def add_node(self, word, typing):
'''
向 Trie 树添加节点
:param word: 字典中的词汇
:param typing: 词汇类型
:return: None
'''
word = word.strip()
if word not in ['', '\t', ' ', '\r']:
tree = self.dict_trie
depth = len(word)
word = word.lower() # 将所有的字母全部转换成小写
for char in word:
if char in tree:
tree = tree[char]
else:
tree[char] = dict()
tree = tree[char]
if depth > self.depth:
self.depth = depth
if 'type' in tree and tree['type'] != typing:
logging.warning('`{}` belongs to both `{}` and `{}`.'.format(
word, tree['type'], typing))
else:
tree['type'] = typing
def wrapper(self, *args, **kargs):
# 按索引检索的 appkey
if self.appkey_obj_list is not None:
count = 0
while count <= self.appkey_num:
self.appkey_obj = self.appkey_obj_list[self.appkey_index]
count += 1
try:
f = func(self, *args, **kargs)
break
except Exception as err:
# 替换密钥的索引
if self.appkey_index == self.appkey_num - 1:
self.appkey_index = 0
else:
self.appkey_index += 1
# 统计，若循环次数大于密钥个数，即全部密钥被尝试，则退出；否则继续尝试下一个密钥
if count < self.appkey_num:
logging.warning(
'The appkey {} of `{}` is invalid.'.format(
json.dumps(self.appkey_obj, ensure_ascii=False),
self.__class__.__name__))
else:
logging.error(err)
raise Exception(err)
break
else:
f = func(self, *args, **kargs)
return f
def _wrong_message(_idx, ts):
if verbose:
logging.info(token_list)
logging.info(tags)
logging.warning('wrong tag: {}'.format(
ts[start if start is not None
else max(0, _idx - 2): _idx + 2]))
def entity2tag(token_list: List[str],
entities: List[Dict[str, Any]],
formater='BIOES'):
""" 将实体 entity 格式转为 tag 格式，若标注过程中有重叠标注，则会自动将靠后的
实体忽略、删除。针对单条处理，不支持批量处理。
Args:
token_list(List[str]): token 化的文本的 list
entities(List[str, Dict[str, Any]]): 文本相应的实体。
formater(str): 选择的标注标准
return:
List[List[str], List[str]]: tag 格式的数据
Examples:
>>> token_list = '胡静静在水利局工作。' # 字级别
>>> token_list = ['胡', '静', '静', '在', '水',
'利', '局', '工', '作', '。'] # 字或词级别
>>> ner_entities =
[{'text': '胡静静', 'offset': [0, 3], 'type': 'Person'},
{'text': '水利局', 'offset': [4, 7], 'type': 'Orgnization'}]
>>> print(jio.ner.entity2tag(token_list, ner_entities))
['B-Person', 'I-Person', 'E-Person', 'O', 'B-Orgnization',
'I-Orgnization', 'E-Orgnization', 'O', 'O', 'O']
"""
tags = ['O' for i in range(len(token_list))]
flag = 0 # 判断重叠标注
entities = sorted(entities, key=lambda i: i['offset'][0])
for idx, entity in enumerate(entities):
if entity['offset'][1] < flag: # 说明重叠标注，要删除
if 1 < idx + 1 < len(entities):
logging.warning('The entity {} is overlapped with {}.'.format(
json.dumps(entity, ensure_ascii=False),
json.dumps(entities[idx - 1], ensure_ascii=False)))
else:
if entity['offset'][1] - entity['offset'][0] == 1:
tags[entity['offset'][0]] = 'S-' + entity['type']
else:
tags[entity['offset'][0]] = 'B-' + entity['type']
if entity['offset'][1] - entity['offset'][0] > 2:
for j in range(entity['offset'][0] + 1,
entity['offset'][1] - 1):
tags[j] = 'I-' + entity['type']
tags[entity['offset'][1] - 1] = 'E-' + entity['type']
flag = entity['offset'][1]
return tags
def entity2tag(token_list: List[str], entities: List[Dict[str, Any]],
formater='BIOES'):
''' 将实体 entity 格式转为 tag 格式，若标注过程中有重叠标注，则会自动将靠后的
实体忽略、删除。
Args:
ner_entities(List[str, Dict[str, Any]]): 文本以及相应的实体。
formater(str): 选择的标注标准
return:
List[List[str], List[str]]: tag 格式的数据
Examples:
>>> ner_entities = [
'胡静静在水利局工作。',
{'text': '胡静静', 'offset': [0, 3], 'type': 'Person'},
{'text': '水利局', 'offset': [4, 7], 'type': 'Orgnization'}]]
>>> print(entity2tag(ner_entities))
[['胡', '静', '静', '在', '水', '利', '局', '工', '作', '。'],
['B-Person', 'I-Person', 'E-Person', 'O', 'B-Orgnization',
'I-Orgnization', 'E-Orgnization', 'O', 'O', 'O']]
'''
tags = ['O' for i in range(len(token_list))]
flag = 0 # 判断重叠标注
for idx, entity in enumerate(entities):
if entity['offsets'][1] < flag: # 说明重叠标注，要删除
if 1 < idx + 1 < len(entities):
logging.warning(
'The entity {} is overlapped with {}.'.format(
json.dumps(entity, ensure_ascii=False),
json.dumps(entities[idx - 1], ensure_ascii=False)))
else:
if entity['offsets'][1] - entity['offsets'][0] == 1:
tags[entity['offsets'][0]] = 'S-' + entity['type']
else:
tags[entity['offsets'][0]] = 'B-' + entity['type']
if entity['offsets'][1] - entity['offsets'][0] > 2:
for j in range(entity['offsets'][0] + 1,
entity['offsets'][1] - 1):
tags[j] = 'I-' + entity['type']
tags[entity['offsets'][1] - 1] = 'E-' + entity['type']
flag = entity['offsets'][1]
return tags
def __call__(self,
cur_idiom,
same_pinyin=True,
check_idiom=False,
same_tone=True,
with_prob=True,
restart=False):
if self.idiom_list is None:
self._prepare()
if restart:
# 重新开始游戏，清空历史记录
self.already_used_idioms = set()
if cur_idiom not in self.pure_idiom_list:
logging.warning('{} may not be a Chinese idiom.'.format(cur_idiom))
if check_idiom:
return 'wrong input idiom'
else:
pass
else:
# add cur idiom into the already-list
self.already_used_idioms.add(cur_idiom)
if same_pinyin:
cur_last_pinyin = self.pinyin_obj(cur_idiom, formater='simple')[-1]
backup_idioms = list()
if same_tone:
for idiom_obj in self.idiom_list:
if idiom_obj['idiom'] in self.already_used_idioms:
continue
if cur_last_pinyin == idiom_obj['pinyin'][0]:
backup_idioms.append(idiom_obj)
else:
for idiom_obj in self.idiom_list:
if idiom_obj['idiom'] in self.already_used_idioms:
continue
if cur_last_pinyin[:-1] == idiom_obj['pinyin'][0][:-1]:
backup_idioms.append(idiom_obj)
else:
cur_last_char = cur_idiom[-1]
backup_idioms = list()
for idiom_obj in self.idiom_list:
if idiom_obj in self.already_used_idioms:
continue
if cur_last_char == idiom_obj['idiom'][0]:
backup_idioms.append(idiom_obj)
if len(backup_idioms) == 0:
return 'can not find next'
if not with_prob:
result = random.choice(backup_idioms)
self.already_used_idioms.add(result['idiom'])
return result['idiom']
else:
result = self._random_select(backup_idioms)
self.already_used_idioms.add(result['idiom'])
return result['idiom']
def char2word(char_entity_list, word_token_list, verbose=False):
'''将字 token 的 ner 训练数据组织成词 token，数据结构不变。针对单条数据处理，
不支持批量处理。
根据经验，jieba 分词的分词错误造成实体被丢弃，其错误率在 4.62%，
而 pkuseg 分词器错误率在 3.44%。
Args:
char_entity_list: 以字 token 为基准对应的实体列表
word_token_list: 采用分词器分词后的 list
verbose(bool): 字级别数据转换为词级别时，由于分词器误差，会有数据错漏，
此处选择是否打印详细错漏
Returns:
list: 词 token 数据
Examples:
>>> char_token_list = '胡静静喜欢江西红叶建筑公司' # 字级别
>>> char_token_list = [
'胡', '静', '静', '喜', '欢', '江', '西',
'红', '叶', '建', '筑', '公', '司'] # 字或词级别
>>> char_entity_list = [
{'text': '胡静静', 'offset': [0, 3], 'type': 'Person'},
{'text': '江西红叶建筑公司', 'offset': [5, 13], 'type': 'Company'}]
>>> word_token_list = ['胡静静', '喜欢', '江西', '红叶', '建筑', '公司']
>>> print(jio.ner.char2word(char_entity_list, word_token_list))
[{'text': '胡静静', 'offset': [0, 1], 'type': 'Person'},
{'text': '江西红叶建筑公司', 'offset': [2, 6], 'type': 'Company'}]
'''
idx_flag = 0
idx_list = [0]
for word in word_token_list:
idx_flag += len(word)
idx_list.append(idx_flag)
word_entity_list = list()
for char_entity in char_entity_list:
# 判断该实体有没有与分词产生冲突
try:
start = idx_list.index(char_entity['offset'][0])
end = idx_list.index(char_entity['offset'][1])
word_entity_list.append(
{'type': char_entity['type'], 'offset': [start, end],
'text': char_entity['text']})
except ValueError:
if verbose:
# 确定该实体的具体位置，给出日志
if char_entity['offset'][0] not in idx_list:
start = idx_list.index(
max([idx for idx in idx_list
if idx < char_entity['offset'][0]]))
else:
start = idx_list.index(char_entity['offset'][0])
if char_entity['offset'][1] not in idx_list:
end = idx_list.index(
min([idx for idx in idx_list
if idx > char_entity['offset'][1]]))
else:
end = idx_list.index(char_entity['offset'][1])
logging.warning(
'the entity {} =/=> {}'.format(
char_entity, word_token_list[start: end]))
return word_entity_list
