ML XGBoost 하이퍼파라미터 조정

from sklearn.ensemble import RandomForestRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import GradientBoostingRegressor
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
from sklearn.linear_model import Ridge, Lasso, ElasticNet
from sklearn.model_selection import cross_val_score


dt_reg =DecisionTreeRegressor(random_state=0, max_depth=4)
ridge = Ridge(alpha = 10)
lasso = Lasso(alpha = 10)
ela = ElasticNet(alpha = 10)
# rf_reg = RandomForestRegressor(random_state=0,n_estimators=1000)
# gb_reg = GradientBoostingRegressor(random_state=0, n_estimators=1000)
xgb_reg = XGBRegressor(n_estimators=1000)
lgb_reg = LGBMRegressor(n_estimators=1000)
score = cross_val_score(ridge, X, Y, scoring='neg_mean_squared_error')
print(score)

# #트리 기반의 회귀 모델을 반복하면서 평가 수행
models = [dt_reg, ridge, lasso, ela, xgb_reg, lgb_reg]

for m in models:
    m.fit(X_train, y_train)
    Y_predict = m.predict(X_test)
    mse = mean_squared_error(y_test, Y_predict)
    rmse = np.sqrt(mse)
    # score = cross_val_score(re_reg, X, y_1d, scoring='neg_mean_squared_error')
    print(m.__class__.__name__)
    print('MSE: {:.3f}, RMSE: {:.3f}'.format(mse,rmse))
    print('R^2(Variance score):{:.3f}'.format(r2_score(y_test,Y_predict)))

 
 
n_estimators = 1000

n_estimators =100

n_estimators = 500, lr = 0.05

n_estimators = 1000, lr = 0.05

n_estimators = 3000, lr = 0.01