Tri-training/Tri-training.py at master · LiangjunFeng/Tri-training · 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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
import numpy as np
import sklearn
import scipy.io as scio
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

class TriTraining:
    def __init__(self, classifier):
        if sklearn.base.is_classifier(classifier):
            self.classifiers = [sklearn.base.clone(classifier) for i in range(3)]
        else:
            self.classifiers = [sklearn.base.clone(classifier[i]) for i in range(3)]

    def fit(self, L_X, L_y, U_X):
        for i in range(3):
            sample = sklearn.utils.resample(L_X, L_y)
            self.classifiers[i].fit(*sample)
        e_prime = [0.5]*3
        l_prime = [0]*3
        e = [0]*3
        update = [False]*3
        Li_X, Li_y = [[]]*3, [[]]*3#to save proxy labeled data
        improve = True
        self.iter = 0

        while improve:
            self.iter += 1#count iterations

            for i in range(3):
                j, k = np.delete(np.array([0,1,2]),i)
                update[i] = False
                e[i] = self.measure_error(L_X, L_y, j, k)
                if e[i] < e_prime[i]:
                    U_y_j = self.classifiers[j].predict(U_X)
                    U_y_k = self.classifiers[k].predict(U_X)
                    Li_X[i] = U_X[U_y_j == U_y_k]#when two models agree on the label, save it
                    Li_y[i] = U_y_j[U_y_j == U_y_k]
                    if l_prime[i] == 0:#no updated before
                        l_prime[i]  = int(e[i]/(e_prime[i] - e[i]) + 1)
                    if l_prime[i] < len(Li_y[i]):
                        if e[i]*len(Li_y[i])<e_prime[i] * l_prime[i]:
                            update[i] = True
                        elif l_prime[i] > e[i]/(e_prime[i] - e[i]):
                            L_index = np.random.choice(len(Li_y[i]), int(e_prime[i] * l_prime[i]/e[i] -1))
                            Li_X[i], Li_y[i] = Li_X[i][L_index], Li_y[i][L_index]
                            update[i] = True

            for i in range(3):
                if update[i]:
                    self.classifiers[i].fit(np.append(L_X,Li_X[i],axis=0), np.append(L_y, Li_y[i], axis=0))
                    e_prime[i] = e[i]
                    l_prime[i] = len(Li_y[i])

            if update == [False]*3:
                improve = False#if no classifier was updated, no improvement


    def predict(self, X):
        pred = np.asarray([self.classifiers[i].predict(X) for i in range(3)])
        pred[0][pred[1]==pred[2]] = pred[1][pred[1]==pred[2]]
        return pred[0]

    def score(self, X, y):
        return sklearn.metrics.accuracy_score(y, self.predict(X))

    def measure_error(self, X, y, j, k):
        j_pred = self.classifiers[j].predict(X)
        k_pred = self.classifiers[k].predict(X)
        wrong_index =np.logical_and(j_pred != y, k_pred==j_pred)
        #wrong_index =np.logical_and(j_pred != y_test, k_pred!=y_test)
        return sum(wrong_index)/sum(j_pred == k_pred)


dataFile = './norb.mat'
data = scio.loadmat(dataFile)

traindata  = np.double(data['train_x']/255)
trainlabel = np.double(data['train_y'])
testdata   = np.double(data['test_x']/255)
testlabel  = np.double(data['test_y'])

data = np.row_stack([traindata,testdata])
label = np.row_stack([trainlabel,testlabel]).argmax(axis=1)

train_index = np.random.choice(data.shape[0],8600,replace=False)
rest_index = list(set(np.arange(data.shape[0])) - set(train_index))
test_index = np.random.choice(rest_index,10000,replace=False)
u_index = list(set(rest_index) - set(test_index))

traindata = data[train_index]
trainlabel = label[train_index]

testdata = data[test_index]
testlabel = label[test_index]

udata = data[u_index]

print(traindata.shape,testdata.shape,udata.shape)
print(trainlabel.shape,testlabel.shape)

clf = RandomForestClassifier()
clf.fit(traindata,trainlabel)
res1 = clf.predict(testdata)
print(accuracy_score(res1,testlabel))


TT = TriTraining([RandomForestClassifier(),RandomForestClassifier(),RandomForestClassifier()])
TT.fit(traindata,trainlabel,udata)
res2 = TT.predict(testdata)
print(accuracy_score(res2,testlabel))