training-evaluation-iris-v1.py
7.58 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
# -*- encoding: utf-8 -*-
import os
from time import time
import argparse
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, \
classification_report
# Author:
# Carlos Méndez-Cruz
# Goal: training and evaluation using Iris dataset
# Arguments:
# 1) --inputPath Path to read input files.
# 2) --inputTrainingData File to read training data.
# 3) --inputTrainingClasses File to read training true classes.
# 4) --inputEvaluationData File to read evaluation data.
# 5) --inputEvaluationClasses File to read evaluation true classes.
# 6) --outputPath Path to place output files.
# 7) --outputFile File to place evaluation report.
# 8) --classifier Classifier: MultinomialNB, SVM, DecisionTree, Perceptron.
# Ouput:
# 1) Evaluation report.
# Execution:
# python training-evaluation-iris-v1.py
# --inputPath /home/clasificacion/iris-dataset
# --inputTrainingData training-data.txt
# --inputTrainingClasses training-classes.txt
# --inputEvaluationData test-data.txt
# --inputEvaluationClasses test-classes.txt
# --outputPath /home/classification/reports
# --outputFile report-iris-svm.txt
# --classifier SVM
# python training-evaluation-iris-v1.py --inputPath /home/laigen-supervised-learning/iris-data-set --inputTrainingData training-data.txt --inputTrainingClasses training-classes.txt --inputEvaluationData test-data.txt --inputEvaluationClasses test-classes.txt --outputPath /home/laigen-supervised-learning/iris-data-set/reports --outputFile report-iris-svm.txt --classifier SVM
###########################################################
# MAIN PROGRAM #
###########################################################
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Training and testing Iris data set.')
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("--inputTrainingClasses", dest="inputTrainingClasses",
help="File to read training true classes", metavar="FILE")
parser.add_argument("--inputEvaluationData", dest="inputEvaluationData",
help="File to read evaluation data", metavar="FILE")
parser.add_argument("--inputEvaluationClasses", dest="inputEvaluationClasses",
help="File to read evaluation true classes", metavar="FILE")
parser.add_argument("--outputPath", dest="outputPath",
help="Path to place output files", metavar="PATH")
parser.add_argument("--outputFile", dest="outputFile",
help="File to write evaluation report", metavar="FILE")
parser.add_argument("--classifier", dest="classifier",
help="Classifier", metavar="CLASSIFIER")
args = parser.parse_args()
# Printing parameter
print('-------------------------------- PARAMETERS --------------------------------')
print("Path to read input files: " + str(args.inputPath))
print("File to read training data: " + str(args.inputTrainingData))
print("File to read training true classes: " + str(args.inputTrainingClasses))
print("File to read evaluation data: " + str(args.inputEvaluationData))
print("File to read evaluation true classes: " + str(args.inputEvaluationClasses))
print("Path to place output files: " + str(args.outputPath))
print("File to write evaluation report: " + str(args.outputFile))
print("Classifier: " + str(args.classifier))
# Start time
t0 = time()
print(" Reading training and evaluation data, and true classes...")
trueTrainingClasses = []
trueEvaluationClasses = []
with open(os.path.join(args.inputPath, args.inputTrainingClasses), encoding='utf8', mode='r') \
as classFile:
for line in classFile:
line = line.strip('\r\n')
trueTrainingClasses.append(line)
with open(os.path.join(args.inputPath, args.inputEvaluationClasses), encoding='utf8', mode='r') \
as classFile:
for line in classFile:
line = line.strip('\r\n')
trueEvaluationClasses.append(line)
# print(trueEvaluationClasses)
dataTraining = []
dataEvaluation = []
with open(os.path.join(args.inputPath, args.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(args.inputPath, args.inputEvaluationData), 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))
dataEvaluation.append(listFloat)
# print(dataEvaluation)
print(" Reading data and true classes done!")
if args.classifier == "MultinomialNB":
classifier = MultinomialNB()
elif args.classifier == "SVM":
classifier = SVC(kernel="linear")
elif args.classifier == "DecisionTree":
classifier = DecisionTreeClassifier()
elif args.classifier == "Perceptron":
classifier = Perceptron()
print(" Training...")
classifier.fit(dataTraining, trueTrainingClasses)
print(" Prediction...")
y_pred = classifier.predict(dataEvaluation)
if args.classifier in ["Perceptron", "SVM"]:
confidence_scores = classifier.decision_function(dataEvaluation)
print(" Training and predition done!")
print(" Saving evaluation 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(trueEvaluationClasses, y_pred)))
oFile.write('Precision: {}\n'.format(precision_score(trueEvaluationClasses, y_pred, average='weighted')))
oFile.write('Recall: {}\n'.format(recall_score(trueEvaluationClasses, y_pred, average='weighted')))
oFile.write('F-score: {}\n'.format(f1_score(trueEvaluationClasses, y_pred, average='weighted')))
oFile.write('Confusion matrix: \n')
oFile.write(str(confusion_matrix(trueEvaluationClasses, y_pred)) + '\n')
oFile.write('Classification report: \n')
oFile.write(classification_report(trueEvaluationClasses, y_pred) + '\n')
if args.classifier in ["Perceptron", "SVM"]:
oFile.write('\nWeights assigned to the features: \n')
oFile.write("{}\n".format(classifier.coef_))
oFile.write('Confidence scores: \n')
oFile.write("{}\n".format(confidence_scores))
if args.classifier == "SVM":
oFile.write('Number of support vectors per class: \n{}\n'.format(classifier.n_support_))
oFile.write('Support vectors: \n{}\n'.format(classifier.support_vectors_))
print(" Saving evaluation report done!")
print("Training and evaluation done in: %fs" % (time() - t0))