/envs/py310/lib/python3.10/site-packages/pandas/core/series.py:853, in Series.getitem(self, key)
850 return self._values[key]
852 elif key_is_scalar:
--> 853 return self._get_value(key)
855 if is_hashable(key):
856 # Otherwise index.get_value will raise InvalidIndexError
857 try:
858 # For labels that don't resolve as scalars like tuples and frozensets

File ~/miniconda3/envs/py310/lib/python3.10/site-packages/pandas/core/series.py:961, in Series._get_value(self, label, takeable)
958 return self._values[label]
960 # Similar to Index.get_value, but we do not fall back to positional
--> 961 loc = self.index.get_loc(label)
962 return self.index._get_values_for_loc(self, loc, label)

File ~/miniconda3/envs/py310/lib/python3.10/site-packages/pandas/core/indexes/base.py:3083, in Index.get_loc(self, key, method, tolerance)
3081 return self._engine.get_loc(casted_key)
3082 except KeyError as err:
-> 3083 raise KeyError(key) from err
3085 if tolerance is not None:
3086 tolerance = self._convert_tolerance(tolerance, np.asarray(key))