Python梯度提升库XGBoost解决机器学习问题使用探究

pip install xgboost

import xgboost as xgb
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
# 加载鸢尾花数据集
iris = load_iris()
X, y = iris.data, iris.target
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 将数据转换为XGBoost格式
dtrain = xgb.DMatrix(X_train, label=y_train)
dtest = xgb.DMatrix(X_test, label=y_test)
# 定义参数
params = {
    'max_depth': 3,
    'eta': 0.3,
    'objective': 'multi:softmax',
    'num_class': 3
}
# 训练模型
model = xgb.train(params, dtrain, num_boost_round=10)
# 进行预测
predictions = model.predict(dtest)
accuracy = accuracy_score(y_test, predictions)
print(f'Accuracy: {accuracy}')

# 参数调优示例
param_grid = {
    'max_depth': [3, 6, 9],
    'learning_rate': [0.1, 0.01, 0.001],
    'n_estimators': [50, 100, 200]
}
# 使用GridSearchCV寻找最佳参数
grid = GridSearchCV(estimator=xgb.XGBClassifier(), param_grid=param_grid, scoring='accuracy', cv=5)
grid.fit(X_train, y_train)
best_params = grid.best_params_
print(f"Best parameters: {best_params}")
# 使用最佳参数重新训练模型
best_model = xgb.XGBClassifier(**best_params)
best_model.fit(X_train, y_train)
# 评估模型
predictions = best_model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
print(f'Accuracy with best parameters: {accuracy}')

# 特征重要性示例
xgb.plot_importance(model)

# 回归问题示例
from sklearn.datasets import load_boston

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

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

xg_reg = xgb.XGBRegressor(objective ='reg:squarederror', colsample_bytree = 0.3, learning_rate = 0.1,
                max_depth = 5, alpha = 10, n_estimators = 10)

xg_reg.fit(X_train, y_train)

preds = xg_reg.predict(X_test)