forked from v-mipeng/LexiconAugmentedNER
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmetric.py
234 lines (204 loc) · 7.82 KB
/
metric.py
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
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
# -*- coding: utf-8 -*-
# from operator import add
#
import numpy as np
import math
import sys
import os
## input as sentence level labels
def get_ner_fmeasure(golden_lists, predict_lists, label_type="BMES",printnum=True):
sent_num = len(golden_lists)
golden_full = []
predict_full = []
right_full = []
right_tag = 0
all_tag = 0
for idx in range(0,sent_num):
# word_list = sentence_lists[idx]
golden_list = golden_lists[idx]
predict_list = predict_lists[idx]
for idy in range(len(golden_list)):
if golden_list[idy] == predict_list[idy]:
right_tag += 1
all_tag += len(golden_list)
if label_type == "BMES":
gold_matrix = get_ner_BMES(golden_list)
pred_matrix = get_ner_BMES(predict_list)
else:
gold_matrix = get_ner_BIO(golden_list)
pred_matrix = get_ner_BIO(predict_list)
# print "gold", gold_matrix
# print "pred", pred_matrix
right_ner = list(set(gold_matrix).intersection(set(pred_matrix)))
golden_full += gold_matrix
predict_full += pred_matrix
right_full += right_ner
right_num = len(right_full)
golden_num = len(golden_full)
predict_num = len(predict_full)
if predict_num == 0:
precision = -1
else:
precision = (right_num+0.0)/predict_num
if golden_num == 0:
recall = -1
else:
recall = (right_num+0.0)/golden_num
if (precision == -1) or (recall == -1) or (precision+recall) <= 0.:
f_measure = -1
else:
f_measure = 2*precision*recall/(precision+recall)
accuracy = (right_tag+0.0)/all_tag
# print "Accuracy: ", right_tag,"/",all_tag,"=",accuracy
if printnum:
print("gold_num = ", golden_num, " pred_num = ", predict_num, " right_num = ", right_num)
return accuracy, precision, recall, f_measure
def reverse_style(input_string):
target_position = input_string.index('[')
input_len = len(input_string)
output_string = input_string[target_position:input_len] + input_string[0:target_position]
return output_string
def get_ner_BMES(label_list):
# list_len = len(word_list)
# assert(list_len == len(label_list)), "word list size unmatch with label list"
list_len = len(label_list)
begin_label = 'B-'
end_label = 'E-'
single_label = 'S-'
whole_tag = ''
index_tag = ''
tag_list = []
stand_matrix = []
for i in range(0, list_len):
# wordlabel = word_list[i]
current_label = label_list[i].upper() if label_list[i] else []
if begin_label in current_label:
if index_tag != '':
tag_list.append(whole_tag + ',' + str(i-1))
whole_tag = current_label.replace(begin_label,"",1) +'[' +str(i)
index_tag = current_label.replace(begin_label,"",1)
elif single_label in current_label:
if index_tag != '':
tag_list.append(whole_tag + ',' + str(i-1))
whole_tag = current_label.replace(single_label,"",1) +'[' +str(i)
tag_list.append(whole_tag)
whole_tag = ""
index_tag = ""
elif end_label in current_label:
if index_tag != '':
tag_list.append(whole_tag +',' + str(i))
whole_tag = ''
index_tag = ''
else:
continue
if (whole_tag != '')&(index_tag != ''):
tag_list.append(whole_tag)
tag_list_len = len(tag_list)
for i in range(0, tag_list_len):
if len(tag_list[i]) > 0:
tag_list[i] = tag_list[i]+ ']'
insert_list = reverse_style(tag_list[i])
stand_matrix.append(insert_list)
# print stand_matrix
return stand_matrix
def get_ner_BIO(label_list):
# list_len = len(word_list)
# assert(list_len == len(label_list)), "word list size unmatch with label list"
list_len = len(label_list)
begin_label = 'B-'
inside_label = 'I-'
whole_tag = ''
index_tag = ''
tag_list = []
stand_matrix = []
for i in range(0, list_len):
# wordlabel = word_list[i]
current_label = label_list[i].upper()
if begin_label in current_label:
if index_tag == '':
whole_tag = current_label.replace(begin_label,"",1) +'[' +str(i)
index_tag = current_label.replace(begin_label,"",1)
else:
tag_list.append(whole_tag + ',' + str(i-1))
whole_tag = current_label.replace(begin_label,"",1) + '[' + str(i)
index_tag = current_label.replace(begin_label,"",1)
elif inside_label in current_label:
if current_label.replace(inside_label,"",1) == index_tag:
whole_tag = whole_tag
else:
if (whole_tag != '')&(index_tag != ''):
tag_list.append(whole_tag +',' + str(i-1))
whole_tag = ''
index_tag = ''
else:
if (whole_tag != '')&(index_tag != ''):
tag_list.append(whole_tag +',' + str(i-1))
whole_tag = ''
index_tag = ''
if (whole_tag != '')&(index_tag != ''):
tag_list.append(whole_tag)
tag_list_len = len(tag_list)
for i in range(0, tag_list_len):
if len(tag_list[i]) > 0:
tag_list[i] = tag_list[i]+ ']'
insert_list = reverse_style(tag_list[i])
stand_matrix.append(insert_list)
return stand_matrix
def readSentence(input_file):
in_lines = open(input_file,'r').readlines()
sentences = []
labels = []
sentence = []
label = []
for line in in_lines:
if len(line) < 2:
sentences.append(sentence)
labels.append(label)
sentence = []
label = []
else:
pair = line.strip('\n').split(' ')
sentence.append(pair[0])
label.append(pair[-1])
return sentences,labels
def readTwoLabelSentence(input_file, pred_col=-1):
in_lines = open(input_file,'r').readlines()
sentences = []
predict_labels = []
golden_labels = []
sentence = []
predict_label = []
golden_label = []
for line in in_lines:
if "##score##" in line:
continue
if len(line) < 2:
sentences.append(sentence)
golden_labels.append(golden_label)
predict_labels.append(predict_label)
sentence = []
golden_label = []
predict_label = []
else:
pair = line.strip('\n').split(' ')
sentence.append(pair[0])
golden_label.append(pair[1])
predict_label.append(pair[pred_col])
return sentences,golden_labels,predict_labels
def fmeasure_from_file(golden_file, predict_file, label_type="BMES"):
print( "Get f measure from file:", golden_file, predict_file)
print ("Label format:",label_type)
golden_sent,golden_labels = readSentence(golden_file)
predict_sent,predict_labels = readSentence(predict_file)
acc, P,R,F = get_ner_fmeasure(golden_labels, predict_labels, label_type)
print ("Acc:%s, P:%s R:%s, F:%s"%(acc, P,R,F))
def fmeasure_from_singlefile(twolabel_file, label_type="BMES", pred_col=-1):
sent,golden_labels,predict_labels = readTwoLabelSentence(twolabel_file, pred_col)
P,R,F = get_ner_fmeasure(golden_labels, predict_labels, label_type)
print ("P:%s, R:%s, F:%s"%(P,R,F))
if __name__ == '__main__':
# print "sys:",len(sys.argv)
if len(sys.argv) == 3:
fmeasure_from_singlefile(sys.argv[1],"BMES",int(sys.argv[2]))
else:
fmeasure_from_singlefile(sys.argv[1],"BMES")