Carlos-Francisco Méndez-Cruz / conditional-random-fields

Go to a project
Toggle navigation Toggle navigation pinning
Carlos-Francisco Méndez-Cruz
1393a83f 1 parent 4791fb14

Obtaining training and test data sets

Inline Side-by-side
Showing 1 changed file with 30 additions and 174 deletions
...@@ -32,7 +32,7 @@ from nltk.corpus import stopwords ...@@ -32,7 +32,7 @@ from nltk.corpus import stopwords
32 # --testFile File with test data set 32 # --testFile File with test data set
33 # --outputPath=PATH Output path to place output files 33 # --outputPath=PATH Output path to place output files
34 # --filteringStopWords Filtering stop words 34 # --filteringStopWords Filtering stop words
35 -# --filterSymbols Filtering punctuation marks 35 +# --excludeSymbols Filtering punctuation marks
36 36
37 # Output 37 # Output
38 # 1) Best model 38 # 1) Best model
...@@ -42,116 +42,44 @@ from nltk.corpus import stopwords ...@@ -42,116 +42,44 @@ from nltk.corpus import stopwords
42 # --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets 42 # --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets
43 # --trainingFile training-data-set-70.txt 43 # --trainingFile training-data-set-70.txt
44 # --testFile test-data-set-30.txt 44 # --testFile test-data-set-30.txt
45 -# --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields/reports 45 +# --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields
46 -# python3.4 training-validation-v1.py --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields/reports 46 +# python3.4 training-validation-v1.py --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields
47 47
48 ################################# 48 #################################
49 # FUNCTIONS # 49 # FUNCTIONS #
50 ################################# 50 #################################
51 51
52 -def wordSize(text):
53 - lWord = len(text)
54 - if lWord == 1:
55 - return '1'
56 - elif lWord == 2:
57 - return '2'
58 - elif lWord == 3:
59 - return '3'
60 - elif lWord == 4:
61 - return '4'
62 - elif lWord == 5:
63 - return '5'
64 - elif 6 <= lWord <= 10:
65 - return '6-10'
66 - elif 11 <= lWord <= 15:
67 - return '11-15'
68 - elif 16 <= lWord <= 20:
69 - return '16-20'
70 - elif 21 <= lWord <= 30:
71 - return '21-30'
72 - else:
73 - return '>30'
74 -
75 -def hasUpperLower(text):
76 - has = False
77 - if len(text) < 3:
78 - return False
79 - regexUp = nltk.re.compile('[A-Z]')
80 - regexLo = nltk.re.compile('[a-z]')
81 - if (regexUp.search(text) != None) and (regexLo.search(text) != None):
82 - has = True
83 - return has
84 -
85 -def hasDigit(text):
86 - has = False
87 - if len(text) < 3:
88 - return False
89 - myRegex = nltk.re.compile('[0-9]')
90 - if myRegex.search(text) != None:
91 - has = True
92 - return has
93 -
94 -
95 -def hasNonAlphaNum(text):
96 - has = False
97 - if len(text) < 3:
98 - return False
99 - myRegex = nltk.re.compile('\W')
100 - if myRegex.search(text) != None:
101 - has = True
102 - return has
103 -
104 def word2features(sent, i): 52 def word2features(sent, i):
105 - # print "i: " + str(i)
106 - # print "sent[i]" + sent[i]
107 listElem = sent[i].split('|') 53 listElem = sent[i].split('|')
108 word = listElem[0] 54 word = listElem[0]
109 lemma = listElem[1] 55 lemma = listElem[1]
110 postag = listElem[2] 56 postag = listElem[2]
111 57
112 features = { 58 features = {
113 - # Names of TF and genes change by lower and upper characters: 'word.lower()': word.lower(),
114 # Suffixes 59 # Suffixes
115 'word[-3:]': word[-3:], 60 'word[-3:]': word[-3:],
116 'word[-2:]': word[-2:], 61 'word[-2:]': word[-2:],
117 'word[-1:]': word[-1:], 62 'word[-1:]': word[-1:],
118 - 'word.isupper()': word.isupper(), 63 + #'word.isupper()': word.isupper(),
119 - 'word.istitle()': word.istitle(),
120 - 'word.hasDigit()': hasDigit(word),
121 - 'word.hasNonAlphaNum': hasNonAlphaNum(word),
122 - # 'word.hasUpperLower': hasUpperLower(word),
123 - #'wordSize': wordSize(word),
124 - # 'word.isdigit()': word.isdigit(),
125 'word': word, 64 'word': word,
126 'lemma': lemma, 65 'lemma': lemma,
127 'lemma[-3:]': lemma[-3:], 66 'lemma[-3:]': lemma[-3:],
128 'lemma[-2:]': lemma[-2:], 67 'lemma[-2:]': lemma[-2:],
129 'lemma[-1:]': lemma[-1:], 68 'lemma[-1:]': lemma[-1:],
130 - 'postag': postag, 69 + 'word[:3]': word[:3],
131 - # Prefixes 70 + 'word[:2]': word[:2],
132 - 'postag[:2]': postag[:2], 71 + 'word[:1]': word[:1],
133 - 'postag[:1]': postag[:1],
134 } 72 }
73 + '''
135 if i > 0: 74 if i > 0:
136 listElem = sent[i - 1].split('|') 75 listElem = sent[i - 1].split('|')
137 word1 = listElem[0] 76 word1 = listElem[0]
138 lemma1 = listElem[1] 77 lemma1 = listElem[1]
139 postag1 = listElem[2] 78 postag1 = listElem[2]
140 features.update({ 79 features.update({
141 - '-1:word.lower()': word1.lower(),
142 - '-1:word.istitle()': word1.istitle(),
143 - '-1:word.isupper()': word1.isupper(),
144 - '-1:word.hasDigit()': hasDigit(word1),
145 - '-1:word.hasNonAlphaNum': hasNonAlphaNum(word1),
146 - # '-1:word.hasUpperLower': hasUpperLower(word1),
147 '-1:word': word1, 80 '-1:word': word1,
148 '-1:lemma': lemma1, 81 '-1:lemma': lemma1,
149 - '-1:postag': postag1,
150 - '-1:postag[:2]': postag1[:2],
151 - '-1:postag[:1]': postag1[:1],
152 }) 82 })
153 - # else:
154 - # features['BOS'] = True
155 83
156 if i < len(sent) - 1: 84 if i < len(sent) - 1:
157 listElem = sent[i + 1].split('|') 85 listElem = sent[i + 1].split('|')
...@@ -159,37 +87,18 @@ def word2features(sent, i): ...@@ -159,37 +87,18 @@ def word2features(sent, i):
159 lemma1 = listElem[1] 87 lemma1 = listElem[1]
160 postag1 = listElem[2] 88 postag1 = listElem[2]
161 features.update({ 89 features.update({
162 - '+1:word.lower()': word1.lower(),
163 - '+1:word.istitle()': word1.istitle(),
164 - '+1:word.isupper()': word1.isupper(),
165 - '+1:word.hasDigit()': hasDigit(word1),
166 - '+1:word.hasNonAlphaNum': hasNonAlphaNum(word1),
167 - # '+1:word.hasUpperLower': hasUpperLower(word1),
168 '+1:word': word1, 90 '+1:word': word1,
169 '+1:lemma': lemma1, 91 '+1:lemma': lemma1,
170 - '+1:postag': postag1,
171 - '+1:postag[:2]': postag1[:2],
172 - '+1:postag[:1]': postag1[:1],
173 }) 92 })
174 - # else: 93 +
175 - # features['EOS'] = True
176 if i > 1: 94 if i > 1:
177 listElem = sent[i - 2].split('|') 95 listElem = sent[i - 2].split('|')
178 word2 = listElem[0] 96 word2 = listElem[0]
179 lemma2 = listElem[1] 97 lemma2 = listElem[1]
180 postag2 = listElem[2] 98 postag2 = listElem[2]
181 features.update({ 99 features.update({
182 - '-2:word.lower()': word2.lower(),
183 - '-2:word.istitle()': word2.istitle(),
184 - '-2:word.isupper()': word2.isupper(),
185 - '-2:word.hasDigit()': hasDigit(word2),
186 - '-2:word.hasNonAlphaNum': hasNonAlphaNum(word2),
187 - # '-2:word.hasUpperLower': hasUpperLower(word2),
188 '-2:word': word2, 100 '-2:word': word2,
189 '-2:lemma': lemma2, 101 '-2:lemma': lemma2,
190 - '-2:postag': postag2,
191 - '-2:postag[:2]': postag2[:2],
192 - '-2:postag[:1]': postag2[:1],
193 }) 102 })
194 103
195 if i < len(sent) - 2: 104 if i < len(sent) - 2:
...@@ -198,17 +107,8 @@ def word2features(sent, i): ...@@ -198,17 +107,8 @@ def word2features(sent, i):
198 lemma2 = listElem[1] 107 lemma2 = listElem[1]
199 postag2 = listElem[2] 108 postag2 = listElem[2]
200 features.update({ 109 features.update({
201 - '+2:word.lower()': word2.lower(),
202 - '+2:word.istitle()': word2.istitle(),
203 - '+2:word.isupper()': word2.isupper(),
204 - '+2:word.hasDigit()': hasDigit(word2),
205 - '+2:word.hasNonAlphaNum': hasNonAlphaNum(word2),
206 - # '+2:word.hasUpperLower': hasUpperLower(word2),
207 '+2:word': word2, 110 '+2:word': word2,
208 '+2:lemma': lemma2, 111 '+2:lemma': lemma2,
209 - '+2:postag': postag2,
210 - '+2:postag[:2]': postag2[:2],
211 - '+2:postag[:1]': postag2[:1],
212 }) 112 })
213 113
214 trigrams = False 114 trigrams = False
...@@ -219,17 +119,8 @@ def word2features(sent, i): ...@@ -219,17 +119,8 @@ def word2features(sent, i):
219 lemma3 = listElem[1] 119 lemma3 = listElem[1]
220 postag3 = listElem[2] 120 postag3 = listElem[2]
221 features.update({ 121 features.update({
222 - '-3:word.lower()': word3.lower(),
223 - '-3:word.istitle()': word3.istitle(),
224 - '-3:word.isupper()': word3.isupper(),
225 - '-3:word.hasDigit()': hasDigit(word3),
226 - '-3:word.hasNonAlphaNum': hasNonAlphaNum(word3),
227 - # '-3:word.hasUpperLower': hasUpperLower(word3),
228 '-3:word': word3, 122 '-3:word': word3,
229 '-3:lemma': lemma3, 123 '-3:lemma': lemma3,
230 - '-3:postag': postag3,
231 - '-3:postag[:2]': postag3[:2],
232 - '-3:postag[:1]': postag3[:1],
233 }) 124 })
234 125
235 if i < len(sent) - 3: 126 if i < len(sent) - 3:
...@@ -238,19 +129,10 @@ def word2features(sent, i): ...@@ -238,19 +129,10 @@ def word2features(sent, i):
238 lemma3 = listElem[1] 129 lemma3 = listElem[1]
239 postag3 = listElem[2] 130 postag3 = listElem[2]
240 features.update({ 131 features.update({
241 - '+3:word.lower()': word3.lower(),
242 - '+3:word.istitle()': word3.istitle(),
243 - '+3:word.isupper()': word3.isupper(),
244 - '+3:word.hasDigit()': hasDigit(word3),
245 - '+3:word.hasNonAlphaNum': hasNonAlphaNum(word3),
246 - # '+3:word.hasUpperLower': hasUpperLower(word3),
247 '+3:word': word3, 132 '+3:word': word3,
248 '+3:lemma': lemma3, 133 '+3:lemma': lemma3,
249 - '+3:postag': postag3,
250 - '+3:postag[:2]': postag3[:2],
251 - '+3:postag[:1]': postag3[:1],
252 }) 134 })
253 - 135 + '''
254 return features 136 return features
255 137
256 138
...@@ -260,7 +142,6 @@ def sent2features(sent): ...@@ -260,7 +142,6 @@ def sent2features(sent):
260 142
261 def sent2labels(sent): 143 def sent2labels(sent):
262 return [elem.split('|')[3] for elem in sent] 144 return [elem.split('|')[3] for elem in sent]
263 - # return [label for token, postag, label in sent]
264 145
265 146
266 def sent2tokens(sent): 147 def sent2tokens(sent):
...@@ -269,19 +150,11 @@ def sent2tokens(sent): ...@@ -269,19 +150,11 @@ def sent2tokens(sent):
269 150
270 def print_transitions(trans_features, f): 151 def print_transitions(trans_features, f):
271 for (label_from, label_to), weight in trans_features: 152 for (label_from, label_to), weight in trans_features:
272 - # f.write("%-6s -> %-7s %0.6f\n" % (label_from, label_to, weight))
273 - # f.write("label_from :" + label_from)
274 - # f.write("label_to :" + label_to)
275 - # f.write("label_weight :" + weight)
276 - # f.write("{} -> {} {:0.6f}\n".format(label_from.encode("utf-8"), label_to.encode("utf-8"), weight))
277 f.write("{:6} -> {:7} {:0.6f}\n".format(label_from, label_to, weight)) 153 f.write("{:6} -> {:7} {:0.6f}\n".format(label_from, label_to, weight))
278 154
279 155
280 def print_state_features(state_features, f): 156 def print_state_features(state_features, f):
281 for (attr, label), weight in state_features: 157 for (attr, label), weight in state_features:
282 - # f.write("%0.6f %-8s %s\n" % (weight, label, attr))
283 - # f.write(attr.encode("utf-8"))
284 - # '{:06.2f}'.format(3.141592653589793)
285 f.write("{:0.6f} {:8} {}\n".format(weight, label, attr.encode("utf-8"))) 158 f.write("{:0.6f} {:8} {}\n".format(weight, label, attr.encode("utf-8")))
286 159
287 160
...@@ -303,12 +176,12 @@ if __name__ == "__main__": ...@@ -303,12 +176,12 @@ if __name__ == "__main__":
303 help="File with training data set", metavar="FILE") 176 help="File with training data set", metavar="FILE")
304 parser.add_option("--testFile", dest="testFile", 177 parser.add_option("--testFile", dest="testFile",
305 help="File with test data set", metavar="FILE") 178 help="File with test data set", metavar="FILE")
306 - parser.add_option("--filterStopWords", default=False, 179 + parser.add_option("--excludeStopWords", default=False,
307 - action="store_true", dest="filterStopWords", 180 + action="store_true", dest="excludeStopWords",
308 - help="Filtering stop words") 181 + help="Exclude stop words")
309 - parser.add_option("--filterSymbols", default=False, 182 + parser.add_option("--excludeSymbols", default=False,
310 - action="store_true", dest="filterSymbols", 183 + action="store_true", dest="excludeSymbols",
311 - help="Filtering punctuation marks") 184 + help="Exclude punctuation marks")
312 185
313 (options, args) = parser.parse_args() 186 (options, args) = parser.parse_args()
314 if len(args) > 0: 187 if len(args) > 0:
...@@ -320,10 +193,10 @@ if __name__ == "__main__": ...@@ -320,10 +193,10 @@ if __name__ == "__main__":
320 print("File with training data set: " + str(options.trainingFile)) 193 print("File with training data set: " + str(options.trainingFile))
321 print("Path of test data set: " + options.inputPath) 194 print("Path of test data set: " + options.inputPath)
322 print("File with test data set: " + str(options.testFile)) 195 print("File with test data set: " + str(options.testFile))
323 - print("Filtering stop words: " + str(options.filterStopWords)) 196 + print("Exclude stop words: " + str(options.excludeStopWords))
324 symbols = ['.', ',', ':', ';', '?', '!', '\'', '"', '<', '>', '(', ')', '-', '_', '/', '\\', '¿', '¡', '+', '{', 197 symbols = ['.', ',', ':', ';', '?', '!', '\'', '"', '<', '>', '(', ')', '-', '_', '/', '\\', '¿', '¡', '+', '{',
325 '}', '[', ']', '*', '%', '$', '#', '&', '°', '`', '...'] 198 '}', '[', ']', '*', '%', '$', '#', '&', '°', '`', '...']
326 - print("Filtering symbols " + str(symbols) + ': ' + str(options.filterSymbols)) 199 + print("Exclude symbols " + str(symbols) + ': ' + str(options.excludeSymbols))
327 200
328 print('-------------------------------- PROCESSING --------------------------------') 201 print('-------------------------------- PROCESSING --------------------------------')
329 print('Reading corpus...') 202 print('Reading corpus...')
...@@ -332,67 +205,50 @@ if __name__ == "__main__": ...@@ -332,67 +205,50 @@ if __name__ == "__main__":
332 sentencesTrainingData = [] 205 sentencesTrainingData = []
333 sentencesTestData = [] 206 sentencesTestData = []
334 207
335 - # Original: stopwords = [word.decode('utf-8') for word in stopwords.words('english')]
336 stopwords = [word for word in stopwords.words('english')] 208 stopwords = [word for word in stopwords.words('english')]
337 209
338 with open(os.path.join(options.inputPath, options.trainingFile), "r") as iFile: 210 with open(os.path.join(options.inputPath, options.trainingFile), "r") as iFile:
339 - # with open(os.path.join(options.inputPath, options.trainingFile), "r", encoding="utf-8", errors='replace') as iFile:
340 for line in iFile.readlines(): 211 for line in iFile.readlines():
341 listLine = [] 212 listLine = []
342 line = line.strip('\n') 213 line = line.strip('\n')
343 for token in line.split(): 214 for token in line.split():
344 - if options.filterStopWords: 215 + if options.excludeStopWords:
345 listToken = token.split('|') 216 listToken = token.split('|')
346 lemma = listToken[1] 217 lemma = listToken[1]
347 - # Original: if lemma in stopwords.words('english'):
348 - # trainingTesting_Sklearn_crfsuite.py:269:
349 - # UnicodeWarning: Unicode equal comparison failed to
350 - # convert both arguments to Unicode -
351 - # interpreting them as being unequal
352 if lemma in stopwords: 218 if lemma in stopwords:
353 continue 219 continue
354 - if options.filterSymbols: 220 + if options.excludeSymbols:
355 listToken = token.split('|') 221 listToken = token.split('|')
356 lemma = listToken[1] 222 lemma = listToken[1]
357 if lemma in symbols: 223 if lemma in symbols:
358 - # if lemma == ',':
359 - # print "Coma , identificada"
360 continue 224 continue
361 listLine.append(token) 225 listLine.append(token)
362 sentencesTrainingData.append(listLine) 226 sentencesTrainingData.append(listLine)
363 print(" Sentences training data: " + str(len(sentencesTrainingData))) 227 print(" Sentences training data: " + str(len(sentencesTrainingData)))
364 - # print sentencesTrainingData[0]
365 228
366 with open(os.path.join(options.inputPath, options.testFile), "r") as iFile: 229 with open(os.path.join(options.inputPath, options.testFile), "r") as iFile:
367 - # with open(os.path.join(options.inputPath, options.testFile), "r", encoding="utf-8", errors='replace') as iFile:
368 for line in iFile.readlines(): 230 for line in iFile.readlines():
369 listLine = [] 231 listLine = []
370 line = line.strip('\n') 232 line = line.strip('\n')
371 for token in line.split(): 233 for token in line.split():
372 - if options.filterStopWords: 234 + if options.excludeStopWords:
373 listToken = token.split('|') 235 listToken = token.split('|')
374 lemma = listToken[1] 236 lemma = listToken[1]
375 - # Original if lemma in stopwords.words('english'):
376 if lemma in stopwords: 237 if lemma in stopwords:
377 continue 238 continue
378 - if options.filterSymbols: 239 + if options.excludeSymbols:
379 listToken = token.split('|') 240 listToken = token.split('|')
380 lemma = listToken[1] 241 lemma = listToken[1]
381 if lemma in symbols: 242 if lemma in symbols:
382 - # if lemma == ',':
383 - # print "Coma , identificada"
384 continue 243 continue
385 listLine.append(token) 244 listLine.append(token)
386 sentencesTestData.append(listLine) 245 sentencesTestData.append(listLine)
387 print(" Sentences test data: " + str(len(sentencesTestData))) 246 print(" Sentences test data: " + str(len(sentencesTestData)))
388 - # print sentencesTestData[0]
389 247
390 print("Reading corpus done in: %fs" % (time() - t0)) 248 print("Reading corpus done in: %fs" % (time() - t0))
391 249
392 print(sent2features(sentencesTrainingData[0])[0]) 250 print(sent2features(sentencesTrainingData[0])[0])
393 print(sent2features(sentencesTestData[0])[0]) 251 print(sent2features(sentencesTestData[0])[0])
394 - # print(sent2labels(sentencesTrainingData[0]))
395 - # print(sent2labels(sentencesTestData[0]))
396 t0 = time() 252 t0 = time()
397 253
398 X_train = [sent2features(s) for s in sentencesTrainingData] 254 X_train = [sent2features(s) for s in sentencesTrainingData]
...@@ -445,8 +301,8 @@ if __name__ == "__main__": ...@@ -445,8 +301,8 @@ if __name__ == "__main__":
445 301
446 # Best hiperparameters 302 # Best hiperparameters
447 # crf = rs.best_estimator_ 303 # crf = rs.best_estimator_
448 - nameReport = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.filterStopWords) + '.fSymbols_' + str( 304 + nameReport = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.excludeStopWords) + '.fSymbols_' + str(
449 - options.filterSymbols) + '.txt') 305 + options.excludeSymbols) + '.txt')
450 with open(os.path.join(options.outputPath, "reports", "report_" + nameReport), mode="w") as oFile: 306 with open(os.path.join(options.outputPath, "reports", "report_" + nameReport), mode="w") as oFile:
451 oFile.write("********** TRAINING AND TESTING REPORT **********\n") 307 oFile.write("********** TRAINING AND TESTING REPORT **********\n")
452 oFile.write("Training file: " + options.trainingFile + '\n') 308 oFile.write("Training file: " + options.trainingFile + '\n')
...@@ -464,23 +320,23 @@ if __name__ == "__main__": ...@@ -464,23 +320,23 @@ if __name__ == "__main__":
464 # Saving model 320 # Saving model
465 print(" Saving training model...") 321 print(" Saving training model...")
466 t1 = time() 322 t1 = time()
467 - nameModel = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.filterStopWords) + '.fSymbols_' + str( 323 + nameModel = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.excludeStopWords) + '.fSymbols_' + str(
468 - options.filterSymbols) + '.mod') 324 + options.excludeSymbols) + '.mod')
469 joblib.dump(crf, os.path.join(options.outputPath, "models", nameModel)) 325 joblib.dump(crf, os.path.join(options.outputPath, "models", nameModel))
470 print(" Saving training model done in: %fs" % (time() - t1)) 326 print(" Saving training model done in: %fs" % (time() - t1))
471 327
472 # Evaluation against test data 328 # Evaluation against test data
473 y_pred = crf.predict(X_test) 329 y_pred = crf.predict(X_test)
474 print("*********************************") 330 print("*********************************")
475 - name = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.filterStopWords) + '.fSymbols_' + str( 331 + name = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.excludeStopWords) + '.fSymbols_' + str(
476 - options.filterSymbols) + '.txt') 332 + options.excludeSymbols) + '.txt')
477 with open(os.path.join(options.outputPath, "reports", "y_pred_" + name), "w") as oFile: 333 with open(os.path.join(options.outputPath, "reports", "y_pred_" + name), "w") as oFile:
478 for y in y_pred: 334 for y in y_pred:
479 oFile.write(str(y) + '\n') 335 oFile.write(str(y) + '\n')
480 336
481 print("*********************************") 337 print("*********************************")
482 - name = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.filterStopWords) + '.fSymbols_' + str( 338 + name = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.excludeStopWords) + '.fSymbols_' + str(
483 - options.filterSymbols) + '.txt') 339 + options.excludeSymbols) + '.txt')
484 with open(os.path.join(options.outputPath, "reports", "y_test_" + name), "w") as oFile: 340 with open(os.path.join(options.outputPath, "reports", "y_test_" + name), "w") as oFile:
485 for y in y_test: 341 for y in y_test:
486 oFile.write(str(y) + '\n') 342 oFile.write(str(y) + '\n')
......