splitdata.py

train = df[(df.year > 2006) & (df.year < 2017)]
test = df[df.year >= 2017]



feature_names = ['region_cd', 'year', 'month', 'building_type',
                 'tradeprice_sido', 'construction_realized_amount','cd',
                 'spirit_deposit_rate','exchange_rate','composite_stock_price_index',
                 'economy_growth','exchequer_bond_three','household_loan_all',
                 'mortgage_all','numberofnosells','unsalenum_c']



X_train = train[feature_names]
X_test = test[feature_names]

lable_name = "tradeprice_sido_n1"
Y_train = train[lable_name]

Y_test = test[lable_name]


print(X_train.shape)
print(X_test.shape)