-
Notifications
You must be signed in to change notification settings - Fork 0
/
model_prediccio_futur_Nvars.py
166 lines (143 loc) · 4.19 KB
/
model_prediccio_futur_Nvars.py
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
import pandas
from pandas.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
import numpy as np
import random
seed = 123456
Ncross = 100
data = pandas.read_excel(open('./data/results_new.xlsx','rb'), sheet_name=0);
result = pandas.read_excel(open('./data/results_new.xlsx','rb'), sheet_name=1);
f = open('./data/errors_Nvar_model21.txt','w');
X0 = data.values
Y0 = result.values
Nin = 8
Nout = 1
N = 1000
Ncross = 1
Nfit = 8000
X = np.zeros([N*Nin,12])
Y = np.zeros(N*Nin)
k = 0
for ii in range(Nin):
for jj in range(N):
X[k,0:11] = X0[jj,:]
X[k,11] = Y0[jj,ii]
Y[k] = Y0[jj,ii+1]
k = k + 1
X_v0 = np.zeros([Nout*N,12])
Y_v0 = np.zeros(Nout*N)
for jj in range(N):
X_v0[jj,0:11] = X0[jj,:]
X_v0[jj,11] = Y0[jj,8]
Y_v0[jj] = Y0[jj,9]
ordreDTC = [11, 5, 10, 0, 1, 4, 7, 3, 6, 2, 9, 8]
ordreRFC = [11, 6, 3, 2, 9, 4, 1, 5, 7, 10, 0, 8]
errorSVM = np.zeros([12,2])
errorLR = np.zeros([12,2])
errorLDA = np.zeros([12,2])
errorKNC = np.zeros([12,2])
errorDTC = np.zeros([12,2])
errorGNB = np.zeros([12,2])
errorRF = np.zeros([12,2])
for ss in range(Ncross):
for var in range(12):
for order in range(2):
print ss, var, order
if order == 0:
classificacio = ordreDTC
else:
classificacio = ordreRFC
X_t = X[:,classificacio[0:var+1]]
Y_t = Y
X_v = X_v0[:,classificacio[0:var+1]]
Y_v = Y_v0
# Suport Vector Machine
clf = SVC()
clf.fit(X_t,Y_t)
Y_p = clf.predict(X_v)
for i in range(0,N):
errorSVM[var,order] = errorSVM[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Logistic Regression
logreg = LogisticRegression()
logreg.fit(X_t, Y_t)
Y_p = logreg.predict(X_v)
for i in range(0,N):
errorLR[var,order] = errorLR[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Linear Discriminant Analysis
lda = LinearDiscriminantAnalysis()
lda.fit(X_t, Y_t)
Y_p = lda.predict(X_v)
for i in range(0,N):
errorLDA[var,order] = errorLDA[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# K Neighbors Classifier
KNC = KNeighborsClassifier()
KNC.fit(X_t, Y_t)
Y_p = KNC.predict(X_v)
for i in range(0,N):
errorKNC[var,order] = errorKNC[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Decision Tree Classifier
DTC = DecisionTreeClassifier()
DTC.fit(X_t, Y_t)
Y_p = DTC.predict(X_v)
for i in range(0,N):
errorDTC[var,order] = errorDTC[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Gaussian Naive Bayes
GNB = GaussianNB()
GNB.fit(X_t, Y_t)
Y_p = GNB.predict(X_v)
for i in range(0,N):
errorGNB[var,order] = errorGNB[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
# Random Forest
RFC = RandomForestClassifier()
RFC.fit(X_t, Y_t)
Y_p = RFC.predict(X_v)
for i in range(0,N):
errorRF[var,order] = errorRF[var,order]+abs(float(Y_v[i]-Y_p[i]))/Y_v[i]
errorSVM = errorSVM/N/Ncross
errorLR = errorLR/N/Ncross
errorLDA = errorLDA/N/Ncross
errorKNC = errorKNC/N/Ncross
errorDTC = errorDTC/N/Ncross
errorGNB = errorGNB/N/Ncross
errorRF = errorRF/N/Ncross
print 'SVM error = ', errorSVM
print 'LR error = ', errorLR
print 'LDA error = ', errorLDA
print 'KNC error = ', errorKNC
print 'DTC error = ', errorDTC
print 'GNB error = ', errorGNB
print 'RF error = ', errorRF
for ii in range(2):
for err in errorSVM[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
for err in errorLR[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
for err in errorLDA[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
for err in errorKNC[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
for err in errorDTC[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
for err in errorGNB[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
for err in errorRF[:,ii]:
f.write('%.4f ' % err)
f.write('\n')
f.close()