#!/usr/bin/python
#?-*-?coding:utf-8?-*-
#?**************************
#?*?Author??????:??baiyyang
#?*?Email???????:??baiyyang@163.com
#?*?Description?:??
#?*?create?time?:??2018/1/10上午10:29
#?*?file?name???:??crf_unit.py


import?sys
import?codecs
import?pycrfsuite
import?string
import?zhon.hanzi?as?zh
import?reader
from?sklearn.metrics?import?classification_report
from?sklearn.preprocessing?import?LabelBinarizer
reload（sys）
sys.setdefaultencoding（‘utf-8‘）


#?獲取數據
def?readData（filename）:
????fr?=?codecs.open（filename?‘r‘?‘utf-8‘）
????data?=?[]
????for?line?in?fr:
????????fields?=?line.strip（）.split（‘\t‘）
????????if?len（fields）?==?3:
????????????data.append（fields）
????return?data


train?=?readData（‘train.txt‘）
test?=?readData（‘test.txt‘）


#?判斷是否為標點符號
#?punctuation
def?ispunctuation（word）:
????punctuation?=?string.punctuation?+?zh.punctuation
????if?punctuation.find（word）?!=?-1:
????????return?True
????else:
????????return?False


#?特征定義
def?word2features（sent?i）:
????“““返回特征列表“““
????word?=?sent[i][0]
????postag?=?sent[i][1]
????features?=?[
????????‘bias‘
????????‘word=‘?+?word
????????‘word_tag=‘?+?postag
????]
????if?i?>?0:
????????features.append（‘word[-1]=‘?+?sent[i-1][0]）
????????features.append（‘word[-1]_tag=‘?+?sent[i-1][1]）
????????if?i?>?1:
????????????features.append（‘word[-2]=‘?+?sent[i-2][0]）
????????????features.append（‘word[-2?-1]=‘?+?sent[i-2][0]?+?sent[i-1][0]）
????????????features.append（‘word[-2]_tag=‘?+?sent[i-2][1]）
????if?i?????????features.append（‘word[1]=‘?+?sent[i+1][0]）
????????features.append（‘word[1]_tag=‘?+?sent[i+1][1]）
????????if?i?????????????features.append（‘word[2]=‘?+?sent[i+2][0]）
????????????features.append（‘word[1?2]=‘?+?sent[i+1][0]?+?sent[i+2][0]）
????????????features.append（‘word[2]_tag=‘?+?sent[i+2][1]）
????return?features


def?sent2feature（sent）:
????return?[word2features（sent?i）?for?i?in?range（len（sent））]


def?sent2label（sent）:
????return?[label?for?word?tag?label?in?sent]


def?sent2word（sent）:
????return?[word?for?word?tag?label?in?sent]


X_train?=?sent2feature（train）
y_train?=?sent2label（train）

X_test?=?sent2feature（test）
y_test?=?sent2label（test）

#?訓練模型
model?=?pycrfsuite.Trainer（verbose=True）
model.append（X_train?y_train）
model.set_params（{
????‘c1‘:?1.0??#?coefficient?for?L1?penalty
????‘c2‘:?1e-3??#?coefficient?for?L2?penalty
????‘max_iterations‘:?100??#?stop?earlier
????#?include?transitions?that?are?possible?but?not?observed
????‘feature.possible_transitions‘:?True
????‘feature.minfreq‘:?3
}）

model.train（‘./medical.crfsuite‘）


#?預測數據
tagger?=?pycrfsuite.Tagger（）
tagger.open（‘./medical.crfsuite‘）

#?一份測試數據集
print?‘?‘.join（sent2word（readData（‘test1.txt‘）））
predicted?=?tagger.tag（sent2feature（readData（‘test1.txt‘）））
correct?=?sent2label（readData（‘test1.txt‘））

#?預測結果對比
print?‘Predicted:?‘?‘?‘.join（predicted）
print?‘Correct:?‘?‘?‘.join（correct）

#?預測準確率
num?=?0
for?i?tag?in?enumerate（predicted）:
????if?tag?==?correct[i]:
????????num?

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2018-05-03?01:54??medical_ner_crfsuite-master\
?????文件????????1239??2018-05-03?01:54??medical_ner_crfsuite-master\README.md
?????文件????????4103??2018-05-03?01:54??medical_ner_crfsuite-master\crf_unit.py
?????目錄???????????0??2018-05-03?01:54??medical_ner_crfsuite-master\data\
?????文件????????2350??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-1.txt
?????文件????????2505??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-10.txt
?????文件????????4555??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-100.txt
?????文件????????2898??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-11.txt
?????文件????????5652??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-12.txt
?????文件????????2127??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-13.txt
?????文件????????2832??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-14.txt
?????文件????????2314??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-15.txt
?????文件????????2533??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-16.txt
?????文件????????3044??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-17.txt
?????文件????????2310??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-18.txt
?????文件????????5179??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-19.txt
?????文件????????2368??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-2.txt
?????文件????????2010??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-20.txt
?????文件?????????233??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-21.txt
?????文件????????5934??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-22.txt
?????文件????????2808??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-23.txt
?????文件????????5115??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-24.txt
?????文件????????5503??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-25.txt
?????文件????????3506??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-26.txt
?????文件????????2210??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-27.txt
?????文件????????2457??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-28.txt
?????文件????????3772??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-29.txt
?????文件????????3023??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-3.txt
?????文件????????3063??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-30.txt
?????文件????????2256??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-31.txt
?????文件????????1810??2018-05-03?01:54??medical_ner_crfsuite-master\data\病史特點-32.txt
............此處省略79個文件信息