nimare.annotate.text.generate_cooccurrence

generate_cooccurrence(text_df, text_column='abstract', vocabulary=None, window=5)[source]

Build co-occurrence matrix from documents. Not the same approach as used by the GloVe model.

Parameters:
  • text_df ((D x 2) pandas.DataFrame) – A DataFrame with two columns (‘id’ and ‘text’). D = document.
  • vocabulary (list, optional) – List of words in vocabulary to extract from text.
  • window (int, optional) – Window size for cooccurrence. Words which appear within window words of one another co-occur.
Returns:

df – One cooccurrence matrix per document in text_df.

Return type:

(V, V, D) pandas.Panel