def reward2(s1, s2):
indices = corpus[:]
tfi = TFIDF()
tfidf = tfi.get_tfidf(corpus)
score = tfi.relevancy(tfidf, indices, s1, s2)
return score + 1
print(wikipedia[3][0])
#return wikipedia
import copy
#def get_corpus():
corpus = [news.text]
titles = [soup.title]
print len(corpus)
for article in wikipedia:
# if article[0] in topics:
corpus.append(article[1])
titles.append(article[0])
print len(corpus)
#return corpus, titles
from tfidf import TFIDF
#def get_sim_docs():
tfi = TFIDF()
tfidf = tfi.get_tfidf(corpus)
sim_docs = []
for index, score in tfi.similar_docs(tfidf, 0, 5):
sim_docs.append((index, score))
print score, titles[index]
print "Most relevant document is " + titles[sim_docs[0][0]]
#return sim_docs
