Xgboost参数调节

转自：https://segmentfault.com/a/1190000014040317

整体:

# 1.调试n_estimators
cv_params = {'n_estimators': [550, 575, 600, 650, 675]}
other_params = {'learning_rate': 0.1, 'n_estimators': 600, 'max_depth': 5, 'min_child_weight': 1, 'seed': 0,
'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0, 'reg_alpha': 0, 'reg_lambda': 1}
# 2.调试max_depth、min_child_weight
# cv_params = {'max_depth': [3, 4, 5, 6, 7, 8, 9, 10], 'min_child_weight': [1, 2, 3, 4, 5, 6]}
# other_params = {'learning_rate': 0.1, 'n_estimators': 550, 'max_depth': 5, 'min_child_weight': 1, 'seed': 0,
# 'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0, 'reg_alpha': 0, 'reg_lambda': 1}
# 3.调试gamma
# cv_params = {'gamma': [0.1, 0.2, 0.3, 0.4, 0.5, 0.6]}
# other_params = {'learning_rate': 0.1, 'n_estimators': 550, 'max_depth': 4, 'min_child_weight': 5, 'seed': 0,
# 'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0, 'reg_alpha': 0, 'reg_lambda': 1}
# 4.调试subsample、colsample_bytree
# cv_params = {'subsample': [0.6, 0.7, 0.8, 0.9], 'colsample_bytree': [0.6, 0.7, 0.8, 0.9]}
# other_params = {'learning_rate': 0.1, 'n_estimators': 550, 'max_depth': 4, 'min_child_weight': 5, 'seed': 0,
# 'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0.1, 'reg_alpha': 0, 'reg_lambda': 1}
# 5.调试reg_alpha、reg_lambda
# cv_params = {'reg_alpha': [0.05, 0.1, 1, 2, 3], 'reg_lambda': [0.05, 0.1, 1, 2, 3]}
# other_params = {'learning_rate': 0.1, 'n_estimators': 550, 'max_depth': 4, 'min_child_weight': 5, 'seed': 0,
# 'subsample': 0.7, 'colsample_bytree': 0.7, 'gamma': 0.1, 'reg_alpha': 0, 'reg_lambda': 1}
# 6.调试learning_rate
# cv_params = {'learning_rate': [0.01, 0.05, 0.07, 0.1, 0.2]}
# other_params = {'learning_rate': 0.1, 'n_estimators': 550, 'max_depth': 4, 'min_child_weight': 5, 'seed': 0,
# 'subsample': 0.7, 'colsample_bytree': 0.7, 'gamma': 0.1, 'reg_alpha': 1, 'reg_lambda': 1}
 
model = xgb.XGBClassifier(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, cv=5, verbose=1, n_jobs=4)
optimized_GBM.fit(X_train, y_train)
evalute_result = optimized_GBM.grid_scores_
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))

1.调节最大迭代次数n_estimators

# 最佳迭代次数：n_estimators
from xgboost import XGBRegressor
from sklearn.model_selection import GridSearchCV
cv_params = {'n_estimators': [20,30,40]}
other_params = {'learning_rate': 0.1, 'n_estimators': 500, 'max_depth': 5, 'min_child_weight': 1, 'seed': 0,
                    'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0, 'reg_alpha': 0, 'reg_lambda': 1}
model = XGBRegressor(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, scoring='r2', cv=3, verbose=1, n_jobs=-1)
optimized_GBM.fit(x_data, y_data)
evalute_result =optimized_GBM.return_train_score
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))

2.调试的参数是min_child_weight以及max_depth：

# 调试的参数是min_child_weight以及max_depth：
cv_params = {'max_depth': [3, 4, 5, 6, 7, 8, 9, 10], 'min_child_weight': [6,7,8]}
other_params = {'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 5, 'min_child_weight': 1, 'seed': 0,
                    'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0, 'reg_alpha': 0, 'reg_lambda': 1}
model = XGBRegressor(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, scoring='r2', cv=3, verbose=1, n_jobs=-1)
optimized_GBM.fit(x_data, y_data)
evalute_result =optimized_GBM.return_train_score
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))

3.调试参数：gamma：

# 调试参数：gamma：
cv_params = {'gamma': [0.1, 0.2, 0.3, 0.4, 0.5, 0.6]}
other_params = {'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 4, 'min_child_weight': 6, 'seed': 0,
                    'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0, 'reg_alpha': 0, 'reg_lambda': 1}
model = XGBRegressor(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, scoring='r2', cv=3, verbose=1, n_jobs=-1)
optimized_GBM.fit(x_data, y_data)
evalute_result =optimized_GBM.return_train_score
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))

4. 调试subsample以及colsample_bytree：

# 调试subsample以及colsample_bytree：
cv_params = {'subsample': [0.6, 0.7, 0.8, 0.9], 'colsample_bytree': [0.6, 0.7, 0.8, 0.9]}
other_params = {'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 4, 'min_child_weight': 6, 'seed': 0,
                    'subsample': 0.8, 'colsample_bytree': 0.8, 'gamma': 0.2, 'reg_alpha': 0, 'reg_lambda': 1}
model = XGBRegressor(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, scoring='r2', cv=3, verbose=1, n_jobs=4)
optimized_GBM.fit(x_data, y_data)
evalute_result =optimized_GBM.return_train_score
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))

5.调试reg_alpha以及reg_lambda：

# 调试reg_alpha以及reg_lambda：
cv_params = {'reg_alpha': [0.05, 0.1, 1, 2, 3], 'reg_lambda': [0.05, 0.1, 1, 2, 3]}
other_params = {'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 4, 'min_child_weight': 6, 'seed': 0,
                    'subsample': 0.8, 'colsample_bytree': 0.9, 'gamma': 0.2, 'reg_alpha': 0, 'reg_lambda': 1}
model = XGBRegressor(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, scoring='r2', cv=3, verbose=1, n_jobs=4)
optimized_GBM.fit(x_data, y_data)
evalute_result =optimized_GBM.return_train_score
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))

6.调试learning_rate：

# 调试learning_rate，一般这时候要调小学习率来测试：
cv_params = {'learning_rate': [0.01, 0.05, 0.07, 0.1, 0.2]}
other_params = {'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 4, 'min_child_weight': 6, 'seed': 0,
                    'subsample': 0.8, 'colsample_bytree': 0.9, 'gamma': 0.2, 'reg_alpha': 0.1, 'reg_lambda': 1}
model = XGBRegressor(**other_params)
optimized_GBM = GridSearchCV(estimator=model, param_grid=cv_params, scoring='r2', cv=3, verbose=1, n_jobs=4)
optimized_GBM.fit(x_data, y_data)
evalute_result =optimized_GBM.return_train_score
print('每轮迭代运行结果:{0}'.format(evalute_result))
print('参数的最佳取值：{0}'.format(optimized_GBM.best_params_))
print('最佳模型得分:{0}'.format(optimized_GBM.best_score_))