NLP on Financial Statements

10-Ks

Criteria	Meet Specification
Get Documents	The function `get_documents` extracts the documents from the text.
Get Document Types	The function `get_document_type` returns the document type lowercased.

Criteria	Meet Specification
Lemmatize	The function `lemmatize_words` lemmatizes verbs.

Criteria	Meet Specification
Bag of Words	The function `get_bag_of_words` generates a bag of words from documents.
Jaccard Similarity	The function `get_jaccard_similarity` calculates the jaccard similarities for neighboring documents.
TFIDF	The function `tfidf` generate TFIDF vectors for each document.
Cosine Similarity	The function `get_cosine_similarity` calculates the cosine similarities for each neighboring TFIDF vector/document.