Bug on 1.1.11
ririya opened this issue · 0 comments
ririya commented
Running into a bug with a sequential flow. The same is not happening on 1.1.10
def char_aug(data, ocr_error_dict, p_replace=0.1, p_insert=0.1, p_delete=0.1,
replace_char_p=0.05, insert_char_p=0.05, delete_char_p=0.05,
lowercase=False):
ocr_aug = nac.OcrAug(
aug_char_min=1,
aug_char_p=replace_char_p,
dict_of_path=ocr_error_dict,
)
insert_aug = nac.RandomCharAug(
action="insert",
aug_char_min=1,
aug_char_p=insert_char_p,
)
delete_aug = nac.RandomCharAug(
action="delete",
aug_char_min=1,
aug_char_p=delete_char_p,
stopwords_regex="^.$", # Don't do any replacements on single characters
)
ocr_sometimes = naf.Sometimes(ocr_aug, aug_p=p_replace)
insert_sometimes = naf.Sometimes(insert_aug, aug_p=p_insert)
delete_sometimes = naf.Sometimes(delete_aug, aug_p=p_delete)
sequential_flow = naf.Sequential([ocr_sometimes, insert_sometimes, delete_sometimes])
if lowercase:
data = data.lower()
augmented = sequential_flow.augment(data)[0]
Traceback (most recent call last):
File "/mnt/c/Users/Rafael/My Drive/codes/pam-ml-2.0/util/augmentation.py", line 206, in <module>
augmented = char_aug("abc def ghi jkl mno pqr stu wxy z 01234567890 [] ", ocr_error_dict,
File "/mnt/c/Users/Rafael/My Drive/codes/pam-ml-2.0/util/augmentation.py", line 174, in char_aug
augmented = sequential_flow.augment(data)[0]
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/flow/pipeline.py", line 58, in augment
augmented_results = [self._augment(data) for _ in range(n)]
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/flow/pipeline.py", line 58, in <listcomp>
augmented_results = [self._augment(data) for _ in range(n)]
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/flow/pipeline.py", line 101, in _augment
augmented_data = aug.augment(augmented_data, n=n, num_thread=num_thread)
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/flow/pipeline.py", line 58, in augment
augmented_results = [self._augment(data) for _ in range(n)]
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/flow/pipeline.py", line 58, in <listcomp>
augmented_results = [self._augment(data) for _ in range(n)]
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/flow/pipeline.py", line 101, in _augment
augmented_data = aug.augment(augmented_data, n=n, num_thread=num_thread)
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/base_augmenter.py", line 75, in augment
clean_data = self.clean(data)
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/augmenter/char/char_augmenter.py", line 40, in clean
return [d.strip() for d in data]
File "/home/rafael/anaconda3/envs/llm_env/lib/python3.8/site-packages/nlpaug/augmenter/char/char_augmenter.py", line 40, in <listcomp>
return [d.strip() for d in data]
AttributeError: 'list' object has no attribute 'strip'