trainingEvaluation_Iris_v1.py
7.36 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
# -*- encoding: utf-8 -*-
import os
from time import time
from optparse import OptionParser
from sklearn.naive_bayes import MultinomialNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, \
classification_report
import sys
__author__ = 'CMendezC'
# Goal: training and test Iris dataset
# Parameters:
# 1) --inputPath Path to read input files.
# 2) --inputTrainingData File to read training data.
# 3) --inputTrainingClasses File to read training true classes.
# 4) --inputTestData File to read test data.
# 5) --inputTestClasses File to read test true classes.
# 6) --outputPath Path to place output files.
# 7) --outputFile File to place evaluation report.
# 8) --classifier Classifier: MultinomialNB, SVM, RandomForest.
# Ouput:
# 1) Evaluation report.
# Execution:
# C:\Anaconda3\python trainingTest_Iris_v2.py
# --inputPath C:\Users\cmendezc\Documents\GENOMICAS\LICENCIATURA_LCGPDCB\dataSet_Iris
# --inputTrainingData training_Data.txt
# --inputTrainingClasses training_TrueClasses.txt
# --inputTestData test_Data.txt
# --inputTestClasses test_TrueClasses.txt
# --outputPath C:\Users\cmendezc\Documents\GENOMICAS\LICENCIATURA_LCGPDCB\dataSet_Iris
# --outputFile report_MultinomialNB.txt
# --classifier MultinomialNB
# C:\Anaconda3\python trainingTest_Iris_v2.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\LICENCIATURA_LCGPDCB\dataSet_Iris --inputTrainingData training_Data.txt --inputTrainingClasses training_TrueClasses.txt --inputTestData test_Data.txt --inputTestClasses test_TrueClasses.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\LICENCIATURA_LCGPDCB\dataSet_Iris --outputFile report_MultinomialNB.txt --classifier MultinomialNB
###########################################################
# MAIN PROGRAM #
###########################################################
if __name__ == "__main__":
# Parameter definition
parser = OptionParser()
parser.add_option("--inputPath", dest="inputPath",
help="Path to read input files", metavar="PATH")
parser.add_option("--inputTrainingData", dest="inputTrainingData",
help="File to read training data", metavar="FILE")
parser.add_option("--inputTrainingClasses", dest="inputTrainingClasses",
help="File to read training true classes", metavar="FILE")
parser.add_option("--inputTestData", dest="inputTestData",
help="File to read test data", metavar="FILE")
parser.add_option("--inputTestClasses", dest="inputTestClasses",
help="File to read test true classes", metavar="FILE")
parser.add_option("--outputPath", dest="outputPath",
help="Path to place output files", metavar="PATH")
parser.add_option("--outputFile", dest="outputFile",
help="File to write evaluation report", metavar="FILE")
parser.add_option("--classifier", dest="classifier",
help="Classifier", metavar="CLASSIFIER")
(options, args) = parser.parse_args()
if len(args) <= 0:
parser.error("None parameters indicated.")
sys.exit(1)
# Printing parameter values
print('-------------------------------- PARAMETERS --------------------------------')
print("Path to read input files: " + str(options.inputPath))
print("File to read training data: " + str(options.inputTrainingData))
print("File to read training true classes: " + str(options.inputTrainingClasses))
print("File to read test data: " + str(options.inputTestData))
print("File to read test true classes: " + str(options.inputTestClasses))
print("Path to place output files: " + str(options.outputPath))
print("File to write evaluation report: " + str(options.outputFile))
print("Classifier: " + str(options.outputFile))
# Start time
t0 = time()
print(" Reading training and test data and true classes...")
trueTrainingClasses = []
trueTestClasses = []
with open(os.path.join(options.inputPath, options.inputTrainingClasses), encoding='utf8', mode='r') \
as classFile:
for line in classFile:
line = line.strip('\r\n')
trueTrainingClasses.append(line)
with open(os.path.join(options.inputPath, options.inputTestClasses), encoding='utf8', mode='r') \
as classFile:
for line in classFile:
line = line.strip('\r\n')
trueTestClasses.append(line)
# print(trueTestClasses)
dataTraining = []
dataTest = []
with open(os.path.join(options.inputPath, options.inputTrainingData), encoding='utf8', mode='r') \
as dataFile:
for line in dataFile:
listTemp = []
listFloat = []
line = line.strip('\r\n')
listTemp = line.split('\t')
for elem in listTemp:
listFloat.append(float(elem))
dataTraining.append(listFloat)
print(dataTraining)
with open(os.path.join(options.inputPath, options.inputTestData), encoding='utf8', mode='r') \
as dataFile:
for line in dataFile:
listTemp = []
listFloat = []
line = line.strip('\r\n')
listTemp = line.split('\t')
for elem in listTemp:
listFloat.append(float(elem))
dataTest.append(listFloat)
print(dataTest)
print(" Reading data and true classes done!")
if options.classifier == "MultinomialNB":
classifier = MultinomialNB()
elif options.classifier == "SVM":
pass
elif options.classifier == "RandomForest":
classifier = RandomForestClassifier()
print(" Training...")
classifier.fit(dataTraining, trueTrainingClasses)
print(" Prediction...")
y_pred = classifier.predict(dataTest)
print(" Training and predition done!")
# for i in range(len(trueClasses)):
# print(str(trueClasses[i]) + "\t" + str(y_pred[i]))
print(" Saving test report...")
with open(os.path.join(options.outputPath, options.outputFile), mode='w', encoding='utf8') as oFile:
oFile.write('********** EVALUATION REPORT **********\n')
oFile.write('Classifier: {}\n'.format(options.classifier))
oFile.write('Accuracy: {}\n'.format(accuracy_score(trueTestClasses, y_pred)))
oFile.write('Precision: {}\n'.format(precision_score(trueTestClasses, y_pred, average='weighted')))
oFile.write('Recall: {}\n'.format(recall_score(trueTestClasses, y_pred, average='weighted')))
oFile.write('F-score: {}\n'.format(f1_score(trueTestClasses, y_pred, average='weighted')))
# oFile.write('{}\t{}\t{}\t{}\n'.format(accuracy_score(trueClasses, y_pred),
# precision_score(trueClasses, y_pred, average='weighted'),
# recall_score(trueClasses, y_pred, average='weighted'),
# f1_score(trueClasses, y_pred, average='weighted')))
oFile.write('Confusion matrix: \n')
oFile.write(str(confusion_matrix(trueTestClasses, y_pred)) + '\n')
oFile.write('Classification report: \n')
oFile.write(classification_report(trueTestClasses, y_pred) + '\n')
print(" Saving test report done!")
print("Training and test done in: %fs" % (time() - t0))