XGBoost 详解

pip install xgboost # GPU 版本（需要 CUDA） pip install xgboost # 新版已内置 GPU 支持 # 验证安装 python -c "import xgboost; print(xgboost.__version__)"

import xgboost as xgb from sklearn.datasets import load_breast_cancer from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score, classification_report # 加载数据 data = load_breast_cancer() X_train, X_test, y_train, y_test = train_test_split( data.data, data.target, test_size=0.2, random_state=42 ) # 创建分类器 clf = xgb.XGBClassifier( n_estimators=200, max_depth=5, learning_rate=0.1, subsample=0.8, colsample_bytree=0.8, reg_alpha=0.1, reg_lambda=1.0, random_state=42, eval_metric='logloss' ) # 训练（带 early stopping） clf.fit( X_train, y_train, eval_set=[(X_test, y_test)], verbose=False ) # 预测与评估 y_pred = clf.predict(X_test) print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}") print(classification_report(y_test, y_pred, target_names=data.target_names))

import xgboost as xgb from sklearn.datasets import fetch_california_housing from sklearn.model_selection import train_test_split from sklearn.metrics import mean_squared_error, r2_score import numpy as np # 加载数据 data = fetch_california_housing() X_train, X_test, y_train, y_test = train_test_split( data.data, data.target, test_size=0.2, random_state=42 ) # 创建回归器 reg = xgb.XGBRegressor( n_estimators=500, max_depth=6, learning_rate=0.05, subsample=0.8, colsample_bytree=0.8, reg_lambda=1.0, random_state=42 ) # 训练 reg.fit( X_train, y_train, eval_set=[(X_test, y_test)], verbose=False ) # 评估 y_pred = reg.predict(X_test) rmse = np.sqrt(mean_squared_error(y_test, y_pred)) r2 = r2_score(y_test, y_pred) print(f"RMSE: {rmse:.4f}") print(f"R2: {r2:.4f}")

import matplotlib.pyplot as plt # 方法 1: 内置 plot_importance xgb.plot_importance(clf, max_num_features=15, importance_type='gain') plt.title('Feature Importance (Gain)') plt.tight_layout() plt.savefig('feature_importance.png', dpi=150) plt.show() # 方法 2: 使用 feature_importances_ 属性 importances = clf.feature_importances_ indices = np.argsort(importances)[::-1][:15] plt.figure(figsize=(10, 6)) plt.bar(range(len(indices)), importances[indices]) plt.xticks(range(len(indices)), [data.feature_names[i] for i in indices], rotation=45) plt.title('Top 15 Features') plt.tight_layout() plt.show()

import xgboost as xgb from sklearn.model_selection import cross_val_score # 方法 1: sklearn 交叉验证 clf = xgb.XGBClassifier( n_estimators=200, max_depth=5, learning_rate=0.1, random_state=42, eval_metric='logloss' ) scores = cross_val_score(clf, X_train, y_train, cv=5, scoring='accuracy') print(f"CV Accuracy: {scores.mean():.4f} (+/- {scores.std():.4f})") # 方法 2: xgboost 原生 CV（推荐，支持 early stopping） dtrain = xgb.DMatrix(X_train, label=y_train) params = { 'max_depth': 5, 'eta': 0.1, 'objective': 'binary:logistic', 'eval_metric': 'logloss', 'subsample': 0.8, 'colsample_bytree': 0.8, } cv_results = xgb.cv( params, dtrain, num_boost_round=1000, nfold=5, early_stopping_rounds=50, verbose_eval=False ) best_rounds = len(cv_results) best_score = cv_results['test-logloss-mean'].iloc[-1] print(f"Best rounds: {best_rounds}, Best logloss: {best_score:.4f}")

from sklearn.model_selection import GridSearchCV import xgboost as xgb # Step 2 示例: 调 max_depth 和 min_child_weight param_grid = { 'max_depth': [3, 5, 7, 9], 'min_child_weight': [1, 3, 5, 7], } clf = xgb.XGBClassifier( n_estimators=200, # Step 1 得到的最优值 learning_rate=0.1, subsample=0.8, colsample_bytree=0.8, random_state=42, eval_metric='logloss' ) grid = GridSearchCV( clf, param_grid, cv=5, scoring='accuracy', n_jobs=-1, verbose=1 ) grid.fit(X_train, y_train) print(f"Best params: {grid.best_params_}") print(f"Best score: {grid.best_score_:.4f}") # 也可以使用 Optuna 进行贝叶斯优化（更高效） # pip install optuna import optuna def objective(trial): params = { 'max_depth': trial.suggest_int('max_depth', 3, 10), 'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3, log=True), 'subsample': trial.suggest_float('subsample', 0.5, 1.0), 'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1.0), 'reg_alpha': trial.suggest_float('reg_alpha', 1e-8, 10, log=True), 'reg_lambda': trial.suggest_float('reg_lambda', 1e-8, 10, log=True), 'min_child_weight': trial.suggest_int('min_child_weight', 1, 10), 'gamma': trial.suggest_float('gamma', 0, 5), } clf = xgb.XGBClassifier(n_estimators=500, random_state=42, **params) scores = cross_val_score(clf, X_train, y_train, cv=5, scoring='accuracy') return scores.mean() study = optuna.create_study(direction='maximize') study.optimize(objective, n_trials=100) print(f"Best params: {study.best_params}")

# 计算正负样本比例 neg_count = (y_train == 0).sum() pos_count = (y_train == 1).sum() scale = neg_count / pos_count # 例如 99:1 的数据，scale=99 clf = xgb.XGBClassifier( scale_pos_weight=scale, # 自动调整正类权重 n_estimators=300, max_depth=5, learning_rate=0.1, eval_metric='aucpr' # 不平衡数据用 AUC-PR 更合理 ) clf.fit(X_train, y_train)

import numpy as np from sklearn.utils.class_weight import compute_sample_weight # 自动计算样本权重 sample_weights = compute_sample_weight('balanced', y_train) clf = xgb.XGBClassifier(n_estimators=300, max_depth=5) clf.fit(X_train, y_train, sample_weight=sample_weights)

# pip install imbalanced-learn from imblearn.over_sampling import SMOTE smote = SMOTE(random_state=42) X_resampled, y_resampled = smote.fit_resample(X_train, y_train) clf = xgb.XGBClassifier(n_estimators=300, max_depth=5) clf.fit(X_resampled, y_resampled)

# GPU 训练只需设置 tree_method 和 device clf = xgb.XGBClassifier( tree_method='hist', # 使用直方图算法 device='cuda', # 使用 GPU（XGBoost >= 2.0） n_estimators=1000, max_depth=8, learning_rate=0.05, subsample=0.8, colsample_bytree=0.8, ) clf.fit(X_train, y_train) # 旧版 XGBoost (< 2.0) 使用: # tree_method='gpu_hist' # predictor='gpu_predictor' # 检查是否使用了 GPU import xgboost as xgb print(xgb.build_info()) # 查看编译信息中是否包含 CUDA