def test_count_matrix_specials_indexes():
specials = (UNK(), PAD())
vocab = Vocab(specials=specials)
for i in DATA:
vocab += i.split(" ")
vocab.finalize()
count_vectorizer = CountVectorizer(vocab=vocab)
count_vectorizer._init_special_indexes()
assert len(count_vectorizer._special_indexes) == 2
for i in specials:
assert vocab.stoi[i] in count_vectorizer._special_indexes
def test_specials_indexes():
specials = (UNK(), PAD())
vocab = Vocab(specials=specials)
for i in DATA:
vocab += i.split(" ")
vocab.finalize()
tfidf = TfIdfVectorizer(vocab=vocab)
tfidf._init_special_indexes()
assert len(tfidf._special_indexes) == 2
for i in specials:
assert vocab.stoi[i] in tfidf._special_indexes
def test_build_count_matrix_costum_specials_vocab_with_specials():
vocab = Vocab(specials=(UNK(), PAD()))
vocab_words = ["this", "is", "the", "first", "document"]
vocab += vocab_words
vocab.finalize()
tfidf = TfIdfVectorizer(vocab=vocab, specials=[PAD(), "this", "first"])
tfidf._init_special_indexes()
numericalized_data = get_numericalized_data(data=DATA, vocab=vocab)
count_matrix = tfidf._build_count_matrix(
data=numericalized_data, unpack_data=tfidf._get_tensor_values)
expected = np.array([[0, 1, 1, 1], [1, 1, 1, 2], [3, 1, 1, 0],
[0, 1, 1, 1]])
assert np.all(count_matrix == expected)
def test_label_field():
vocab = Vocab(specials=())
data = ["label_1", "label_2", "label_3"]
vocab += data
vocab.finalize()
label_field = LabelField("test_label_field", numericalizer=vocab)
preprocessed_data = [label_field.preprocess(label) for label in data]
for x in preprocessed_data:
_, data = x[0]
_, tokenized = data
assert label_field.numericalize(data) == vocab.stoi[tokenized]
def test_build_count_matrix_costum_specials_vocab_without_specials():
vocab = Vocab(specials=())
for i in DATA:
vocab += i.split(" ")
vocab.finalize()
tfidf = TfIdfVectorizer(
vocab=vocab,
specials=["the", "first", "second", "one", "third", "and"])
tfidf._init_special_indexes()
numericalized_data = get_numericalized_data(data=DATA, vocab=vocab)
count_matrix = tfidf._build_count_matrix(
data=numericalized_data, unpack_data=tfidf._get_tensor_values)
expected = np.array([[1, 1, 1], [1, 1, 2], [1, 1, 0], [1, 1, 1]])
assert np.all(count_matrix == expected)
def test_count_vectorizer_transform_tokens_tensor():
vocab = Vocab(specials=())
for i in DATA:
vocab += i.split(" ")
vocab.finalize()
count_vectorizer = CountVectorizer(vocab=vocab)
count_vectorizer.fit(dataset=None, field=None)
numericalized_data = get_numericalized_data(data=DATA, vocab=vocab)
bow = count_vectorizer.transform(numericalized_data).todense()
expected = np.array([
[1, 1, 1, 1, 1, 0, 0, 0, 0],
[1, 1, 1, 2, 0, 1, 0, 0, 0],
[1, 1, 1, 0, 0, 0, 1, 1, 1],
[1, 1, 1, 1, 1, 0, 0, 0, 0],
])
assert np.allclose(a=bow, b=expected, rtol=0, atol=1.0e-6)
def test_build_count_matrix_from_tensor_with_specials():
vocab = Vocab(specials=(UNK(), PAD()))
for i in DATA:
vocab += i.split(" ")
vocab.finalize()
tfidf = TfIdfVectorizer(vocab=vocab)
tfidf._init_special_indexes()
numericalized_data = get_numericalized_data(data=DATA, vocab=vocab)
count_matrix = tfidf._build_count_matrix(
data=numericalized_data, unpack_data=tfidf._get_tensor_values)
expected = np.array([
[1, 1, 1, 1, 1, 0, 0, 0, 0],
[1, 1, 1, 2, 0, 1, 0, 0, 0],
[1, 1, 1, 0, 0, 0, 1, 1, 1],
[1, 1, 1, 1, 1, 0, 0, 0, 0],
])
assert np.all(count_matrix == expected)
