sklearn sklearn中Xgboost算法介绍和XGBClassifier方法的代码实现

xgboost.XGBClassifier(max_depth=3, learning_rate=0.1, n_estimators=100, verbosity=1, objective='binary:logistic',
				booster='gbtree', tree_method='auto',n_jobs=1, gpu_id=-1, gamma=0,min_child_weight=1,
				max_delta_step=0, subsample=1, colsample_bytree=1, colsample_bylevel=1,colsample_bynode=1,
				reg_alpha=0,reg_lambda=1,scale_pos_weight=1,base_score=0.5,random_state=0,missing=None,**kwargs)

参数：

代码：

# 导入库
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from xgboost import XGBClassifier
from xgboost import plot_importance
 
### 载入数据
digits = datasets.load_digits()
 
### data analysis
print(digits.data.shape)
print(digits.target.shape)
 
### 划分训练集测试集
x_train,x_test,y_train,y_test = train_test_split(digits.data, digits.target, test_size = 0.3,random_state = 33)
### 训练模型
model = XGBClassifier(learning_rate=0.1,
                      n_estimators=100,         # 树的个数--100棵树建立xgboost
                      max_depth=6,               # 树的深度
                      min_child_weight = 1,      # 叶子节点最小权重
                      gamma=0.,                  # 惩罚项中叶子结点个数前的参数
                      subsample=0.8,             # 随机选择80%样本建立决策树
                      colsample_btree=0.8,       # 随机选择80%特征建立决策树
                      objective='multi:softmax', # 指定损失函数
                      scale_pos_weight=1,        # 解决样本个数不平衡的问题
                      random_state=27            # 随机数
                      )
# 拟合
model.fit(x_train, y_train, eval_set = [(x_test,y_test)], eval_metric = "mlogloss", early_stopping_rounds = 10,
          verbose = True)
 
### 特征重要性
fig,ax = plt.subplots(figsize=(15,15))
plot_importance(model, height=0.5, ax=ax, max_num_features=64)
plt.show()
 
### 预测
y_pred = model.predict(x_test)
 
### 模型正确率
accuracy = accuracy_score(y_test,y_pred)
print("准确率: %.2f%%" % (accuracy*100.0))

准确率：

(1797, 64)   #数据总共1797条，每条64个变量
(1797,)      #目标值个数对应数据条数
准确率: 95.37%

xgb.cv(params = list(), data, nrounds, nfold, label = NULL, missing = NA, prediction = FALSE, showsd = TRUE,
	metrics = list(), obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, verbose = TRUE
	print_every_n = 1L, early_stopping_rounds = NULL, maximize = NULL, callbacks = list(), ...

使用交叉验证获取最好的参数：

import xgboost as xgb

xgb_param = model.get_xgb_params()
xgtrain = xgb.DMatrix(x_train, label=y_train)
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=5000, nfold=5, metrics=['mlogloss'], 
     early_stopping_rounds=50, stratified=True, seed=1301)
#交叉验证后最好的树
print('Best number of trees = {}'.format(cvresult.shape[0]))
model.set_params(n_estimators=cvresult.shape[0])#把model的参数设置成最好的树对应的参数
# 下面进行相同方式的结果展现
fig,ax = plt.subplots(figsize=(15,15))
plot_importance(model, height=0.5, ax=ax, max_num_features=64)
plt.show()
 
### 预测
y_pred = model.predict(x_test)
 
### 模型正确率
accuracy = accuracy_score(y_test,y_pred)
print("准确率: %.2f%%" % (accuracy*100.0))