tagging.py
17.4 KB
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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
# -*- coding: UTF-8 -*-
import os
import re
from pandas import DataFrame as DF
from optparse import OptionParser
from time import time
from collections import Counter
import nltk
import sklearn
import scipy.stats
import sys
import joblib
from sklearn.metrics import make_scorer
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RandomizedSearchCV
import sklearn_crfsuite
from sklearn_crfsuite import scorers
from sklearn_crfsuite import metrics
from nltk.corpus import stopwords
import training_validation_v14 as training
#-------------------------------------------------------------------------------
# Objective
# Tagging transformed file with CRF model with sklearn-crfsuite.
#
# Input parameters
# --inputPath=PATH Path of transformed files x|y|z
# --outputPath Output path to place output files
# --outputFileI Output tagged file I
# --outputFileII Output tagged file II
# --modelPath Path to CRF model
# --modelName Model name
# --infoPath Path of GSE-GSM index file
# --infoFile GSE-GSM index file",
# --variant Part of S2 variant
# --S1 Inner word features set
# --S2 Complete word features
# --S3 Extended context features
# --S4 Semantic features
# --filteringStopWords Filtering stop words
# --filterSymbols Filtering punctuation marks
# Output
# 1) Tagged files in transformed format
# Examples
# --inputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/input/
# --outputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/output/
# --outputFileI annot-input_bg_outputI.txt
# --outputFileII annot-input_bg_outputII.txt
# --modelPath /home/egaytan/automatic-extraction-growth-conditions/CRF/models
# --modelName model_Run3_v10_S1_False_S2_True_S3_False_S4_False_Run3_v10
# --infoPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/mapping
# --infoFile bg_sentences_midx.txt
# --variant 13
#Examples
#python3 tagging.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/input/ --outputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/output/ --outputFileI annot-input_bg_outputI.txt --outputFileII annot-input_bg_outputII.txt --modelPath /home/egaytan/automatic-extraction-growth-conditions/CRF/models --modelName model_Run3_v10_S1_False_S2_True_S3_False_S4_False_Run3_v10 --infoPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/mapping --infoFile bg_sentences_midx.txt --variant 13 --S4 --S1 > ../../reports/output_tagging_report.txt
#python3 predict-annot/bin/tagging/tagging.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/input/ --outputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/output/ --outputFileI annot-input_bg_outputI_v4.txt --outputFileII annot-input_bg_outputII_v4 --modelPath /home/egaytan/automatic-extraction-growth-conditions/CRF/models --modelName model_Run3_v10_S1_False_S2_True_S3_False_S4_False_Run3_v10 --infoPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/mapping --infoFile bg_sentences_midx_v4.txt --variant 13 --S4 --S1 > predict-annot/reports/output_tagging_report_v4.txt
#python3 predict-annot/bin/tagging/tagging.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/input/ --outputPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/output/ --outputFileI annot-input_bg_outputI_v4.txt --outputFileII annot-input_bg_outputII_v4 --outputFileII annot-input_bg_outputIII_v4 --modelPath /home/egaytan/automatic-extraction-growth-conditions/CRF/models --modelName model_Run3_v10_S1_False_S2_True_S3_False_S4_False_Run3_v10 --infoPath /home/egaytan/automatic-extraction-growth-conditions/predict-annot/mapping --infoFile bg_sentences_midx_v4.txt --variant 13 --S4 --S1 > predict-annot/reports/annot-input_bg_report_v4.txt
__author__ = 'egaytan'
##########################################
# MAIN PROGRAM #
##########################################
if __name__ == "__main__":
########################################### Defining parameters ##########################################
parser = OptionParser()
parser.add_option("--inputPath", dest="inputPath", help="Path of training data set", metavar="PATH")
parser.add_option("--outputPath", dest="outputPath", help="Output path to place output files", metavar="PATH")
parser.add_option("--outputFileI", dest="outFileI", help="Output tagged file I", metavar="FILE")
parser.add_option("--outputFileII", dest="outFileII", help="Output tagged file II", metavar="FILE")
parser.add_option("--outputFileIII", dest="outFileIII", help="Output tagged file III", metavar="FILE")
parser.add_option("--modelPath", dest="modelPath", help="Path to read CRF model", metavar="PATH")
parser.add_option("--modelName", dest="modelName", help="Model name", metavar="TEXT")
parser.add_option("--infoPath", dest="infoPath", help="Path of GSE-GSM index file", metavar="PATH")
parser.add_option("--infoFile", dest="idx", help="GSE-GSM index file", metavar="FILE")
parser.add_option("--variant", dest="variant", help="Run variant", metavar="FILE")
parser.add_option("--S1", dest="S1", help="General features", action="store_true", default=False)
parser.add_option("--S2", dest="S2", help="Inner/Complete word features", action="store_true", default=False)
parser.add_option("--S3", dest="S3", help="Extended context features", action="store_true", default=False)
parser.add_option("--S4", dest="S4", help="Semantic features", action="store_true", default=False)
parser.add_option("--filterStopWords", dest="filterStopWords", help="Filtering stop words", action="store_true", default=False)
parser.add_option("--filterSymbols", dest="filterSymbols", help="Filtering punctuation marks", action="store_true", default=False)
(options, args) = parser.parse_args()
if len(args) > 0:
parser.error("Any parameter given.")
sys.exit(1)
########################################### DISP PARAMETERS ##########################################
print('-------------------------------- PARAMETERS --------------------------------')
print("--inputPath Path of training data set : " + str(options.inputPath ))
print("--outputPath Output path to place output files: " + str(options.outputPath ))
print("--outputFileI Output tagged file I : " + str(options.outFileI ))
print("--outputFileII Output tagged file II : " + str(options.outFileII ))
print("--outputFileII Output tagged file III : " + str(options.outFileIII ))
print("--modelPath Path to read CRF model : " + str(options.modelPath ))
print("--modelName Model name : " + str(options.modelName ))
print("--infoPath Path of GSE-GSM index file : " + str(options.infoPath ))
print("--infoFile GSE-GSM index file : " + str(options.idx ))
print("--variant Run variant : " + str(options.variant ))
print("--S1 General features : " + str(options.S1 ))
print("--S2 Inner/Complete word features : " + str(options.S2 ))
print("--S3 Extended context features : " + str(options.S3 ))
print("--S4 Semantic features : " + str(options.S4 ))
print("--filteringStopWords Filtering stop words : " + str(options.filterStopWords ))
print("--filterSymbols Filtering punctuation marks : " + str(options.filterSymbols ))
symbols = ['.', ',', ':', ';', '?', '!', '\'', '"', '<', '>', '(', ')', '-', '_', '/', '\\', '¿', '¡', '+', '{',
'}', '[', ']', '*', '%', '$', '#', '&', '°', '`', '...']
#print("Filtering symbols " + str(symbols) + ': ' + str(options.filterSymbols))
########################################### PROCESSING ##########################################
print('-------------------------------- PROCESSING --------------------------------')
stopwords = [word for word in stopwords.words('english')]
# Read index mapping GSE file information
idx = open(os.path.join(options.infoPath, options.idx), "r").readlines()
########################################### Read CRF model ##########################################
t0 = time()
print('Reading CRF model...')
crf = joblib.load(os.path.join(options.modelPath, options.modelName + '.mod'))
print("Reading CRF model done in: %fs" % (time() - t0))
########################################### Reading sentences ##########################################
print('Processing corpus...')
t0 = time()
labels = list(['Gtype', 'Gversion', 'Med', 'Phase', 'Strain', 'Substrain', 'Supp', 'Technique', 'Temp', 'OD', 'Anti', 'Agit', 'Air', 'Vess', 'pH'])
#####################################################################################
# Walk directory to read files
for path, dirs, files in os.walk(options.inputPath):
# For each file in dir
for file in files:
print("Preprocessing file..." + str(file))
sentencesInputData = []
sentencesOutputDataI = []
sentencesOutputDataII = []
with open(os.path.join(options.inputPath, file), "r") as iFile:
lines = iFile.readlines()
for line in lines:
listLine = []
for token in line.strip('\n').split():
if options.filterStopWords:
listToken = token.split('|')
lemma = listToken[1]
if lemma in stopwords:
continue
if options.filterSymbols:
listToken = token.split('|')
lemma = listToken[1]
if lemma in symbols:
if lemma == ',':
print("Coma , identificada")
continue
listLine.append(token)
sentencesInputData.append(listLine)
X_input = [training.sent2features(s, options.S1, options.S2, options.S3, options.S4, options.variant) for s in sentencesInputData]
print("Sentences input data: " + str(len(sentencesInputData)))
########################################### Predicting tags ###########################################
t1 = time()
print("Predicting tags with model...")
y_pred = crf.predict(X_input)
print("Prediction done in: %fs" % (time() - t1))
########################################### Tagging with CRF model ###########################################
print("Tagging file...")
lidx = 0
for line, tagLine in zip(lines, y_pred):
Ltags = set(labels).intersection(set(tagLine))
outputLine = ''
line = line.strip('\n')
tb = 'O'
i = 0
########################## one word sentences ##########################
if len(tagLine)==1:
if tagLine[0] in labels:
start = '<' + tagLine[0] + '> '
end = '</' + tagLine[0] + '/>'
word = line.split('|')[0] + ' '
outputLine = start + word + end
else:
outputLine = line.split(' ')[0]
########################## Saving Sentence Ouput I ##########################
sentencesOutputDataI.append(idx[lidx].replace('\n','\t') + outputLine + '\t' + ', '.join(Ltags))
########################## Saving Sentence Ouput II ##########################
sentencesOutputDataII.append(idx[lidx].replace('\n', '\t') + word.split('|')[0] + '\t' + tag)
lidx += 1
continue
sentence = ''
sb = False
for word,tag in zip(line.split(' '), tagLine):
# start tagging
if tag in labels and tb != tag:
# start tagging
outputLine += '<' + tag + '> '
sb = True
sentence = word.split('|')[0] + ' '
tb = tag
outputLine += word.split('|')[0] + ' '
i += 1
continue
# end tagging
elif tb in labels:
if i+1==len(tagLine):
# end sentence
outputLine += word.split('|')[0] + ' '
outputLine += '</' + tag + '/> '
########################## Saving Sentence Ouput II ##########################
sentencesOutputDataII.append(idx[lidx].replace('\n', '\t') + sentence + word.split('|')[0] + '\t' +tag)
sb = False
tb = 'O'
i += 1
continue
elif tag!=tagLine[i+1]:
# start new tag
outputLine += word.split('|')[0] + ' '
outputLine += '</' + tag + '/> '
########################## Saving Sentence Ouput II ##########################
sentencesOutputDataII.append(idx[lidx].replace('\n', '\t') + sentence + word.split('|')[0] + '\t' +tag)
sb = False
tb = 'O'
i += 1
continue
# word tagged
outputLine += word.split('|')[0] + ' '
i += 1
if sb:
sentence+= word.split('|')[0] + ' '
########################## Saving Sentence Ouput I ##########################
sentencesOutputDataI.append(idx[lidx].replace('\n', '\t') + outputLine+ '\t' +', '.join(Ltags))
lidx += 1
########################################### Save Output I ##########################################
print("Saving Ouput I...")
with open(os.path.join(options.outputPath, options.outFileI + '_' + options.modelName + '.tsv'), "w") as oFileI:
for line in sentencesOutputDataI:
if re.findall('</', line):
#print(line)
oline = line.replace('LDR','(')
oline = oline.replace('RDR',')')
oFileI.write(oline + '\n')
########################################### Save Output II ##########################################
print("Saving Ouput II...")
with open(os.path.join(options.outputPath, options.outFileII + '_' + options.modelName + '.tsv'), "w") as oFileII:
for line in sentencesOutputDataII:
#print(line)
oline = line.replace('LDR','(')
oline = oline.replace('RDR',')')
oFileII.write(oline + '\n')
########################################### Save Output III ##########################################
print("Saving Ouput III...")
with open(os.path.join(options.outputPath, options.outFileIII + '_' + options.modelName + '.tsv'), "w") as oFileIII:
for line, tagLine in zip(lines, y_pred):
oline = [ w.split('|')[0].replace('LDR','(').replace('LDR','(')+'|'+tag for w,tag in zip(line.split(' '), tagLine)]
oFileIII.write(' '.join(oline) + '\n')
print("Processing corpus done in: %fs" % (time() - t0))