import numpy as np
from sklearn.metrics import mean_squared_error as MSE
select_columns = ["変数A","変数B","変数C","変数D","変数E"]
dummy_data = pd.get_dummies(data[select_columns],drop_first=True)
X_train,X_test,y_train,y_test = train_test_split(dummy_data, data["y"], random_state = 123)
lr = LinearRegression()
lr.fit(X_train, y_train)
y_pred_train = lr.predict(X_train)
y_pred_test = lr.predict(X_test)
rmse_train = np.sqrt(MSE(y_train, y_pred_train))
rmse_test = np.sqrt(MSE(y_test, y_pred_test))
print(rmse_train)
print(rmse_test)