training-validation-binding-thrombin.py
7.79 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
# -*- 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 NearestCentroid
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, \
classification_report
import sys
from scipy.sparse import csr_matrix
import numpy as np
__author__ = 'CMendezC'
# Goal: training and validation 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, NearestCentroid.
# Ouput:
# 1) Classification model and evaluation report.
# Execution:
# python training-validation-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
# source activate python3
# python training-validation-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
###########################################################
# 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', 'NearestCentroid'), default='SVM')
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))
# Start time
t0 = time()
print(" Reading training data and true classes...")
trainingClasses = []
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(',')
trainingClasses.append(listLine[0])
trainingData.append(listLine[1:])
# trainingMatrix = np.matrix(trainingData)
trainingMatrix = csr_matrix(trainingData, dtype='double')
print("Number of training classes: {}".format(len(trainingClasses)))
print("Number of training class A: {}".format(trainingClasses.count('A')))
print("Number of training class I: {}".format(trainingClasses.count('I')))
print("Shape of training matrix: {}".format(trainingMatrix.shape))
print(" Reading testing data and true classes...")
testingClasses = []
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:])
testingMatrix = 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')
testingClasses.append(line)
print("Number of testing classes: {}".format(len(testingClasses)))
print("Number of testing class A: {}".format(trainingClasses.count('A')))
print("Number of testing class I: {}".format(trainingClasses.count('I')))
print("Shape of testing matrix: {}".format(testingMatrix.shape))
if args.classifier == "MultinomialNB":
classifier = BernoulliNB()
elif args.classifier == "SVM":
classifier = SVC()
elif args.classifier == "NearestCentroid":
classifier = NearestCentroid()
print(" Training...")
classifier.fit(trainingMatrix, trainingClasses)
print(" Done!")
print(" Testing (prediction in new data)...")
y_pred = classifier.predict(testingMatrix)
print(" Done!")
print(" Saving report...")
with open(os.path.join(args.outputPath, args.outputFile), mode='w', encoding='utf8') as oFile:
oFile.write('********** EVALUATION REPORT **********\n')
oFile.write('Classifier: {}\n'.format(args.classifier))
oFile.write('Accuracy: {}\n'.format(accuracy_score(testingClasses, y_pred)))
oFile.write('Precision: {}\n'.format(precision_score(testingClasses, y_pred, average='weighted')))
oFile.write('Recall: {}\n'.format(recall_score(testingClasses, y_pred, average='weighted')))
oFile.write('F-score: {}\n'.format(f1_score(testingClasses, y_pred, average='weighted')))
oFile.write('Confusion matrix: \n')
oFile.write(str(confusion_matrix(testingClasses, y_pred)) + '\n')
oFile.write('Classification report: \n')
oFile.write(classification_report(testingClasses, y_pred) + '\n')
print(" Done!")
print("Training and testing done in: %fs" % (time() - t0))