normalizer/main.py at master · tinchoa/normalizer · GitHub

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
from histograma import Histograma
from original import Original
#from normalizerOffline import normalizer
from maxMin_Normalizer import maxMin_Normalizer

'''
added by Martin
'''
import time,sys
import numpy as np
from sklearn.metrics import mean_squared_error


####ate aqui

class Main:
	def run(self):
		beg=time.time()

		data = open("classes-17-end.out", "r")
		saida = open("classes-17-norm-histo.out", "w")
		#tamanhoJanela = int(sys.argv[1]) #as paper
		tamanhoJanela=500
		self.hists = []
		hists = self.hists

		linha = data.readline()


		resFinal=[]
		while linha !="":
			janela = []
			while linha !="" and len(janela) < tamanhoJanela:
				tmp1 = linha.strip("\n").split(",")[5:-1]#removing IPsrc,IPdst,portsrc,portdsc,proto,class
				tmp2 = []
				for i in tmp1:
					tmp2.append(float(i))
				janela.append(tmp2)
				linha = data.readline()
			#processa janela
			#print len(janela)

			features = []

			for i in range(len(janela)):
				for j in range(len(janela[i])):
					if (len(features)-1) < j:
						features+=[[]]
					features[j].append(janela[i][j])


			for j in range(len(features)):
				if len(hists) < j+1:
					hists.append(Histograma(features[j]))
				else:
					hists[j].updateHistograma(features[j])
				#    print j, "hist", hists[j].hist, hists[j].pivo
					#print features[j]

	#	end=time.time()-beg
	#	return hists,end

			resultados = []

			for i in range(len(janela)):
				resultados.append([])
				for j in range(len(janela[i])):
					resultados[-1].append(hists[j].getNormalizedValues(janela[i][j])[0])


	 		for k in resultados:
	 			tmp = []
	 			tmp2= []
	 	 		for l in k:
	 	 			tmp.append(str(l))
	 	 			tmp2.append(l)
	 	 		resFinal.append(tmp2)
	 	 		linhaSaida =  ",".join(tmp)
	 	 		saida.write(linhaSaida+"\n")

		end=time.time()-beg

	# 	# saida.write(str('processing time : '+str(end))+'\n')


		##return hists,end #to retunr the object
		return resFinal,end
	# 	#print janela


if __name__ == "__main__":

	#output_file=open(str(sys.argv[1])+'-output','w')
	print 'proposal starting... '+'\n'
	proposal,timeProposal=Main().run()
	print 'proposal finished... '+'\n'

	print 'original started...'+'\n'
	old=Original().run()

	print 'maxMin started....'+'\n'
	maxMin,timeMaxmin=maxMin_Normalizer().run()

	'''
	to calculate the mean square error
	'''
	original_proposal=[]
	original_max=[]
	original=np.asfarray(old)
	proposal=np.asfarray(proposal)
	maxMin=np.asfarray(maxMin)
	for i in range(len(proposal[0])):
	  	original_proposal.append(mean_squared_error(original[:,i],proposal[:,i]))
	  	original_max.append(mean_squared_error(original[:,i],maxMin[:,i]))

	# #MSEproposal=mean_squared_error(original,proposal)
	# #MSEmaxMin=mean_squared_error(original,maxMin)

	MSEproposal=sum(original_proposal)/float(len(original_proposal))
	MSEmaxMin=sum(original_max)/float(len(original_max))

	output_file.write(str(MSEproposal)+','+str(timeProposal)+'\n')
	# #output_file.write('Proposal Procesing time: '+ str(timeProposal)+'\n')
	output_file.write(str(MSEmaxMin)+','+str(timeMaxmin)+'\n')
	# #output_file.write('MaxMin Procesing time: '+ str(timeMaxmin)+'\n')


	output_file.close()