def segmentation(filename, output_filename):
print "segmenting '%s' to '%s'" % (filename, output_filename)
f = open(filename, "r")
lines = f.readlines()
f.close()
MODELDIR = "./ltp_data/"
# segment
segmentor = Segmentor()
segmentor.load(os.path.join(MODELDIR, "cws.model"))
# postag
postagger = Postagger()
postagger.load(os.path.join(MODELDIR, "pos.model"))
# Named Entity Recognize
recognizer = NamedEntityRecognizer()
recognizer.load(os.path.join(MODELDIR, "ner.model"))
# Parse and get SVO
parser = Parser()
parser.load(os.path.join(MODELDIR, "parser.model"))
f = open(output_filename, "w")
fner = open(output_filename.split(".")[0]+"_ner.txt", "w")
for _line in lines:
line = _line[:-1]
if line[-1] in "\n\r":
line = line[:-1]
words = segmentor.segment(line)
postags = postagger.postag(words)
# netags = recognizer.recognize(words, postags)
# arcs = parser.parse(words, postags)
for i in range(len(words)):
f.write( "%s/%s\t" % (words[i], postags[i]))
# if netags[i]!='O':
# fner.write("%s/%s\t" % (words[i], netags[i]))
f.write("\n")
# fner.write("\n")
f.close()
def segmentsentence(sentence):
segmentor = Segmentor()
postagger = Postagger()
parser = Parser()
recognizer = NamedEntityRecognizer()
segmentor.load("./ltpdata/ltp_data_v3.4.0/cws.model")
postagger.load("./ltpdata/ltp_data_v3.4.0/pos.model")
# parser.load("./ltpdata/ltp_data_v3.4.0/parser.model")
recognizer.load("./ltpdata/ltp_data_v3.4.0/ner.model")
#############
word_list = segmentor.segment(sentence)
postags_list = postagger.postag(word_list)
nertags = recognizer.recognize(word_list, postags_list)
############
for word, ntag in zip(word_list, nertags):
if ntag == 'Nh':
entity_list.append(word)
print(" ".join(word_list))
print(' '.join(nertags))
############
segmentor.release()
postagger.release()
# parser.release()
recognizer.release()
return word_list
def namedEntityRecognize(sentence):
'''
使用pyltp模块进行命名实体识别
返回：1）命名实体和类别元组列表、2）实体类别列表
'''
namedEntityTagTupleList = []
segmentor = Segmentor()
# segmentor.load(inout.getLTPPath(index.CWS))
segmentor.load_with_lexicon(inout.getLTPPath(index.CWS),
inout.getResourcePath('userDic.txt'))
words = segmentor.segment(sentence)
segmentor.release()
postagger = Postagger()
postagger.load(inout.getLTPPath(index.POS))
postags = postagger.postag(words)
postagger.release()
recognizer = NamedEntityRecognizer()
recognizer.load(inout.getLTPPath(index.NER))
netags = recognizer.recognize(words, postags)
recognizer.release()
# 封装成元组形式
for word, netag in zip(words, netags):
namedEntityTagTupleList.append((word, netag))
neTagList = '\t'.join(netags).split('\t')
return namedEntityTagTupleList, neTagList
def ltp_ner_data():
"""使用 LTP 进行命名实体识别"""
LTP_DATA_DIR = 'D:\BaiduNetdiskDownload\ltp_data_v3.4.0' # ltp模型目录的路径
ner_model_path = os.path.join(LTP_DATA_DIR,
'ner.model') # 命名实体识别模型路径，模型名称为`pos.model`
from pyltp import NamedEntityRecognizer
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(ner_model_path) # 加载模型
result = []
file = [(const.qc_train_pos, const.qc_train_ner),
(const.qc_test_pos, const.qc_test_ner)]
for i in range(2):
with open(file[i][0], 'r', encoding='utf-8') as f:
for line in f.readlines():
attr = line.strip().split('\t')
words_pos = attr[1].split(" ")
words = [word.split('/_')[0] for word in words_pos]
postags = [word.split('/_')[1] for word in words_pos]
netags = recognizer.recognize(words, postags) # 命名实体识别
res = ' '.join([
"{}/_{}".format(words[i], netags[i])
for i in range(len(words))
])
result.append("{}\t{}\n".format(attr[0], res))
with open(file[i][1], 'w', encoding='utf-8') as f:
f.writelines(result)
result.clear()
recognizer.release() # 释放模型
def __init__(self):
LTP_DIR = "./ltp_data"
self.lac = LAC(mode='lac')
self.lac.load_customization('data/custom.txt', sep=None)
self.ddparser = DDParser(encoding_model='transformer')
self.fine_info = FineGrainedInfo
self.keyword = Keyword()
self.jieba = jieba
self.posseg = jieba.posseg
self.segmentor = Segmentor(os.path.join(LTP_DIR, "cws.model"))
self.postagger = Postagger(
model_path=os.path.join(LTP_DIR, "pos.model"))
self.parser = Parser(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer(
os.path.join(LTP_DIR, "ner.model"))
def restart(self):
self.segmentor.release()
self.postagger.release()
self.recognizer.release()
self.parser.release()
self.srler.release()
self.segmentor = Segmentor()
self.segmentor.load(os.path.join(self.MODELDIR, "cws.model"))
self.postagger = Postagger()
self.postagger.load(os.path.join(self.MODELDIR, "pos.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(self.MODELDIR, "ner.model"))
self.parser = Parser()
self.parser.load(os.path.join(self.MODELDIR, "parser.model"))
self.srler = SementicRoleLabeller()
self.srler.load(os.path.join(self.MODELDIR, "pisrl.model"))
def __init__(self):
LTP_DIR = "./ltp_data"
self.segmentor = Segmentor()
# self.segmentor.load(os.path.join(LTP_DIR, "cws.model"))
self.segmentor.load_with_lexicon(os.path.join(LTP_DIR, "cws.model"),
'./dict.txt')
self.postagger = Postagger()
self.postagger.load(os.path.join(LTP_DIR, "pos.model"))
self.parser = Parser()
self.parser.load(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_DIR, "ner.model"))
self.labeller = SementicRoleLabeller()
self.labeller.load(os.path.join(LTP_DIR, 'pisrl.model'))
def __init__(self):
LTP_PATH = '/root/tmp/pycharm_project_96/pyltp_test/ltp_data'
# 分词
self.segmentor = Segmentor()
self.segmentor.load(os.path.join(LTP_PATH,'cws.model'))
# 词性标注
self.postagger = Postagger()
self.postagger.load(os.path.join(LTP_PATH,'pos.model'))
# 依存句法
self.parser = Parser()
self.parser.load(os.path.join(LTP_PATH,'parser.model'))
# 命名实体识别
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_PATH,'ner.model'))
# # 语义角色标注
self.labeller = SementicRoleLabeller()
self.labeller.label(os.path.join(LTP_PATH,'pisrl.model'))
def __init__(self):
print(111)
LTP_DIR = "D:\\ltp_data\\ltp_data_v3.4.0"
self.segmentor = Segmentor()
self.segmentor.load(os.path.join(LTP_DIR, "cws.model"))
self.postagger = Postagger()
self.postagger.load(os.path.join(LTP_DIR, "pos.model"))
self.parser = Parser()
self.parser.load(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_DIR, "ner.model"))
self.labeller = SementicRoleLabeller()
self.labeller.load(os.path.join(LTP_DIR, 'pisrl_win.model'))
print(111)
def getNameRecognizer(self):
if Config.c_namerecognizer:
return Config.c_namerecognizer
else:
ner_model_path = os.path.join(Config.ltp_data_dir,
Config.ner_model)
Config.c_namerecognizer = NamedEntityRecognizer()
Config.c_namerecognizer.load(ner_model_path)
return Config.c_namerecognizer
def __init__(self,):
LTP_DATA_DIR = SETTINGS.LTP_DATA_DIR # ltp模型目录的路径
cws_model_path = os.path.join(LTP_DATA_DIR, 'cws.model') # 分词模型路径，模型名称为`cws.model`
pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') # 词性标注模型路径，模型名称为`pos.model`
par_model_path = os.path.join(LTP_DATA_DIR, 'parser.model') # 依存句法分析模型路径，模型名称为`parser.model`
srl_model_path = os.path.join(LTP_DATA_DIR, 'srl') # 语义角色标注模型目录路径，模型目录为`srl`。注意该模型路径是一个目录，而不是一个文件。
ner_model_path = os.path.join(LTP_DATA_DIR, 'ner.model') # 命名实体识别模型路径，模型名称为`pos.model`
self.segmentor = Segmentor() # 初始化实例
self.segmentor.load_with_lexicon(cws_model_path,'./segName') # 加载模型
self.postagger = Postagger() # 初始化实例
self.postagger.load_with_lexicon(pos_model_path,'./postagName') # 加载模型
self.parser = Parser() # 初始化实例
self.parser.load(par_model_path) # 加载模型
self.labeller = SementicRoleLabeller() # 初始化实例
self.labeller.load(srl_model_path) # 加载模型
self.recognizer = NamedEntityRecognizer() # 初始化实例
self.recognizer.load(ner_model_path) # 加载模型
def __init__(self):
# LTP_DIR = './ltp_data_v3.4.0'
print("加载模型路径", LTP_DIR)
self.segmentor = Segmentor()
self.segmentor.load(os.path.join(LTP_DIR, "cws.model"))
self.postagger = Postagger()
self.postagger.load(os.path.join(LTP_DIR, "pos.model"))
self.parser = Parser()
self.parser.load(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_DIR, "ner.model"))
self.labeller = SementicRoleLabeller()
self.labeller.load(os.path.join(LTP_DIR, 'pisrl.model'))
print("加载完毕")
def __init__(self, **kwargs):
"""
Args:
annotators: set that can include pos and ner.
model: ltp model to use (path).
"""
self.segmentor = Segmentor() # 初始化分词器实例
self.recognizer = NamedEntityRecognizer() # 初始化命名实体识别器实例
self.postagger = Postagger() # 初始化词性标注实例
self.segmentor.load(cws_model_path) # 加载分词模型
self.annotators = copy.deepcopy(kwargs.get('annotators', set()))
if {'pos'} & self.annotators:
self.postagger.load(pos_model_path)
if {'ner'} & self.annotators:
self.postagger.load(pos_model_path)
self.recognizer.load(ner_model_path)
def dependency_parsing(ltp_model_path, sents, postags, said):
LTP_DATA_DIR = ltp_model_path # ltp模型目录的路径
par_model_path = os.path.join(
LTP_DATA_DIR, 'parser.model') # 依存句法分析模型路径，模型名称为`parser.model`
ner_model_path = os.path.join(
LTP_DATA_DIR, 'ner.model') # 依存句法分析模型路径，模型名称为`parser.model`
from pyltp import Parser, NamedEntityRecognizer
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(ner_model_path) # 加载模型
parser = Parser() # 初始化实例
parser.load(par_model_path) # 加载模型
contents = []
for index in range(len(sents)):
wo = sents[index].split()
po = postags[index]
netags = recognizer.recognize(wo, po) # 命名实体识别
# print("netags", list(netags))
netags = list(netags)
if ('S-Ns' not in netags) and ('S-Ni'
not in netags) and ('S-Nh'
not in netags):
continue
arcs = parser.parse(wo, po) # 句法分析
arcs = [(arc.head, arc.relation) for arc in arcs]
arcs = [(i, arc) for i, arc in enumerate(arcs) if arc[1] == 'SBV']
for arc in arcs:
verb = arc[1][0]
subject = arc[0]
if wo[verb - 1] not in said:
continue
contents.append((wo[subject], wo[verb - 1], ''.join(wo[verb:])))
# parser.release() # 释放模型
# recognizer.release() # 释放模型
return contents
def name_recognize_one():
import sys, os
import pyltp
from pyltp import SentenceSplitter, Segmentor, Postagger, Parser, NamedEntityRecognizer, SementicRoleLabeller
paragraph = '叙利亚东古塔地区。7日发生疑似化学武器袭击事件，导致70余人丧生。报道一出，叙利亚反对派、美国、英国、法国等纷纷指责叙政府军使用化学武器袭击无辜平民。但叙利亚坚决否认，并指责西方和叙反对派造谣，目的是保护被围困的恐怖分子。俄外交部则认为，该谣言旨在袒护恐怖分子，并为外部势力发动打击寻找借口。'
sentence = SentenceSplitter.split(paragraph)[1]
print('split {}'.format(sentence))
# 断句
# for i in sentence:
# print(i)
# print()
segmentor = Segmentor()
segmentor.load(sg_model_path)
words = segmentor.segment(sentence)
print('|'.join(words))
postagger = Postagger()
postagger.load(ps_model_path)
postags = postagger.postag(words)
for k, v in dict(zip(words, postags)).items():
print(k, v)
# print(' ## '.join(postags))
parser = Parser()
parser.load(pr_model_path)
arcs = parser.parse(words, postags)
print(' '.join('%d:%s ' % (arc.head, arc.relation) for arc in arcs))
print('#' * 8)
recognizer = NamedEntityRecognizer()
recognizer.load(ner_model_path)
netag = recognizer.recognize(words, postags)
for word, ntag in zip(words, netag):
if ntag != 'O':
# print('ntag')
print(word + ' / ' + netag)
print(' / '.join(netag))
# 命名实体识别
word_list = ['欧几里得', '是', '西元前', '三', '世纪', '的', '希腊', '数学家', '。']
postags_list = ['nh', 'v', 'nt', 'm', 'n', 'u', 'ns', 'n', 'wp']
nertags = recognizer.recognize(word_list, postags_list)
for word, ntag in zip(word_list, nertags):
if ntag != 'O':
print(word + '/' + ntag)
#print (" ".join(word_list))
print(' '.join(nertags))
segmentor.release()
postagger.release()
parser.release()
recognizer.release()
def get_all_name(r_filename, w_file):
# global nlp
LTP_DATA_DIR = r'ltp_data_v3.4.0' # LTP模型目录路径
# 分词
segmentor = Segmentor() # 初始化
segmentor.load(os.path.join(LTP_DATA_DIR, 'cws.model')) # 加载模型
# words = segmentor.segment(line) # 分词
# 词性标注
postagger = Postagger() # 初始化
postagger.load(os.path.join(LTP_DATA_DIR, 'pos.model')) # 加载模型
#postags = postagger.postag(words)
# postags = postagger.postag(['中国', '进出口', '银行', '与', '中国银行', '加强', '合作', '。'])
#res=[]
# 命名实体识别
recognizer = NamedEntityRecognizer() # 实例化
recognizer.load(os.path.join(LTP_DATA_DIR, 'ner.model'))
f_r = open(r_filename, "r", encoding="utf-8")
f_w = open(w_file, "w", encoding="utf-8")
count = 0
for line in f_r:
count += 1
line = line.strip(r"\n")
line = raplace_line_feed(line)
line = more_space_to_one(line)
print(line)
words = segmentor.segment(line)
postags = postagger.postag(words)
netags = recognizer.recognize(words, postags)
name_list = get_name(netags, words)
if name_list != []:
print(name_list)
sen = get_some_idea(line, name_list)
print(sen)
if sen:
for key in sen:
# print(sen[key])
sens = "\t".join(list(set([data[1] for data in sen[key]])))
f_w.write(key + "\t" + sens + "\n")
# nlp.close()
f_r.close()
f_w.close()
def ner(words, postags):
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(os.path.join(LTP_DATA_DIR, 'ner.model')) # 加载模型
netags = recognizer.recognize(words, postags) # 命名实体识别
for word, ntag in zip(words, netags):
print(word + '/' + ntag)
recognizer.release() # 释放模型
return netags
def get_ner(words, postags):
""" ltp 命名实体识别 """
ner_model_path = os.path.join(LTP_TOP_DIR, 'ner.model')
recognizer = NamedEntityRecognizer()
recognizer.load(ner_model_path)
netags = recognizer.recognize(words, postags)
recognizer.release()
return list(netags)
def ltp_name_entity_recognizer(LTP_DATA_DIR, words, postags):
# 命名实体识别模型路径，模型名称为`ner.model`
ner_model_path = os.path.join(LTP_DATA_DIR, 'ner.model')
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(ner_model_path) # 加载模型
netags = recognizer.recognize(words, postags) # 命名实体识别
recognizer.release() # 释放模型
return netags
def ner(words, postags):
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load('/Users/chenming/Spyder/3.3.1/ltp_data/ner.model') # 加载模型
netags = recognizer.recognize(words, postags) # 命名实体识别
for word, ntag in zip(words, netags):
print (word + '/' + ntag)
recognizer.release() # 释放模型
return netags
def entity_recognize(cutting_list, tagging_list):
ner_model_path = os.path.join(LtpParser.ltp_path, 'ner.model')
from pyltp import NamedEntityRecognizer
recognizer = NamedEntityRecognizer()
recognizer.load(ner_model_path)
ne_tags = recognizer.recognize(cutting_list, tagging_list)
recognizer.release()
return ne_tags
def e_recognize(words, postags):
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(ner_model_path) # 加载模型
netags = recognizer.recognize(words, postags) # 命名实体识别
#for word, ntag in zip(words, netags):
#print(word + '/' + ntag)
recognizer.release() # 释放模型
return netags
def ner(words, postags):
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load('../ltp_data/ner.model') # 加载模型
netags = recognizer.recognize(words, postags) # 命名实体识别
# for word,tag in zip(words,netags):
# print word+'/'+tag
recognizer.release() # 释放模型
return netags
def get_ner(self, word_list, postag_list, model):
recognizer = NamedEntityRecognizer()
recognizer.load(model)
netags = recognizer.recognize(word_list, postag_list) # 命名实体识别
# for word, ntag in zip(word_list, netags):
# print(word + '/' + ntag)
recognizer.release() # 释放模型
return list(netags)
class LtpLanguageAnalysis(object):
def __init__(self, model_dir="D:/ltp_data_v3.4.0"):
self.segmentor = Segmentor()
self.segmentor.load(os.path.join(model_dir, "cws.model"))
self.postagger = Postagger()
self.postagger.load(os.path.join(model_dir, "pos.model"))
self.parser = Parser()
self.parser.load(os.path.join(model_dir, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(model_dir, "ner.model")) # 加载命名实体识别模型
def analyze(self, text):
# 分词
words = self.segmentor.segment(text)
print('\t'.join(words))
def postags(self, words):
# 词性标注
postags = self.postagger.postag(words)
# print('\t'.join(postags))
return list(postags)
# return '\t'.join(postags)
def parse(self, words, postags):
# 句法分析
arcs = self.parser.parse(words, postags)
# print("\t".join("%d:%s" % (arc.head, arc.relation) for arc in arcs))
# print("\t".join(arc.relation for arc in arcs))
return "\t".join(arc.relation for arc in arcs)
def ner(self, words, postags):
# 命名实体
netag = self.recognizer.recognize(words, postags)
for word, ntag in zip(words, netag):
if ntag != 'O':
print(word + '/' + ntag)
print("\t".join(netag))
def release_model(self):
# 释放模型
self.segmentor.release()
self.postagger.release()
self.parser.release()
def __init__(self, data_dir):
self.LTP_DATA_DIR = data_dir
cws_model_path = os.path.join(self.LTP_DATA_DIR, 'cws.model')
# 分词模型路径，分词模型名称是‘cws.model’
self.segmentor = Segmentor()
self.segmentor.load(cws_model_path)
pos_model_path = os.path.join(self.LTP_DATA_DIR, 'pos.model')
# 词性标注模型路径，分词模型名称是‘pos.model’
self.postagger = Postagger()
self.postagger.load(pos_model_path)
ner_model_path = os.path.join(self.LTP_DATA_DIR, 'ner.model')
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(ner_model_path)
par_model_path = os.path.join(self.LTP_DATA_DIR, 'parser.model')
self.parser = Parser()
self.parser.load(par_model_path)
def __init__(self):
LTP_DIR = "../../res/ltp/ltp_data_v3.4.0"
LTP_DIR_USER = "******"
self.segmentor = Segmentor()
self.segmentor.load_with_lexicon(os.path.join(LTP_DIR, "cws.model"), os.path.join(LTP_DIR_USER, "fulluserdict.txt"))
# self.segmentor.load(os.path.join(LTP_DIR, "cws.model"))
self.postagger = Postagger()
self.postagger.load_with_lexicon(os.path.join(LTP_DIR, "pos.model"), os.path.join(LTP_DIR_USER, "fulluserdict.txt"))
# self.postagger.load(os.path.join(LTP_DIR, "pos.model"))
self.parser = Parser()
self.parser.load(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_DIR, "ner.model"))
self.labeller = SementicRoleLabeller()
self.labeller.load(os.path.join(LTP_DIR, 'pisrl_win.model'))
def segment(self, texts, use_tag_filter=True):
# 初始化实例
# global word_list, netags, postags, relation, heads
words = []
pos = []
ner = []
rel = []
hea = []
segmentor = Segmentor()
segmentor.load_with_lexicon(self.cws_model_path, './dict/user_recg.dic') # 加载模型，参数是自定义词典的文件路径 self.dic_list
postagger = Postagger()
postagger.load(self.pos_model_path)
recognizer = NamedEntityRecognizer()
recognizer.load(self.ner_model_path)
parser = Parser()
parser.load(self.pas_model_path)
for text in texts:
text = text.lower()
word_list = segmentor.segment(text)
word_list = [word for word in word_list if len(word) > 1]
# word_list = [word for word in word_list if re.match("[\u0041-\u005a\u4e00-\u9fa5]+", word) != None] # .decode('utf8') 保留中英文
word_list = [word.strip() for word in word_list if word.strip() not in self.stop_words] # 去除停用词
# 词性标注
posttags = postagger.postag(word_list)
postags = list(posttags)
# NER识别
netags = recognizer.recognize(word_list, postags)
# 句法分析
arcs = parser.parse(word_list, postags)
rely_id = [arc.head for arc in arcs] # 提取依存父节点id
relation = [arc.relation for arc in arcs] # 提取依存关系
heads = ['Root' if id == 0 else word_list[id - 1] for id in rely_id] # 匹配依存父节点词语
if use_tag_filter:
dic = dict(zip(word_list, postags))
word_list = [x for x in dic.keys() if dic[x] in self.tags_filter]
words.append(word_list)
pos.append(postags)
ner.append(netags)
rel.append(relation)
hea.append(heads)
segmentor.release()
postagger.release()
recognizer.release()
parser.release()
return words, pos, ner, rel, hea
def __init__(self):
LTP_DIR = "data\ltp_data"
cws_model_path = os.path.join(LTP_DIR, 'cws.model') # 分词模型路径，模型名称为`cws.model`
lexicon_path = "dictionary\Dir1.txt" # 参数lexicon是自定义词典的文件路径
self.segmentor = Segmentor()
self.segmentor.load_with_lexicon(cws_model_path, lexicon_path)
# self.segmentor.load(os.path.join(LTP_DIR, "cws.model"))
self.postagger = Postagger()
self.postagger.load(os.path.join(LTP_DIR, "pos.model"))
self.parser = Parser()
self.parser.load(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_DIR, "ner.model"))
self.labeller = SementicRoleLabeller()
self.labeller.load(os.path.join(LTP_DIR, 'pisrl_win.model'))
class LTP:
def __init__(self, base_dir, is_custom_seg_dict=False):
if base_dir is None:
base_dir = 'lib/ltp_data_v3.4.0'
self.init(base_dir, is_custom_seg_dict)
def init(self, base_dir, is_custom_seg_dict):
segmentor_model = os.path.join(base_dir, 'cws.model')
tagger_model = os.path.join(base_dir, 'pos.model')
ner_model = os.path.join(base_dir, 'ner.model')
parser_model = os.path.join(base_dir, 'parser.model')
custom_seg_dict = os.path.join(dict_dir,
'vertical_domain_baike_dict.txt')
self.segmentor = Segmentor()
if is_custom_seg_dict:
self.segmentor.load_with_lexicon(segmentor_model, custom_seg_dict)
else:
self.segmentor.load(segmentor_model)
self.tagger = Postagger()
self.tagger.load(tagger_model)
self.nertagger = NamedEntityRecognizer()
self.nertagger.load(ner_model)
self.parser = Parser()
self.parser.load(parser_model)
def parse(self, sentence, parse_tree=True):
words = list(self.segmentor.segment(sentence))
tags = list(self.tagger.postag(words))
ner_tags = list(self.nertagger.recognize(words, tags))
if parse_tree:
arcs = list(self.parser.parse(words, tags))
else:
arcs = None
result = LTPResult(words, tags, ner_tags, arcs, sentence)
return result
def cut(self, sentence):
words = self.segmentor.segment(sentence)
return words
def test(sentence):
os.environ['STANFORD_PARSER'] = STANFORD_PARSER_PATH
os.environ['STANFORD_MODELS'] = STANFORD_MODELS_PATH
os.environ['JAVAHOME'] = JAVA_HOME
stanford_model_path = CHINESE_MODEL_PATH
s_parser = stanford.StanfordParser(model_path=stanford_model_path)
par_model_path = os.path.join(
LTP_DATA_DIR, 'parser.model') # 依存句法分析模型路径，模型名称为`parser.model`
from pyltp import Parser
parser = Parser() # 初始化实例
parser.load(par_model_path) # 加载模型
cws_model_path = os.path.join(LTP_DATA_DIR,
'cws.model') # 分词模型路径，模型名称为`cws.model`
from pyltp import Segmentor
segmentor = Segmentor() # 初始化实例
segmentor.load(cws_model_path) # 加载模型
pos_model_path = os.path.join(LTP_DATA_DIR,
'pos.model') # 词性标注模型路径，模型名称为`pos.model`
from pyltp import Postagger
postagger = Postagger() # 初始化实例
postagger.load(pos_model_path) # 加载模型
ner_model_path = os.path.join(LTP_DATA_DIR,
'ner.model') # 命名实体识别模型路径，模型名称为`pos.model`
from pyltp import NamedEntityRecognizer
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(ner_model_path) # 加载模型
words = segmentor.segment(sentence)
postags = postagger.postag(words)
netags = recognizer.recognize(words, postags)
arcs = parser.parse(words, postags) # 句法分析
res = zip(words, postags, netags, arcs)
for i in res:
print(','.join(i[:3]), str(i[3].head) + ':' + i[3].relation)
def __init__(self):
self.cws_model_path = os.path.join(self.LTP_DATA_DIR, 'cws.model') # 分词模型路径，模型名称为`cws.model`
self.pos_model_path = os.path.join(self.LTP_DATA_DIR, 'pos.model') # 词性标注模型路径，模型名称为`pos.model`
self.ner_model_path = os.path.join(self.LTP_DATA_DIR, 'ner.model') # 命名实体识别模型路径，模型名称为`pos.model`
segmentor = Segmentor()
segmentor.load(self.cws_model_path)
self.words = segmentor.segment(data)
# print("|".join(words))
segmentor.release()
postagger = Postagger() # 初始化实例
postagger.load(self.pos_model_path) # 加载模型
self.postags = postagger.postag(self.words) # 词性标注
# print('\t'.join(postags))
postagger.release() # 释放模型
recognizer = NamedEntityRecognizer() # 初始化实例
recognizer.load(self.ner_model_path) # 加载模型
self.netags = recognizer.recognize(self.words, self.postags) # 命名实体识别
# print('\t'.join(netags))
recognizer.release() # 释放模型
print "\t".join(words)
postagger = Postagger()
postagger.load(os.path.join(MODELDIR, "pos.model"))
postags = postagger.postag(words)
# list-of-string parameter is support in 0.1.5
# postags = postagger.postag(["中国","进出口","银行","与","中国银行","加强","合作"])
print "\t".join(postags)
parser = Parser()
parser.load(os.path.join(MODELDIR, "parser.model"))
arcs = parser.parse(words, postags)
print "\t".join("%d:%s" % (arc.head, arc.relation) for arc in arcs)
recognizer = NamedEntityRecognizer()
recognizer.load(os.path.join(MODELDIR, "ner.model"))
netags = recognizer.recognize(words, postags)
print "\t".join(netags)
labeller = SementicRoleLabeller()
labeller.load(os.path.join(MODELDIR, "srl/"))
roles = labeller.label(words, postags, netags, arcs)
for role in roles:
print role.index, "".join(
["%s:(%d,%d)" % (arg.name, arg.range.start, arg.range.end) for arg in role.arguments])
segmentor.release()
postagger.release()
parser.release()
import sys, os
ROOTDIR = os.path.join(os.path.dirname(__file__), os.pardir)
sys.path.append(os.path.join(ROOTDIR, "lib"))
# Set your own model path
MODELDIR = os.path.join("/home/fish/", "ltp_data")
from pyltp import Segmentor, Postagger, NamedEntityRecognizer # @UnresolvedImport
# 分词功能
segmentor = Segmentor()
segmentor.load(os.path.join(MODELDIR, "cws.model"))
postagger = Postagger()
postagger.load(os.path.join(MODELDIR, "pos.model"))
recognizer = NamedEntityRecognizer()
recognizer.load(os.path.join(MODELDIR, "ner.model"))
def ltp(sentence):
words = segmentor.segment(sentence)
# 词性标注功能
postags = postagger.postag(words)
# 实体识别
netags = recognizer.recognize(words, postags)
l = []
li = zip(list(words), list(postags), list(netags))
for a, b, c in li:
# 去掉命名实体
if c == "O":
# 去掉所有名词
def mingming_shiti(words,postags):
"""命名实体。机构名(Ni)人名(Nh)地名(Ns)"""
recognizer = NamedEntityRecognizer()
recognizer.load(os.path.join(MODELDIR, "ner.model"))
netags = recognizer.recognize(words, postags)
print ("\t".join(netags))
