File size: 6,889 Bytes
d5062c8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 |
# -*- coding: utf-8 -*-
"""
Created on Tue Mar 10 16:34:12 2020
@author: luol2
"""
import numpy as np
import io
import sys
#read ner text (word\tlabel), generate the list[[[w1,label],[w2,label]]]
def ml_intext(file):
fin=open(file,'r',encoding='utf-8')
alltexts=fin.read().strip().split('\n\n')
fin.close()
data_list=[]
label_list=[]
for sents in alltexts:
lines=sents.split('\n')
temp_sentece=[]
for i in range(0,len(lines)):
seg=lines[i].split('\t')
temp_sentece.append(seg[:])
label_list.append(seg[-1])
data_list.append(temp_sentece)
#print(data_list)
#print(label_list)
return data_list,label_list
def ml_intext_fn(alltexts):
# fin=io.StringIO(ml_input)
# alltexts=fin.read().strip().split('\n\n')
# fin.close()
data_list=[]
label_list=[]
for sents in alltexts:
lines=sents.split('\n')
temp_sentece=[]
for i in range(0,len(lines)):
seg=lines[i].split('\t')
temp_sentece.append(seg[:])
label_list.append(seg[-1])
data_list.append(temp_sentece)
#print(data_list)
#print(label_list)
return data_list,label_list
# model predict result to conll evalute format [token answer predict]
def out_BIO(file,raw_pre,raw_input,label_set):
fout=open(file,'w',encoding='utf-8')
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
label_id = raw_pre[i][j]
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
fout.close()
def out_BIO_softmax(file,raw_pre,raw_input,label_set):
fout=open(file,'w',encoding='utf-8')
#print(raw_pre[0:2])
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
label_id = np.argmax(raw_pre[i][j])
#print(label_id)
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
fout.close()
def out_BIO_fn(raw_pre,raw_input,label_set):
fout=io.StringIO()
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
label_id = raw_pre[i][j]
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
return fout.getvalue()
def out_BIO_BERT_softmax(file,raw_pre,raw_input,label_set):
fout=open(file,'w',encoding='utf-8')
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
# label_id = raw_pre[i][j]
label_id = np.argmax(raw_pre[i][j])
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
fout.close()
def out_BIO_BERT(file,raw_pre,raw_input,label_set):
fout=open(file,'w',encoding='utf-8')
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
label_id = raw_pre[i][j]
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
fout.close()
def out_BIO_BERT_fn(raw_pre,raw_input,label_set):
fout=io.StringIO()
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
label_id = raw_pre[i][j]
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
return fout.getvalue()
def out_BIO_BERT_softmax_fn(raw_pre,raw_input,label_set):
fout=io.StringIO()
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
#label_id = raw_pre[i][j]
label_id = np.argmax(raw_pre[i][j])
label_tag = label_set[str(label_id)]
else:
label_tag='O'
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\n')
fout.write('\n')
return fout.getvalue()
def out_BIO_BERT_softmax_score_fn(raw_pre,raw_input,label_set):
fout=io.StringIO()
for i in range(len(raw_input)):
for j in range(len(raw_input[i])):
if j<len(raw_pre[i]):
#label_id = raw_pre[i][j]
label_id = np.argmax(raw_pre[i][j])
label_score = round(raw_pre[i][j][label_id],4)
label_tag = label_set[str(label_id)]
else:
label_tag='O'
label_score = 0.0
fout.write(raw_input[i][j][0]+'\t'+raw_input[i][j][-1]+'\t'+label_tag+'\t'+str(label_score)+'\n')
fout.write('\n')
return fout.getvalue()
#generate char vocab
def char_vocab(infile,outfile_char):
fin=open(infile,'r',encoding='utf-8')
#fout=open(outfile,'w',encoding='utf-8')
fout_char=open(outfile_char,'w',encoding='utf-8')
char_vocab=['oov_char']
max_len=0
for line in fin:
if line.strip()!='':
seg=line.split('\t')
word_len=len(seg[0])
#if word_len<1000:
# fout.write(line)
if word_len>max_len:
max_len=word_len
print(seg[0])
for i in range(word_len):
if seg[0][i] not in char_vocab:
char_vocab.append(seg[0][i])
#else:
# fout.write(line)
fin.close()
#fout.close()
for ele in char_vocab:
fout_char.write(ele+'\n')
fout_char.close()
print('max_len:',max_len)
if __name__=='__main__':
# infile='//panfs/pan1/bionlp/lulab/luoling/HPO_project/AutoPhe/data/pubmed_unlabel/mutation_disease_1990.ner_BIO'
# #outfile='//panfs/pan1/bionlp/lulab/luoling/HPO_project/AutoPhe/data/pubmed_unlabel/mutation_disease_1990.ner_BIO_new'
# outfile_char='//panfs/pan1/bionlp/lulab/luoling/HPO_project/AutoPhe/src/nn_model/vocab/char_vocab'
# #processing_text(file)
# char_vocab(infile,outfile_char)
a=[1,2,3]
print(a[:-1])
|