XGBoost

XGBoost

# ================基于XGBoost原生接口的回归=============

import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error

# 加载数据集
boston = load_boston()
X,y = boston.data,boston.target

# XGBoost训练过程
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

params = {
'booster': 'gbtree',
'objective': 'reg:gamma',
'gamma': 0.1,
'max_depth': 5,
'lambda': 3,
'subsample': 0.7,
'colsample_bytree': 0.7,
'min_child_weight': 3,
'silent': 1,
'eta': 0.1,
'seed': 1000,
'nthread': 4,
}

dtrain = xgb.DMatrix(X_train, y_train)
num_rounds = 300
plst = params.items()
model = xgb.train(plst, dtrain, num_rounds)

# 对测试集进行预测
dtest = xgb.DMatrix(X_test)
ans = model.predict(dtest)

# 显示重要特征
plot_importance(model)
plt.show()

 

 

# ==============基于Scikit-learn接口的分类================
from sklearn.datasets import load_iris
import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 加载样本数据集
iris = load_iris()
X,y = iris.data,iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234565) # 数据集分割

# 训练模型
model = xgb.XGBClassifier(max_depth=5, learning_rate=0.1, n_estimators=160, silent=True, objective='multi:softmax')
model.fit(X_train, y_train)

# 对测试集进行预测
y_pred = model.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test,y_pred)
print("accuarcy: %.2f%%" % (accuracy*100.0))

# 显示重要特征
plot_importance(model)
plt.show()

 

https://blog.csdn.net/luanpeng825485697/article/details/79907149?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase