def segmenter(max_split_length: int = 20, validate: bool = True):
"""
Load Segmenter class.
Parameters
----------
max_split_length: int, (default=20)
max length of words in a sentence to segment
validate: bool, optional (default=True)
if True, malaya will check model availability and download if not available.
Returns
-------
_Segmenter : malaya.preprocessing._Segmenter class
"""
if validate:
check_file(PATH_PREPROCESSING[1], S3_PATH_PREPROCESSING[1])
else:
if not check_available(PATH_PREPROCESSING[1]):
raise Exception(
'preprocessing is not available, please `validate = True`')
if validate:
check_file(PATH_PREPROCESSING[2], S3_PATH_PREPROCESSING[2])
else:
if not check_available(PATH_PREPROCESSING[2]):
raise Exception(
'preprocessing is not available, please `validate = True`')
return _Segmenter(max_split_length=max_split_length)
def probability(sentence_piece: bool = False, **kwargs):
"""
Train a Probability Spell Corrector.
Parameters
----------
sentence_piece: bool, optional (default=False)
if True, reduce possible augmentation states using sentence piece.
validate: bool, optional (default=True)
if True, malaya will check model availability and download if not available.
Returns
-------
_SpellCorrector: malaya.spell._SpellCorrector class
"""
check_file(PATH_NGRAM[1], S3_PATH_NGRAM[1], **kwargs)
tokenizer = None
if sentence_piece:
if validate:
check_file(PATH_NGRAM['sentencepiece'],
S3_PATH_NGRAM['sentencepiece'])
else:
if not check_available(PATH_NGRAM[1]):
raise Exception(
'sentence piece is not available, please `validate = True`'
)
vocab = PATH_NGRAM['sentencepiece']['vocab']
vocab_model = PATH_NGRAM['sentencepiece']['model']
tokenizer = load_sentencepiece(vocab, vocab_model)
with open(PATH_NGRAM[1]['model']) as fopen:
corpus = json.load(fopen)
return _SpellCorrector(corpus, tokenizer)
def shortform(
word: str,
augment_vowel: bool = True,
augment_consonant: bool = True,
prob_delete_vowel: float = 0.5,
validate: bool = True,
):
"""
augmenting a formal word into socialmedia form. Purposely typo, purposely delete some vowels,
purposely replaced some subwords into slang subwords.
Parameters
----------
word: str
augment_vowel: bool, (default=True)
if True, will augment vowels for each samples generated.
augment_consonant: bool, (default=True)
if True, will augment consonants for each samples generated.
prob_delete_vowel: float, (default=0.5)
probability to delete a vowel.
validate: bool, optional (default=True)
if True, malaya will check model availability and download if not available.
Returns
-------
result: list
"""
if not 0 < prob_delete_vowel < 1:
raise Exception(
'prob_delete_vowel must be bigger than 0 and less than 1'
)
word = simple_textcleaning(word)
if not len(word):
raise Exception('word is too short to augment shortform.')
if validate:
check_file(PATH_NGRAM['sentencepiece'], S3_PATH_NGRAM['sentencepiece'])
else:
if not check_available(PATH_NGRAM[1]):
raise Exception(
'sentence piece is not available, please `validate = True`'
)
vocab = PATH_NGRAM['sentencepiece']['vocab']
vocab_model = PATH_NGRAM['sentencepiece']['model']
tokenizer = load_sentencepiece(vocab, vocab_model)
replace_consonants = {
'n': 'm',
't': 'y',
'r': 't',
'g': 'h',
'j': 'k',
'k': 'l',
'd': 's',
'd': 'f',
'g': 'f',
'b': 'n',
}
replace_vowels = {'u': 'i', 'i': 'o', 'o': 'u'}
results = [word]
if len(word) > 1:
if word[-1] == 'a' and word[-2] in consonants:
results.append(word[:-1] + 'e')
if word[0] == 'f' and word[-1] == 'r':
results.append('p' + words[1:])
if word[-2] in consonants and word[-1] in vowels:
results.append(word + 'k')
if word[-2] in vowels and word[-1] == 'h':
results.append(word[:-1])
if len(word) > 2:
if word[-3] in consonants and word[-2:] == 'ar':
results.append(words[:-2] + 'o')
if word[0] == 'h' and word[1] in vowels and word[2] in consonants:
results.append(word[1:])
if word[-3] in consonants and word[-2:] == 'ng':
results.append(word[:-2] + 'g')
if word[1:3] == 'ng':
results.append(word[:1] + x[2:])
if augment_consonant:
result_consonants = []
for k, v in replace_consonants.items():
for r in results:
result_consonants.extend([r.replace(k, v), r.replace(v, k)])
results.extend(result_consonants)
if augment_vowel:
result_vowels = []
for k, v in replace_vowels.items():
for r in results:
result_vowels.extend([r.replace(k, v), r.replace(v, k)])
results.extend(result_vowels)
result_deleted = []
for s in results:
deleted = []
for c in s:
if random.random() > prob_delete_vowel and c in vowels:
continue
else:
deleted.append(c)
result_deleted.append(''.join(deleted))
results.extend(result_deleted)
filtered = []
for s in results:
t = tokenizer.tokenize(s)
if len(t) == 1:
filtered.append(s)
continue
if t[0] == '▁':
continue
if any([len(w) < 3 for w in t]):
continue
filtered.append(s)
return list(set(filtered))
def preprocessing(
normalize: List[str] = [
'url',
'email',
'percent',
'money',
'phone',
'user',
'time',
'date',
'number',
],
annotate: List[str] = [
'allcaps',
'elongated',
'repeated',
'emphasis',
'censored',
'hashtag',
],
lowercase: bool = True,
fix_unidecode: bool = True,
expand_hashtags: bool = True,
expand_english_contractions: bool = True,
translate_english_to_bm: bool = True,
remove_postfix: bool = True,
maxlen_segmenter: int = 20,
validate: bool = True,
speller=None,
):
"""
Load Preprocessing class.
Parameters
----------
normalize: list
normalizing tokens, can check all supported normalizing at malaya.preprocessing.get_normalize()
annotate: list
annonate tokens <open></open>, only accept ['hashtag', 'allcaps', 'elongated', 'repeated', 'emphasis', 'censored']
lowercase: bool
fix_unidecode: bool
expand_hashtags: bool
expand hashtags using Viterbi algorithm, #mondayblues == monday blues
expand_english_contractions: bool
expand english contractions
translate_english_to_bm: bool
translate english words to bahasa malaysia words
remove_postfix: bool
remove postfix from a word, faster way to get root word
speller: object
spelling correction object, need to have a method `correct`
validate: bool, optional (default=True)
if True, malaya will check model availability and download if not available.
Returns
-------
_Preprocessing : malaya.preprocessing._Preprocessing class
"""
if any([e not in _normalize for e in normalize]):
raise ValueError(
'normalize element not able to recognize, supported normalization can check at get_normalize()'
)
if any([e not in _annotate for e in annotate]):
raise ValueError(
"annotate only accept ['hashtag', 'allcaps', 'elongated', 'repeated', 'emphasis', 'censored']"
)
if speller is not None:
if not hasattr(speller, 'correct') and not hasattr(
speller, 'normalize_elongated'):
raise ValueError(
'speller must has `correct` or `normalize_elongated` method')
if expand_hashtags:
if validate:
check_file(PATH_PREPROCESSING[1], S3_PATH_PREPROCESSING[1])
else:
if not check_available(PATH_PREPROCESSING[1]):
raise Exception(
'preprocessing is not available, please `validate = True`')
if validate:
check_file(PATH_PREPROCESSING[2], S3_PATH_PREPROCESSING[2])
else:
if not check_available(PATH_PREPROCESSING[2]):
raise Exception(
'preprocessing is not available, please `validate = True`')
if translate_english_to_bm:
if validate:
check_file(
PATH_PREPROCESSING['english-malay'],
S3_PATH_PREPROCESSING['english-malay'],
)
else:
if not check_available(PATH_PREPROCESSING['english-malay']):
raise Exception(
'translator english-malay is not available, please `validate = True`'
)
with open(PATH_PREPROCESSING['english-malay']['model']) as fopen:
translator = json.load(fopen)
else:
translator = None
return _Preprocessing(
normalize=normalize,
annotate=annotate,
lowercase=lowercase,
fix_unidecode=fix_unidecode,
expand_hashtags=expand_hashtags,
expand_english_contractions=expand_english_contractions,
remove_postfix=remove_postfix,
maxlen_segmenter=maxlen_segmenter,
translator=translator,
speller=speller,
)
