xgboost4分类问题，样本不均衡 应用

#分类案例，样本不均衡
import numpy as np
import pandas as pd
from xgboost import XGBClassifier
from sklearn.datasets import make_blobs
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix,recall_score,roc_auc_score
import matplotlib.pyplot as plt
#制造不平衡数据集
class1=500000
class2=50000
centers=[[0.0,0.0],[10.0,10.0]]
clusters_std=[7.5,3]
X,y=make_blobs(n_samples=[class1,class2]
              ,centers=centers
              ,cluster_std=clusters_std
              ,random_state=0,shuffle=False)#shuffle：将数据进行洗乱，默认值是True
X.shape

#接下来使用sklearn库进行建模
Xtrain,Xtest,ytrain,ytest=train_test_split(X,y,test_size=0.3,random_state=0)
clf=XGBClassifier().fit(Xtrain,ytrain)
preds=clf.predict(Xtest)