def test_tfidf(self):
# Assert tf-idf for documents not in a corpus.
v = [[0.0, 0.1, 0.2], [0.2, 0.1, 0.0]]
v = vector.tf_idf(v)
self.assertAlmostEqual(v[0][2], 0.14, places=2)
self.assertAlmostEqual(v[1][0], 0.14, places=2)
print "pattern.vector.tf_idf()"
def test_tfidf(self):
# Assert tf-idf for documents not in a corpus.
v = [[0.0,0.1,0.2], [0.2,0.1,0.0]]
v = vector.tf_idf(v)
self.assertAlmostEqual(v[0][2], 0.14, places=2)
self.assertAlmostEqual(v[1][0], 0.14, places=2)
print "pattern.vector.tf_idf()"
def test_tfidf(self):
# Assert tf-idf for documents not in a model.
v = [[0.0, 0.4, 0.6], [0.6, 0.4, 0.0]]
v = [dict(enumerate(v)) for v in v]
m = vector.Model([vector.Document(x) for x in v], weight=vector.TFIDF)
v = [vector.sparse(v) for v in vector.tf_idf(v)]
self.assertEqual(sorted(m[0].vector.items()), sorted(v[0].items()))
self.assertAlmostEqual(v[0][2], 0.42, places=2)
self.assertAlmostEqual(v[1][0], 0.42, places=2)
print("pattern.vector.tf_idf()")
def test_tfidf(self):
# Assert tf-idf for documents not in a model.
v = [[0.0, 0.4, 0.6], [0.6, 0.4, 0.0]]
v = [dict(enumerate(v)) for v in v]
m = vector.Model([vector.Document(x) for x in v], weight=vector.TFIDF)
v = [vector.sparse(v) for v in vector.tf_idf(v)]
self.assertEqual(sorted(m[0].vector.items()), sorted(v[0].items()))
self.assertAlmostEqual(v[0][2], 0.42, places=2)
self.assertAlmostEqual(v[1][0], 0.42, places=2)
print("pattern.vector.tf_idf()")
