sergegoussev / nlpru Goto Github PK

    def Get_similarity(self,
                       docs_list,
                       use_normal_form=False,
                       clean_documents=True,
                       stop_words=None,
                       similarity_to='first',
                       use_ngrams=True):
        """
        Get cosine similarity of documents. Uses sklearn's library and the 
        tf-idf approach (TfidfVectorizer()) to calculate result

        (unique) params:
            - stop_words: list (or set) of stop words to use
            - similarity_to: 'first' or 'all' expected

        returns: 
            depending on 'similarity_to' param, either similarity row 
            vector of the first document to all others docs is returned, or
            (if 'All' is specified) matrix of of all docs against all others
        """
        if clean_documents == True:
            docs_list = self.__clean_docs__(docs_list)
        if use_normal_form == True:
            docs_list = self.__normalize_docs__(docs_list)
        if use_ngrams == True:
            tfidf_vectorizer = TfidfVectorizer(
                stop_words=stop_words, ngram_range=(2, 3))
        else:
            tfidf_vectorizer = TfidfVectorizer(stop_words=stop_words)
        tfidf_matrix = tfidf_vectorizer.fit_transform(docs_list)
        cosine_similarity_matrix = cosine_similarity(
            tfidf_matrix[0:1], tfidf_matrix)
        return cosine_similarity_matrix