from sklearn.model_selection import train_test_split
#Whole dataset
#切分:切分时先进行洗牌的操作再切分
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0)
print("Number transactions train dataset: ",len(X_train))
print("Number transactions test dataset: ",len(X_test))
print("Total number of transactions: ",len(X_train)+len(X_test))
#Undersampled dataset
X_train_undersample,X_test_undersample,y_train_undersample,y_test_undersample=train_test_split(X_undersample,
Y_undersample,
test_size=0.3,
random_state=0)
print(" ")
print("Number transactions train dataset: ",len(X_train_undersample))
print("Number transactions test dataset: ",len(X_test_undersample))
print("total number of transations: ",len(X_train_undersample)+len(X_test_undersample))