le.fit(y)
y = le.transform(y)
#get the train and test data
X_test = X[train_size:, :]
y_test = y[train_size:]
X = X[:train_size, :]
y = y[:train_size]
#use BaggingClassifier with oob_score = True
bc = BaggingClassifier(n_estimators=60, oob_score=True)
bc.fit(X, y)
print("BaggingClassifier:train")
predict_train = bc.predict(X)
print(accuracy_score(y, predict_train))
predict_train = bc._lpz_predict(X, y)
print(accuracy_score(y, predict_train))
#print(bc.oob_score_)
print("BaggingClassifier:test")
predict = bc.predict(X_test)
acc = accuracy_score(y_test, predict)
print(acc)
max_acc = acc
max_acc_i = 0
y1 = y
acc = accuracy_score(y, predict_train)
#use IterativeBagging for classifier
print("IterativeBagging")
for i in range(20):
#predict test data
