XGBOOST学习曲线及改进，泛化误差

from xgboost import XGBRegressor as XGBR
from sklearn.ensemble import RandomForestRegressor as RFR
from sklearn.linear_model import LinearRegression as LR
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split,cross_val_score as CV,KFold
from sklearn.metrics import mean_squared_error as MSE
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from time import time
import datetime

data=load_boston()
X=data.data
y=data.target

Xtrain,Xtest,ytrain,ytest=train_test_split(X,y,test_size=0.3,random_state=420)
reg=XGBR(n_estimators=100).fit(Xtrain,ytrain)

reg.predict(Xtest)
reg.score(Xtest,ytest)#返回的是R平方
MSE(ytest,reg.predict(Xtest))
reg.feature_importances_
#查看SKLEARN中所有的模型评估指标
import sklearn
sorted(sklearn.metrics.SCORERS.keys())

#交叉验证，与线性回归随机森林进行结果比对
reg=XGBR(n_estimators=100)