def process(self,
paths: Union[str, Dict[str, str]],
src_vocab_opt: VocabularyOption = None,
tgt_vocab_opt: VocabularyOption = None,
src_embed_opt: EmbeddingOption = None,
char_level_op=False):
paths = check_dataloader_paths(paths)
datasets = {}
info = DataBundle()
for name, path in paths.items():
dataset = self.load(path)
datasets[name] = dataset
def wordtochar(words):
chars = []
for word in words:
word = word.lower()
for char in word:
chars.append(char)
chars.append('')
chars.pop()
return chars
input_name, target_name = 'words', 'target'
info.vocabs={}
# 就分隔为char形式
if char_level_op:
for dataset in datasets.values():
dataset.apply_field(wordtochar, field_name="words", new_field_name='chars')
src_vocab = Vocabulary() if src_vocab_opt is None else Vocabulary(**src_vocab_opt)
src_vocab.from_dataset(datasets['train'], field_name='words')
src_vocab.index_dataset(*datasets.values(), field_name='words')
tgt_vocab = Vocabulary(unknown=None, padding=None) \
if tgt_vocab_opt is None else Vocabulary(**tgt_vocab_opt)
tgt_vocab.from_dataset(datasets['train'], field_name='target')
tgt_vocab.index_dataset(*datasets.values(), field_name='target')
info.vocabs = {
"words": src_vocab,
"target": tgt_vocab
}
info.datasets = datasets
if src_embed_opt is not None:
embed = EmbedLoader.load_with_vocab(**src_embed_opt, vocab=src_vocab)
info.embeddings['words'] = embed
for name, dataset in info.datasets.items():
dataset.set_input("words")
dataset.set_target("target")
return info
def process(self, paths, **kwargs):
data_info = DataBundle()
for name in ['train', 'test', 'dev']:
data_info.datasets[name] = self.load(paths[name])
config = Config()
vocab = Vocabulary().from_dataset(*data_info.datasets.values(),
field_name='sentences')
vocab.build_vocab()
word2id = vocab.word2idx
char_dict = preprocess.get_char_dict(config.char_path)
data_info.vocabs = vocab
genres = {
g: i
for i, g in enumerate(["bc", "bn", "mz", "nw", "pt", "tc", "wb"])
}
for name, ds in data_info.datasets.items():
ds.apply(
lambda x: preprocess.doc2numpy(x['sentences'],
word2id,
char_dict,
max(config.filter),
config.max_sentences,
is_train=name == 'train')[0],
new_field_name='doc_np')
ds.apply(
lambda x: preprocess.doc2numpy(x['sentences'],
word2id,
char_dict,
max(config.filter),
config.max_sentences,
is_train=name == 'train')[1],
new_field_name='char_index')
ds.apply(
lambda x: preprocess.doc2numpy(x['sentences'],
word2id,
char_dict,
max(config.filter),
config.max_sentences,
is_train=name == 'train')[2],
new_field_name='seq_len')
ds.apply(lambda x: preprocess.speaker2numpy(
x["speakers"], config.max_sentences, is_train=name == 'train'),
new_field_name='speaker_ids_np')
ds.apply(lambda x: genres[x["doc_key"][:2]],
new_field_name='genre')
ds.set_ignore_type('clusters')
ds.set_padder('clusters', None)
ds.set_input("sentences", "doc_np", "speaker_ids_np", "genre",
"char_index", "seq_len")
ds.set_target("clusters")
# train_dev, test = self.ds.split(348 / (2802 + 343 + 348), shuffle=False)
# train, dev = train_dev.split(343 / (2802 + 343), shuffle=False)
return data_info
def process(self, paths: Union[str, Dict[str, str]],
train_ds: Iterable[str] = None,
src_vocab_op: VocabularyOption = None,
tgt_vocab_op: VocabularyOption = None,
embed_opt: EmbeddingOption = None,
char_level_op=False,
split_dev_op=True
):
paths = check_dataloader_paths(paths)
datasets = {}
info = DataBundle(datasets=self.load(paths))
src_vocab = Vocabulary() if src_vocab_op is None else Vocabulary(**src_vocab_op)
tgt_vocab = Vocabulary(unknown=None, padding=None) \
if tgt_vocab_op is None else Vocabulary(**tgt_vocab_op)
_train_ds = [info.datasets[name]
for name in train_ds] if train_ds else info.datasets.values()
def wordtochar(words):
chars = []
for word in words:
word = word.lower()
for char in word:
chars.append(char)
chars.append('')
chars.pop()
return chars
input_name, target_name = 'words', 'target'
info.vocabs={}
#就分隔为char形式
if char_level_op:
for dataset in info.datasets.values():
dataset.apply_field(wordtochar, field_name="words",new_field_name='chars')
# if embed_opt is not None:
# embed = EmbedLoader.load_with_vocab(**embed_opt, vocab=vocab)
# info.embeddings['words'] = embed
else:
src_vocab.from_dataset(*_train_ds, field_name=input_name)
src_vocab.index_dataset(*info.datasets.values(),field_name=input_name, new_field_name=input_name)
info.vocabs[input_name]=src_vocab
tgt_vocab.from_dataset(*_train_ds, field_name=target_name)
tgt_vocab.index_dataset(
*info.datasets.values(),
field_name=target_name, new_field_name=target_name)
info.vocabs[target_name]=tgt_vocab
if split_dev_op:
info.datasets['train'], info.datasets['dev'] = info.datasets['train'].split(0.1, shuffle=False)
for name, dataset in info.datasets.items():
dataset.set_input("words")
dataset.set_target("target")
return info
def process(self,
paths: Union[str, Dict[str, str]],
src_vocab_opt: VocabularyOption = None,
tgt_vocab_opt: VocabularyOption = None,
src_embed_opt: EmbeddingOption = None):
paths = check_dataloader_paths(paths)
datasets = {}
info = DataBundle()
for name, path in paths.items():
dataset = self.load(path)
datasets[name] = dataset
src_vocab = Vocabulary() if src_vocab_opt is None else Vocabulary(**src_vocab_opt)
src_vocab.from_dataset(datasets['train'], field_name='words')
src_vocab.index_dataset(*datasets.values(), field_name='words')
tgt_vocab = Vocabulary(unknown=None, padding=None) \
if tgt_vocab_opt is None else Vocabulary(**tgt_vocab_opt)
tgt_vocab.from_dataset(datasets['train'], field_name='target')
tgt_vocab.index_dataset(*datasets.values(), field_name='target')
info.vocabs = {
"words": src_vocab,
"target": tgt_vocab
}
info.datasets = datasets
if src_embed_opt is not None:
embed = EmbedLoader.load_with_vocab(**src_embed_opt, vocab=src_vocab)
info.embeddings['words'] = embed
for name, dataset in info.datasets.items():
dataset.set_input("words")
dataset.set_target("target")
return info
def process(self,
paths,
train_ds: Iterable[str] = None,
src_vocab_op: VocabularyOption = None,
tgt_vocab_op: VocabularyOption = None,
src_embed_op: EmbeddingOption = None):
input_name, target_name = 'words', 'target'
src_vocab = Vocabulary() if src_vocab_op is None else Vocabulary(**src_vocab_op)
tgt_vocab = Vocabulary(unknown=None, padding=None) \
if tgt_vocab_op is None else Vocabulary(**tgt_vocab_op)
info = DataBundle(datasets=self.load(paths))
_train_ds = [info.datasets[name]
for name in train_ds] if train_ds else info.datasets.values()
src_vocab.from_dataset(*_train_ds, field_name=input_name)
tgt_vocab.from_dataset(*_train_ds, field_name=target_name)
src_vocab.index_dataset(
*info.datasets.values(),
field_name=input_name, new_field_name=input_name)
tgt_vocab.index_dataset(
*info.datasets.values(),
field_name=target_name, new_field_name=target_name)
info.vocabs = {
input_name: src_vocab,
target_name: tgt_vocab
}
if src_embed_op is not None:
src_embed_op.vocab = src_vocab
init_emb = EmbedLoader.load_with_vocab(**src_embed_op)
info.embeddings[input_name] = init_emb
for name, dataset in info.datasets.items():
dataset.set_input(input_name)
dataset.set_target(target_name)
return info
def process(
self,
paths: Union[str, Dict[str, str]],
dataset_name: str = None,
to_lower=False,
seq_len_type: str = None,
bert_tokenizer: str = None,
cut_text: int = None,
get_index=True,
auto_pad_length: int = None,
auto_pad_token: str = '<pad>',
set_input: Union[list, str, bool] = True,
set_target: Union[list, str, bool] = True,
concat: Union[str, list, bool] = None,
) -> DataBundle:
"""
:param paths: str或者Dict[str, str]。如果是str，则为数据集所在的文件夹或者是全路径文件名：如果是文件夹，
则会从self.paths里面找对应的数据集名称与文件名。如果是Dict，则为数据集名称（如train、dev、test）和
对应的全路径文件名。
:param str dataset_name: 如果在paths里传入的是一个数据集的全路径文件名，那么可以用dataset_name来定义
这个数据集的名字，如果不定义则默认为train。
:param bool to_lower: 是否将文本自动转为小写。默认值为False。
:param str seq_len_type: 提供的seq_len类型，支持 ``seq_len`` ：提供一个数字作为句子长度； ``mask`` :
提供一个0/1的mask矩阵作为句子长度； ``bert`` ：提供segment_type_id（第一个句子为0，第二个句子为1）和
attention mask矩阵（0/1的mask矩阵）。默认值为None，即不提供seq_len
:param str bert_tokenizer: bert tokenizer所使用的词表所在的文件夹路径
:param int cut_text: 将长于cut_text的内容截掉。默认为None，即不截。
:param bool get_index: 是否需要根据词表将文本转为index
:param int auto_pad_length: 是否需要将文本自动pad到一定长度（超过这个长度的文本将会被截掉），默认为不会自动pad
:param str auto_pad_token: 自动pad的内容
:param set_input: 如果为True，则会自动将相关的field（名字里含有Const.INPUT的）设置为input，如果为False
则不会将任何field设置为input。如果传入str或者List[str]，则会根据传入的内容将相对应的field设置为input，
于此同时其他field不会被设置为input。默认值为True。
:param set_target: set_target将控制哪些field可以被设置为target，用法与set_input一致。默认值为True。
:param concat: 是否需要将两个句子拼接起来。如果为False则不会拼接。如果为True则会在两个句子之间插入一个<sep>。
如果传入一个长度为4的list，则分别表示插在第一句开始前、第一句结束后、第二句开始前、第二句结束后的标识符。如果
传入字符串 ``bert`` ，则会采用bert的拼接方式，等价于['[CLS]', '[SEP]', '', '[SEP]'].
:return:
"""
if isinstance(set_input, str):
set_input = [set_input]
if isinstance(set_target, str):
set_target = [set_target]
if isinstance(set_input, bool):
auto_set_input = set_input
else:
auto_set_input = False
if isinstance(set_target, bool):
auto_set_target = set_target
else:
auto_set_target = False
if isinstance(paths, str):
if os.path.isdir(paths):
path = {
n: os.path.join(paths, self.paths[n])
for n in self.paths.keys()
}
else:
path = {
dataset_name if dataset_name is not None else 'train':
paths
}
else:
path = paths
data_info = DataBundle()
for data_name in path.keys():
data_info.datasets[data_name] = self._load(path[data_name])
for data_name, data_set in data_info.datasets.items():
if auto_set_input:
data_set.set_input(Const.INPUTS(0), Const.INPUTS(1))
if auto_set_target:
if Const.TARGET in data_set.get_field_names():
data_set.set_target(Const.TARGET)
if to_lower:
for data_name, data_set in data_info.datasets.items():
data_set.apply(
lambda x: [w.lower() for w in x[Const.INPUTS(0)]],
new_field_name=Const.INPUTS(0),
is_input=auto_set_input)
data_set.apply(
lambda x: [w.lower() for w in x[Const.INPUTS(1)]],
new_field_name=Const.INPUTS(1),
is_input=auto_set_input)
if bert_tokenizer is not None:
if bert_tokenizer.lower() in PRETRAINED_BERT_MODEL_DIR:
PRETRAIN_URL = _get_base_url('bert')
model_name = PRETRAINED_BERT_MODEL_DIR[bert_tokenizer]
model_url = PRETRAIN_URL + model_name
model_dir = cached_path(model_url)
# 检查是否存在
elif os.path.isdir(bert_tokenizer):
model_dir = bert_tokenizer
else:
raise ValueError(
f"Cannot recognize BERT tokenizer from {bert_tokenizer}.")
words_vocab = Vocabulary(padding='[PAD]', unknown='[UNK]')
with open(os.path.join(model_dir, 'vocab.txt'), 'r') as f:
lines = f.readlines()
lines = [line.strip() for line in lines]
words_vocab.add_word_lst(lines)
words_vocab.build_vocab()
tokenizer = BertTokenizer.from_pretrained(model_dir)
for data_name, data_set in data_info.datasets.items():
for fields in data_set.get_field_names():
if Const.INPUT in fields:
data_set.apply(
lambda x: tokenizer.tokenize(' '.join(x[fields])),
new_field_name=fields,
is_input=auto_set_input)
if isinstance(concat, bool):
concat = 'default' if concat else None
if concat is not None:
if isinstance(concat, str):
CONCAT_MAP = {
'bert': ['[CLS]', '[SEP]', '', '[SEP]'],
'default': ['', '<sep>', '', '']
}
if concat.lower() in CONCAT_MAP:
concat = CONCAT_MAP[concat]
else:
concat = 4 * [concat]
assert len(concat) == 4, \
f'Please choose a list with 4 symbols which at the beginning of first sentence ' \
f'the end of first sentence, the begin of second sentence, and the end of second' \
f'sentence. Your input is {concat}'
for data_name, data_set in data_info.datasets.items():
data_set.apply(
lambda x: [concat[0]] + x[Const.INPUTS(0)] + [concat[
1]] + [concat[2]] + x[Const.INPUTS(1)] + [concat[3]],
new_field_name=Const.INPUT)
data_set.apply(
lambda x: [w for w in x[Const.INPUT] if len(w) > 0],
new_field_name=Const.INPUT,
is_input=auto_set_input)
if seq_len_type is not None:
if seq_len_type == 'seq_len': #
for data_name, data_set in data_info.datasets.items():
for fields in data_set.get_field_names():
if Const.INPUT in fields:
data_set.apply(lambda x: len(x[fields]),
new_field_name=fields.replace(
Const.INPUT, Const.INPUT_LEN),
is_input=auto_set_input)
elif seq_len_type == 'mask':
for data_name, data_set in data_info.datasets.items():
for fields in data_set.get_field_names():
if Const.INPUT in fields:
data_set.apply(lambda x: [1] * len(x[fields]),
new_field_name=fields.replace(
Const.INPUT, Const.INPUT_LEN),
is_input=auto_set_input)
elif seq_len_type == 'bert':
for data_name, data_set in data_info.datasets.items():
if Const.INPUT not in data_set.get_field_names():
raise KeyError(
f'Field ``{Const.INPUT}`` not in {data_name} data set: '
f'got {data_set.get_field_names()}')
data_set.apply(lambda x: [0] *
(len(x[Const.INPUTS(0)]) + 2) + [1] *
(len(x[Const.INPUTS(1)]) + 1),
new_field_name=Const.INPUT_LENS(0),
is_input=auto_set_input)
data_set.apply(lambda x: [1] * len(x[Const.INPUT_LENS(0)]),
new_field_name=Const.INPUT_LENS(1),
is_input=auto_set_input)
if auto_pad_length is not None:
cut_text = min(
auto_pad_length,
cut_text if cut_text is not None else auto_pad_length)
if cut_text is not None:
for data_name, data_set in data_info.datasets.items():
for fields in data_set.get_field_names():
if (Const.INPUT
in fields) or ((Const.INPUT_LEN in fields) and
(seq_len_type != 'seq_len')):
data_set.apply(lambda x: x[fields][:cut_text],
new_field_name=fields,
is_input=auto_set_input)
data_set_list = [d for n, d in data_info.datasets.items()]
assert len(data_set_list) > 0, f'There are NO data sets in data info!'
if bert_tokenizer is None:
words_vocab = Vocabulary(padding=auto_pad_token)
words_vocab = words_vocab.from_dataset(
*[d for n, d in data_info.datasets.items() if 'train' in n],
field_name=[
n for n in data_set_list[0].get_field_names()
if (Const.INPUT in n)
],
no_create_entry_dataset=[
d for n, d in data_info.datasets.items()
if 'train' not in n
])
target_vocab = Vocabulary(padding=None, unknown=None)
target_vocab = target_vocab.from_dataset(
*[d for n, d in data_info.datasets.items() if 'train' in n],
field_name=Const.TARGET)
data_info.vocabs = {
Const.INPUT: words_vocab,
Const.TARGET: target_vocab
}
if get_index:
for data_name, data_set in data_info.datasets.items():
for fields in data_set.get_field_names():
if Const.INPUT in fields:
data_set.apply(
lambda x:
[words_vocab.to_index(w) for w in x[fields]],
new_field_name=fields,
is_input=auto_set_input)
if Const.TARGET in data_set.get_field_names():
data_set.apply(
lambda x: target_vocab.to_index(x[Const.TARGET]),
new_field_name=Const.TARGET,
is_input=auto_set_input,
is_target=auto_set_target)
if auto_pad_length is not None:
if seq_len_type == 'seq_len':
raise RuntimeError(
f'the sequence will be padded with the length {auto_pad_length}, '
f'so the seq_len_type cannot be `{seq_len_type}`!')
for data_name, data_set in data_info.datasets.items():
for fields in data_set.get_field_names():
if Const.INPUT in fields:
data_set.apply(
lambda x: x[fields] +
[words_vocab.to_index(words_vocab.padding)] *
(auto_pad_length - len(x[fields])),
new_field_name=fields,
is_input=auto_set_input)
elif (Const.INPUT_LEN
in fields) and (seq_len_type != 'seq_len'):
data_set.apply(lambda x: x[fields] + [0] *
(auto_pad_length - len(x[fields])),
new_field_name=fields,
is_input=auto_set_input)
for data_name, data_set in data_info.datasets.items():
if isinstance(set_input, list):
data_set.set_input(*[
inputs for inputs in set_input
if inputs in data_set.get_field_names()
])
if isinstance(set_target, list):
data_set.set_target(*[
target for target in set_target
if target in data_set.get_field_names()
])
return data_info