pyltp python具體使用

import re
from pyltp import NamedEntityRecognizer
from pyltp import SementicRoleLabeller
from pyltp import Parser
from pyltp import Postagger      

def ltp_segmentor(sentence):
    """ 分割字元串 """
    segmentor = Segmentor()
    cws_model_path = '..\\ltp_data\\cws.model'
    lexicon_path = '..\\ltp_data\\lexicon.txt'
    segmentor.load_with_lexicon(cws_model_path, lexicon_path)
    segmentor.load(cws_model_path)
    words = segmentor.segment(sentence)
    segmentor.release()
    return list(words)

def extract_data():
    parser = Parser()  # 初始化模型
    postagger = Postagger() # 詞性标注
    labeller = SementicRoleLabeller() # 語義校色标注
    recognizer = NamedEntityRecognizer() # 命名實體識别

    model_path = '..\\ltp_data\\pos.model'
    lexicon_path = '..\\ltp_data\\posLexicon.txt'
    postagger.load_with_lexicon(model_path, lexicon_path) # 加載自定義詞性表

    labeller.load('..\\ltp_data\\pisrl_win.model') # 加載模型
    recognizer.load('..\\ltp_data\\ner.model')
    postagger.load('..\\ltp_data\\pos.model')
    parser.load('..\\ltp_data\\parser.model')

    content = "#•江都建設集團南京分公司南鋼項目部安全生産規章制度不落實，作業現場安全管理缺失，安全操作規程不認真執行"
    text = re.sub("[#•]", "", content) # 對語句進行預處理
    words = sc_fun.ltp_segmentor(text) # 分詞
    postags = postagger.postag(words)
    arcs = parser.parse(words, postags)
    netags = recognizer.recognize(words, postags) # 命名實體識别
    print(list(netags))
    rely_id = [arc.head for arc in arcs]
    relation = [arc.relation for arc in arcs] # 關系
    heads = ['Root' if id == 0 else words[id - 1] for id in rely_id]
    roles = labeller.label(words, postags, arcs)
    for i in range(len(words)):
        print(i, relation[i], (words[i], heads[i]), postags[i])
    for role in roles:
        print([role.index, "".join(["%s:(%d,%d)" % (arg.name, arg.range.start, arg.range.end) for arg in role.arguments])])

    labeller.release()  # 釋放模型
    parser.release()
    postagger.release()
    recognizer.release()      

if __name__ == '__main__':
    extract_data()      

結果：

['B-Ni', 'I-Ni', 'I-Ni', 'I-Ni', 'I-Ni', 'I-Ni', 'E-Ni', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O','O', 'O', 'O', 'O', 'O', 'O']
0 ATT ('江都', '集團') ns
1 ATT ('建設', '集團') v
[11, 'A1:(0,9)ADV:(10,10)']
[24, 'A1:(19,21)ADV:(22,23)']      

分開封裝一樣的：

def ltp_segmentor(sentence):
    """ 分割字元串 """
    segmentor = Segmentor()
    segmentor.load('..\\ltp_data\\cws.model')
    words = segmentor.segment(sentence)
    segmentor.release()
    return list(words)

def ltp_parser(words, postags):
    parser = Parser()
    parser.load('..\\ltp_data\\parser.model')
    arcs = parser.parse(words, postags)
    parser.release()
    return list(arcs)

def ltp_postags(words):
    postagger = Postagger()
    model_path = '..\\ltp_data\\pos.model'
    lexicon_path = '..\\ltp_data\\posLexicon.txt'
    postagger.load_with_lexicon(model_path, lexicon_path)  # 加載自定義詞性表
    postagger.load(model_path)
    postags = postagger.postag(words)
    postagger.release()
    return list(postags)