Create a gist now

Instantly share code, notes, and snippets.

What would you like to do?
PageRank for text summarization
import networkx as nx
import numpy as np
from nltk.tokenize.punkt import PunktSentenceTokenizer
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
def textrank(document):
sentence_tokenizer = PunktSentenceTokenizer()
sentences = sentence_tokenizer.tokenize(document)
bow_matrix = CountVectorizer().fit_transform(sentences)
normalized = TfidfTransformer().fit_transform(bow_matrix)
similarity_graph = normalized * normalized.T
nx_graph = nx.from_scipy_sparse_matrix(similarity_graph)
scores = nx.pagerank(nx_graph)
return sorted(((scores[i],s) for i,s in enumerate(sentences)), reverse=True)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment