本例来自mining social web
from math import log
# XXX: Enter in a query term from the corpus variable
QUERY_TERMS = ['mr.', 'green']
def tf(term, doc, normalize=True):
doc = doc.lower().split()
if normalize:
return doc.count(term.lower()) / float(len(doc))
else:
return doc.count(term.lower()) / 1.0
def idf(term, corpus):
num_texts_with_term = len([True for text in corpus if term.lower()
in text.lower().split()])
# tf-idf calc involves multiplying against a tf value less than 0, so it's
# necessary to return a value greater than 1 for consistent scoring.
# (Multiplying two values less than 1 returns a value less than each of
# them.)
try:
return 1.0 + log(float(len(corpus)) / num_texts_with_term)
except ZeroDivisionError:
return 1.0
def tf_idf(term, doc, corpus):
return tf(term, doc) * idf(term, corpus)
corpus = \
{'a': 'Mr. Green killed Colonel Mustard in the study with the candlestick. \
Mr. Green is not a very nice fellow.',
'b': 'Professor Plum has a green plant in his study.',
'c': "Miss Scarlett watered Professor Plum's green plant while he was away \
from his office last week."}
for (k, v) in sorted(corpus.items()):
print k, ':', v
# Score queries by calculating cumulative tf_idf score for each term in query
query_scores = {'a': 0, 'b': 0, 'c': 0}
for term in [t.lower() for t in QUERY_TERMS]:
for doc in sorted(corpus):
print 'TF(%s): %s' % (doc, term), tf(term, corpus[doc])
print 'IDF: %s' % (term, ), idf(term, corpus.values())
for doc in sorted(corpus):
score = tf_idf(term, corpus[doc], corpus.values())
print 'TF-IDF(%s): %s' % (doc, term), score
query_scores[doc] += score
print "Overall TF-IDF scores for query '%s'" % (' '.join(QUERY_TERMS), )
for (doc, score) in sorted(query_scores.items()):
print doc, score