def get_classifier(self, traindata, kf):
x_tr, x_te, y_tr, y_te = fac.to_kfold(traindata, kf)
acc_max, bestK, acc = 0, 0, [[] for a in range(kf)]
for i in range(kf):
# print('DOAO round', i, 'begin')
# svm 00
print('test00')
clf_svm = SVC()
clf_svm.fit(x_tr[i], y_tr[i].ravel())
label_svm = clf_svm.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_svm)[0])
# KNN 01
print('test01')
acc_k = []
aux_k = [3, 5, 7]
# for k in range(3, 12, 2):
for k in aux_k:
clf_knn = KNN_GPU(k=k)
clf_knn.fit(x_tr[i], y_tr[i])
label_knn = clf_knn.predict(x_te[i])
acc_k.append(fac.get_acc(y_te[i], label_knn)[0])
acc[i].append(max(acc_k))
bestK = aux_k[acc_k.index(max(acc_k))]
# LR 02
print('test02')
clf_lr = LogisticRegression()
clf_lr.fit(x_tr[i], y_tr[i])
label_LR = clf_lr.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_LR)[0])
# XgBoost 03
print('test03')
clf_xgb = DecisionTreeClassifier()
clf_xgb.fit(x_tr[i], y_tr[i])
label_xgb = clf_xgb.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_xgb)[0])
# RF 04
print('test04')
clf_rf = TGBMClassifier()
clf_rf.fit(x_tr[i], y_tr[i])
label_rf = clf_rf.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_rf)[0])
print('DOAO round', i, 'end')
acc = np.array(acc)
acc_mean = acc.mean(axis=0)
# fun_best = np.where(acc_mean == max(acc_mean))
fun_best = np.argmax(acc_mean)
return fun_best, bestK
def get_classifier(self, train, kf):
x_tr, x_te, y_tr, y_te = fac.to_kfold(train, kf)
acc_max, bestK, acc = 0, 0, [[] for a in range(kf)]
for i in range(kf):
# print('DECOC round', i, 'begin')
# svm 00
clf_svm = SVC()
clf_svm.fit(x_tr[i], y_tr[i].ravel())
label_svm = clf_svm.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_svm)[0])
# KNN 01
acc_k = []
aux_k = [3, 5, 7]
# for k in range(3, 12, 2):
for k in aux_k:
clf_knn = KNN_GPU(k=k)
clf_knn.fit(x_tr[i], y_tr[i])
label_knn = clf_knn.predict(x_te[i])
acc_k.append(fac.get_acc(y_te[i], label_knn)[0])
acc[i].append(max(acc_k))
bestK = aux_k[acc_k.index(max(acc_k))]
# # LR 02
# clf_lr = LR_GPU()
# clf_lr.fit(x_tr[i], y_tr[i])
# label_LR = clf_lr.predicted(x_te[i])
# acc[i].append(fac.get_acc(y_te[i], label_LR)[0])
# LR 02
clf_lr = LogisticRegression()
clf_lr.fit(x_tr[i], y_tr[i])
label_LR = clf_lr.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_LR)[0])
# CART 03
clf_cart = DecisionTreeClassifier()
clf_cart.fit(x_tr[i], y_tr[i])
label_cart = clf_cart.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_cart)[0])
# # RF 04
clf_rf = TGBMClassifier()
clf_rf.fit(x_tr[i], y_tr[i].ravel())
label_rf = clf_rf.predict(x_te[i])
acc[i].append(fac.get_acc(y_te[i], label_rf)[0])
print('DECOC round', i, 'end')
acc = np.array(acc)
acc_mean = acc.mean(axis=0)
# fun_best = np.where(acc_mean == max(acc_mean))
fun_best = np.argmax(acc_mean)
return fun_best, bestK
def fun_predict(self, x_te, C, D, L):
print('func_predict')
num = len(D)
cf = C[0]
ck = C[1]
allpre = np.zeros((len(x_te), num))
for i in range(num):
train = D[i]
traindata = train[:, 0:-1]
trainlabel = train[:, -1]
if cf[i] == 0:
# svm
print('SVM predict')
clf_svm = SVC()
clf_svm.fit(traindata, trainlabel.ravel())
label_svm = clf_svm.predict(x_te)
allpre[:, i] = label_svm
elif cf[i] == 1:
# knn
clf_knn = KNN_GPU(k=ck[i])
clf_knn.fit(traindata, trainlabel)
label_knn = clf_knn.predict(x_te)
allpre[:, i] = label_knn
elif cf[i] == 2:
# LR
print('LR predict')
clf_lr = LogisticRegression()
clf_lr.fit(traindata, trainlabel.ravel())
label_LR = clf_lr.predict(x_te)
allpre[:, i] = label_LR
elif cf[i] == 3:
# CART
print('CART predict')
clf_xgb = DecisionTreeClassifier()
clf_xgb.fit(traindata, trainlabel)
label_xgb = clf_xgb.predict(x_te)
allpre[:, i] = label_xgb
elif cf[i] == 4:
# Rf
print('RF predict')
clf_rf = TGBMClassifier()
clf_rf.fit(traindata, trainlabel.ravel())
label_rf = clf_rf.predict(x_te)
allpre[:, i] = label_rf
else:
print('error !!!! DOAO.fun_predict')
label = L[i]
for j in range(len(x_te)):
allpre[j, i] = label[0] if allpre[j, i] == 0 else label[1]
# print('predict end for')
pre = mode(allpre, axis=1)[0]
return pre
def funcPreEDOVO(self, x_test, y_test, C, D):
numC = np.asarray(C).shape[0]
num_set = len(y_test)
allpre = np.zeros([num_set, numC])
for i in range(numC):
train = D[i]
traindata = np.array(train[:, 0:-1])
trainlabel = np.array(train[:, -1], dtype='int64')
if C[i, 0] == 0:
print('test0')
# svm
clf_svm = SVC()
clf_svm.fit(traindata, trainlabel.ravel())
label_svm = clf_svm.predict(x_test)
allpre[:, i] = label_svm
elif C[i, 0] == 1:
# print('test1')
# knn
clf_knn = KNN_GPU(k=C[i][1])
# clf_knn = KNN_torch(k=C[i][1])
clf_knn.fit(traindata, trainlabel)
label_knn = clf_knn.predict(x_test)
allpre[:, i] = label_knn.ravel()
elif C[i, 0] == 2:
print('test2')
# LR
clf_lr = LogisticRegression()
clf_lr.fit(traindata, trainlabel)
label_LR = clf_lr.predict(x_test)
allpre[:, i] = label_LR
# # LR
# clf_lr = LR_GPU()
# clf_lr.fit(traindata, trainlabel)
# label_LR = clf_lr.predicted(x_test)
# allpre[:, i] = label_LR
elif C[i, 0] == 3:
print('test3')
# CART
clf_cart = DecisionTreeClassifier()
clf_cart.fit(traindata, trainlabel)
label_cart = clf_cart.predict(x_test)
allpre[:, i] = label_cart
elif C[i, 0] == 4:
print('test4')
# RandomForest
clf_ada = TGBMClassifier()
clf_ada.fit(traindata, trainlabel.ravel())
label_ada = clf_ada.predict(x_test)
allpre[:, i] = label_ada
else:
print('error !!!! DECOC.funcPreEDOVO')
return allpre