def test_pretokenized_words_frequencies(self):
model = TfDocumentModel(("wC", "wC", "WC", "wA", "WB", "wB"))
self.assertEqual(model.term_frequency("wa"), 1)
self.assertEqual(model.term_frequency("wb"), 2)
self.assertEqual(model.term_frequency("wc"), 3)
self.assertEqual(model.term_frequency("wd"), 0)
self.assertEqual(model.most_frequent_terms(), ("wc", "wb", "wa"))
def test_pretokenized_words_frequencies(self):
model = TfDocumentModel(("wC", "wC", "WC", "wA", "WB", "wB"))
self.assertEqual(model.term_frequency("wa"), 1)
self.assertEqual(model.term_frequency("wb"), 2)
self.assertEqual(model.term_frequency("wc"), 3)
self.assertEqual(model.term_frequency("wd"), 0)
self.assertEqual(model.most_frequent_terms(), ("wc", "wb", "wa"))
def test_pretokenized_words_frequencies():
model = TfDocumentModel(("wC", "wC", "WC", "wA", "WB", "wB"))
assert model.term_frequency("wa") == 1
assert model.term_frequency("wb") == 2
assert model.term_frequency("wc") == 3
assert model.term_frequency("wd") == 0
assert model.most_frequent_terms() == ("wc", "wb", "wa")
def test_pretokenized_words_frequencies():
model = TfDocumentModel(("wC", "wC", "WC", "wA", "WB", "wB"))
assert model.term_frequency("wa") == 1
assert model.term_frequency("wb") == 2
assert model.term_frequency("wc") == 3
assert model.term_frequency("wd") == 0
assert model.most_frequent_terms() == ("wc", "wb", "wa")
def test_term_frequency(self):
tokenizer = Tokenizer("english")
text = "wA wB wC wA wA wC wD wCwB"
model = TfDocumentModel(text, tokenizer)
self.assertEqual(model.term_frequency("wa"), 3)
self.assertEqual(model.term_frequency("wb"), 1)
self.assertEqual(model.term_frequency("wc"), 2)
self.assertEqual(model.term_frequency("wd"), 1)
self.assertEqual(model.term_frequency("wcwb"), 1)
self.assertEqual(model.term_frequency("we"), 0)
self.assertEqual(model.term_frequency("missing"), 0)
def test_term_frequency(self):
tokenizer = Tokenizer("english")
text = "wA wB wC wA wA wC wD wCwB"
model = TfDocumentModel(text, tokenizer)
self.assertEqual(model.term_frequency("wa"), 3)
self.assertEqual(model.term_frequency("wb"), 1)
self.assertEqual(model.term_frequency("wc"), 2)
self.assertEqual(model.term_frequency("wd"), 1)
self.assertEqual(model.term_frequency("wcwb"), 1)
self.assertEqual(model.term_frequency("we"), 0)
self.assertEqual(model.term_frequency("missing"), 0)
def test_term_frequency():
tokenizer = Tokenizer("english")
text = "wA wB wC wA wA wC wD wCwB"
model = TfDocumentModel(text, tokenizer)
assert model.term_frequency("wa") == 3
assert model.term_frequency("wb") == 1
assert model.term_frequency("wc") == 2
assert model.term_frequency("wd") == 1
assert model.term_frequency("wcwb") == 1
assert model.term_frequency("we") == 0
assert model.term_frequency("missing") == 0
def test_term_frequency():
tokenizer = Tokenizer("english")
text = "wA wB wC wA wA wC wD wCwB"
model = TfDocumentModel(text, tokenizer)
assert model.term_frequency("wa") == 3
assert model.term_frequency("wb") == 1
assert model.term_frequency("wc") == 2
assert model.term_frequency("wd") == 1
assert model.term_frequency("wcwb") == 1
assert model.term_frequency("we") == 0
assert model.term_frequency("missing") == 0