lsa.py 文件源码

def search_query(self, query):
        """
        search for query and find most related document for query
        http://webhome.cs.uvic.ca/~thomo/svd.pdf
        """

        def topN(similarities, N=5):
            return np.argsort(similarities)[::-1][:N]

        words = query.split(" ")
        tokens_ids = []
        for word in words:
            try:
                token_id = self.tokens_mapping[word]
            except KeyError:
                print("Token not found in tokens mapping dict")
            else:
                tokens_ids.append(token_id)

        query_representation = np.mean(self.tokens_representation[tokens_ids,:], axis=0)
        similarities = cosine_similarity(query_representation, self.documents_representation)
        topN_documents =[self.documents_mapping[index] for index in topN(similarities[0])] 
        return topN_documents