def test_swap(self):
texts = ['The quick brown fox jumps over the lazy dog', 'testing']
aug = RandomCharAug(action="swap", min_char=1)
for text in texts:
tokens = list(text)
orig_token_freq = {}
for w in tokens:
orig_token_freq[w] = tokens.count(w)
augmented_cnt = 0
augmented_text = text
# https://github.com/makcedward/nlpaug/issues/77
for i in range(10):
augmented_text = aug.augment(augmented_text)
tokens = list(augmented_text)
aug_token_freq = {}
for w in tokens:
aug_token_freq[w] = tokens.count(w)
tokens = aug.tokenizer(text)
augmented_tokens = aug.tokenizer(augmented_text)
for token, augmented_token in zip(tokens, augmented_tokens):
if token != augmented_token:
augmented_cnt += 1
self.assertNotEqual(text, augmented_text)
self.assertTrue(len(texts) > 0)
def test_substitute_multi_words(self):
texts = ['The quick brown fox jumps over the lazy dog']
aug = RandomCharAug(action='substitute', min_char=1)
for text in texts:
augmented_cnt = 0
augmented_text = aug.augment(text)
tokens = aug.tokenizer(text)
augmented_tokens = aug.tokenizer(augmented_text)
for token, augmented_token in zip(tokens, augmented_tokens):
if token != augmented_token:
augmented_cnt += 1
self.assertLess(augmented_cnt, len(tokens))
self.assertNotEqual(text, augmented_text)
self.assertTrue(len(texts) > 0)
def test_swap(self):
texts = ['The quick brown fox jumps over the lazy dog']
aug = RandomCharAug(action=Action.SWAP)
for text in texts:
augmented_cnt = 0
augmented_text = aug.augment(text)
tokens = aug.tokenizer(text)
augmented_tokens = aug.tokenizer(augmented_text)
for token, augmented_token in zip(tokens, augmented_tokens):
if token != augmented_token:
augmented_cnt += 1
self.assertLess(augmented_cnt, len(tokens))
self.assertNotEqual(text, augmented_text)
self.assertTrue(len(texts) > 0)
