training-crossvalidation-testing-binding-thrombin.py
12.8 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
# -*- encoding: utf-8 -*-
import os
from time import time
import argparse
from sklearn.naive_bayes import BernoulliNB
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, \
classification_report
from sklearn.externals import joblib
from sklearn import model_selection
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.decomposition import TruncatedSVD
from scipy.sparse import csr_matrix
import scipy
__author__ = 'CMendezC'
# Goal: training, crossvalidation and testing binding thrombin data set
# Parameters:
# 1) --inputPath Path to read input files.
# 2) --inputTrainingData File to read training data.
# 3) --inputTestingData File to read testing data.
# 4) --inputTestingClasses File to read testing classes.
# 5) --outputModelPath Path to place output model.
# 6) --outputModelFile File to place output model.
# 7) --outputReportPath Path to place evaluation report.
# 8) --outputReportFile File to place evaluation report.
# 9) --classifier Classifier: BernoulliNB, SVM, kNN.
# 10) --saveData Save matrices
# 11) --kernel Kernel
# 12) --reduction Feature selection or dimensionality reduction
# Ouput:
# 1) Classification model and evaluation report.
# Execution:
# python training-crossvalidation-testing-binding-thrombin.py
# --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset
# --inputTrainingData thrombin.data
# --inputTestingData Thrombin.testset
# --inputTestingClasses Thrombin.testset.class
# --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/models
# --outputModelFile SVM-model.mod
# --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/reports
# --outputReportFile SVM.txt
# --classifier SVM
# --saveData
# --kernel linear
# --reduction SVD200
# source activate python3
# python training-crossvalidation-testing-binding-thrombin.py --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset --inputTrainingData thrombin.data --inputTestingData Thrombin.testset --inputTestingClasses Thrombin.testset.class --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/models --outputModelFile SVM-linear-model.mod --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/reports --outputReportFile SVM-linear.txt --classifier SVM --kernel rbf
###########################################################
# MAIN PROGRAM #
###########################################################
if __name__ == "__main__":
# Parameter definition
parser = argparse.ArgumentParser(description='Training validation Binding Thrombin Dataset.')
parser.add_argument("--inputPath", dest="inputPath",
help="Path to read input files", metavar="PATH")
parser.add_argument("--inputTrainingData", dest="inputTrainingData",
help="File to read training data", metavar="FILE")
parser.add_argument("--inputTestingData", dest="inputTestingData",
help="File to read testing data", metavar="FILE")
parser.add_argument("--inputTestingClasses", dest="inputTestingClasses",
help="File to read testing classes", metavar="FILE")
parser.add_argument("--outputModelPath", dest="outputModelPath",
help="Path to place output model", metavar="PATH")
parser.add_argument("--outputModelFile", dest="outputModelFile",
help="File to place output model", metavar="FILE")
parser.add_argument("--outputReportPath", dest="outputReportPath",
help="Path to place evaluation report", metavar="PATH")
parser.add_argument("--outputReportFile", dest="outputReportFile",
help="File to place evaluation report", metavar="FILE")
parser.add_argument("--classifier", dest="classifier",
help="Classifier", metavar="NAME",
choices=('BernoulliNB', 'SVM', 'kNN'), default='SVM')
parser.add_argument("--saveData", dest="saveData", action='store_true',
help="Save matrices")
parser.add_argument("--kernel", dest="kernel",
help="Kernel SVM", metavar="NAME",
choices=('linear', 'rbf', 'poly'), default='linear')
parser.add_argument("--reduction", dest="reduction",
help="Feature selection or dimensionality reduction", metavar="NAME",
choices=('SVD200', 'SVD300', 'CHI250', 'CHI2100'), default=None)
args = parser.parse_args()
# Printing parameter values
print('-------------------------------- PARAMETERS --------------------------------')
print("Path to read input files: " + str(args.inputPath))
print("File to read training data: " + str(args.inputTrainingData))
print("File to read testing data: " + str(args.inputTestingData))
print("File to read testing classes: " + str(args.inputTestingClasses))
print("Path to place output model: " + str(args.outputModelPath))
print("File to place output model: " + str(args.outputModelFile))
print("Path to place evaluation report: " + str(args.outputReportPath))
print("File to place evaluation report: " + str(args.outputReportFile))
print("Classifier: " + str(args.classifier))
print("Save matrices: " + str(args.saveData))
print("Kernel: " + str(args.kernel))
print("Reduction: " + str(args.reduction))
# Start time
t0 = time()
print("Reading training data and true classes...")
X_train = None
if args.saveData:
y_train = []
trainingData = []
with open(os.path.join(args.inputPath, args.inputTrainingData), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
listLine = line.split(',')
y_train.append(listLine[0])
trainingData.append(listLine[1:])
# X_train = np.matrix(trainingData)
X_train = csr_matrix(trainingData, dtype='double')
print(" Saving matrix and classes...")
joblib.dump(X_train, os.path.join(args.outputModelPath, args.inputTrainingData + '.jlb'))
joblib.dump(y_train, os.path.join(args.outputModelPath, args.inputTrainingData + '.class.jlb'))
print(" Done!")
else:
print(" Loading matrix and classes...")
X_train = joblib.load(os.path.join(args.outputModelPath, args.inputTrainingData + '.jlb'))
y_train = joblib.load(os.path.join(args.outputModelPath, args.inputTrainingData + '.class.jlb'))
print(" Done!")
print(" Number of training classes: {}".format(len(y_train)))
print(" Number of training class A: {}".format(y_train.count('A')))
print(" Number of training class I: {}".format(y_train.count('I')))
print(" Shape of training matrix: {}".format(X_train.shape))
print("Reading testing data and true classes...")
X_test = None
if args.saveData:
y_test = []
testingData = []
with open(os.path.join(args.inputPath, args.inputTestingData), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
listLine = line.split(',')
testingData.append(listLine[1:])
X_test = csr_matrix(testingData, dtype='double')
with open(os.path.join(args.inputPath, args.inputTestingClasses), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
y_test.append(line)
print(" Saving matrix and classes...")
joblib.dump(X_test, os.path.join(args.outputModelPath, args.inputTestingData + '.jlb'))
joblib.dump(y_test, os.path.join(args.outputModelPath, args.inputTestingClasses + '.class.jlb'))
print(" Done!")
else:
print(" Loading matrix and classes...")
X_test = joblib.load(os.path.join(args.outputModelPath, args.inputTestingData + '.jlb'))
y_test = joblib.load(os.path.join(args.outputModelPath, args.inputTestingClasses + '.class.jlb'))
print(" Done!")
print(" Number of testing classes: {}".format(len(y_test)))
print(" Number of testing class A: {}".format(y_test.count('A')))
print(" Number of testing class I: {}".format(y_test.count('I')))
print(" Shape of testing matrix: {}".format(X_test.shape))
# Feature selection and dimensional reduction
if args.reduction is not None:
print('Performing dimensionality reduction or feature selection...', args.reduction)
if args.reduction == 'SVD200':
reduc = TruncatedSVD(n_components=200, random_state=42)
X_train = reduc.fit_transform(X_train)
if args.reduction == 'SVD300':
reduc = TruncatedSVD(n_components=300, random_state=42)
X_train = reduc.fit_transform(X_train)
elif args.reduction == 'CHI250':
reduc = SelectKBest(chi2, k=50)
X_train = reduc.fit_transform(X_train, y_train)
elif args.reduction == 'CHI2100':
reduc = SelectKBest(chi2, k=100)
X_train = reduc.fit_transform(X_train, y_train)
print(" Done!")
print(' New shape of training matrix: ', X_train.shape)
jobs = -1
paramGrid = []
nIter = 20
crossV = 10
print("Defining randomized grid search...")
if args.classifier == 'SVM':
# SVM
classifier = SVC()
if args.kernel == 'rbf':
paramGrid = {'C': scipy.stats.expon(scale=100),
'gamma': scipy.stats.expon(scale=.1),
'kernel': ['rbf'], 'class_weight': ['balanced', None]}
elif args.kernel == 'linear':
paramGrid = {'C': scipy.stats.expon(scale=100),
'kernel': ['linear'],
'class_weight': ['balanced', None]}
elif args.kernel == 'poly':
paramGrid = {'C': scipy.stats.expon(scale=100),
'gamma': scipy.stats.expon(scale=.1), 'degree': [2, 3],
'kernel': ['poly'], 'class_weight': ['balanced', None]}
myClassifier = model_selection.RandomizedSearchCV(classifier,
paramGrid, n_iter=nIter,
cv=crossV, n_jobs=jobs, verbose=3)
elif args.classifier == 'BernoulliNB':
# BernoulliNB
classifier = BernoulliNB()
paramGrid = {'alpha': scipy.stats.expon(scale=1.0)}
myClassifier = model_selection.RandomizedSearchCV(classifier, paramGrid, n_iter=nIter,
cv=crossV, n_jobs=jobs, verbose=3)
# elif args.classifier == 'kNN':
# # kNN
# k_range = list(range(1, 7, 2))
# classifier = KNeighborsClassifier()
# paramGrid = {'n_neighbors ': k_range}
# myClassifier = model_selection.RandomizedSearchCV(classifier, paramGrid, n_iter=3,
# cv=crossV, n_jobs=jobs, verbose=3)
else:
print("Bad classifier")
exit()
print(" Done!")
print("Training...")
myClassifier.fit(X_train, y_train)
print(" Done!")
print("Testing (prediction in new data)...")
if args.reduction is not None:
X_test = reduc.transform(X_test)
y_pred = myClassifier.predict(X_test)
best_parameters = myClassifier.best_estimator_.get_params()
print(" Done!")
print("Saving report...")
with open(os.path.join(args.outputReportPath, args.outputReportFile), mode='w', encoding='utf8') as oFile:
oFile.write('********** EVALUATION REPORT **********\n')
oFile.write('Reduction: {}\n'.format(args.reduction))
oFile.write('Classifier: {}\n'.format(args.classifier))
oFile.write('Kernel: {}\n'.format(args.kernel))
oFile.write('Accuracy: {}\n'.format(accuracy_score(y_test, y_pred)))
oFile.write('Precision: {}\n'.format(precision_score(y_test, y_pred, average='weighted')))
oFile.write('Recall: {}\n'.format(recall_score(y_test, y_pred, average='weighted')))
oFile.write('F-score: {}\n'.format(f1_score(y_test, y_pred, average='weighted')))
oFile.write('Confusion matrix: \n')
oFile.write(str(confusion_matrix(y_test, y_pred)) + '\n')
oFile.write('Classification report: \n')
oFile.write(classification_report(y_test, y_pred) + '\n')
oFile.write('Best parameters: \n')
for param in sorted(best_parameters.keys()):
oFile.write("\t%s: %r\n" % (param, best_parameters[param]))
print(" Done!")
print("Training and testing done in: %fs" % (time() - t0))