1.首先导入包html
import xgboost as xgb
2.使用如下的函数实现交叉验证训练xgboost。函数
bst_cvl = xgb.cv(xgb_params, dtrain, num_boost_round=50,
nfold=3, seed=0, feval=xg_eval_mae, maximize=False, early_stopping_rounds=10)
3.cv参数说明:函数cv的第一个参数是对xgboost训练器的参数的设置,具体见如下学习
xgb_params = { 'seed': 0, 'eta': 0.1, 'colsample_bytree': 0.5, 'silent': 1, 'subsample': 0.5, 'objective': 'reg:linear', 'max_depth': 5, 'min_child_weight': 3 }
参数说明以下:优化
4.cv参数说明:dtrain是使用下面的函数DMatrix获得的训练集lua
dtrain = xgb.DMatrix(train_x, train_y)
5.cv参数说明:feval参数是自定义的偏差函数spa
def xg_eval_mae(yhat, dtrain): y = dtrain.get_label() return 'mae', mean_absolute_error(np.exp(y), np.exp(yhat))
6.cv参数说明:nfold是交叉验证的折数, early_stopping_round是多少次模型没有提高后就结束, num_boost_round是加入的决策树的数目。.net
7. bst_cv是cv返回的结果,是一个DataFram的类型,其列为如下列组成线程
8.自定义评价函数:具体见这个博客:https://blog.csdn.net/wl_ss/article/details/78685984code
def customedscore(preds, dtrain): label = dtrain.get_label() pred = [int(i>=0.5) for i in preds] confusion_matrixs = confusion_matrix(label, pred) recall =float(confusion_matrixs[0][0]) / float(confusion_matrixs[0][1]+confusion_matrixs[0][0]) precision = float(confusion_matrixs[0][0]) / float(confusion_matrixs[1][0]+confusion_matrixs[0][0]) F = 5*precision* recall/(2*precision+3*recall)*100 return 'FSCORE',float(F)
这种自定义的评价函数能够用于XGboost的cv函数或者train函数中的feval参数htm
还有一种定义评价函数的方式,以下
def mae_score(y_ture, y_pred): return mean_absolute_error(y_true=np.exp(y_ture), y_pred=np.exp(y_pred))
这种定义的函数能够用于gridSearchCV函数的scorning参数中。
首先初始化参数的值
xgb1 = XGBClassifier(max_depth=3, learning_rate=0.1, n_estimators=5000, silent=False, objective='binary:logistic', booster='gbtree', n_jobs=4, gamma=0, min_child_weight=1, subsample=0.8, colsample_bytree=0.8, seed=7)
用cv函数求得参数n_estimators的最优值。
cv_result = xgb.cv(xgb1.get_xgb_params(), dtrain, num_boost_round=xgb1.get_xgb_params()['n_estimators'], nfold=5, metrics='auc', early_stopping_rounds=50, callbacks=[xgb.callback.early_stop(50), xgb.callback.print_evaluation(period=1,show_stdv=True)])
param_grid = {'max_depth':[1,2,3,4,5], 'min_child_weight':[1,2,3,4,5]} grid_search = GridSearchCV(xgb1,param_grid,scoring='roc_auc',iid=False,cv=5) grid_search.fit(train[feature_name],train['label']) print('best_params:',grid_search.best_params_) print('best_score:',grid_search.best_score_)
首先将上面调好的参数设置好,以下所示
xgb1 = XGBClassifier(max_depth=2, learning_rate=0.1, n_estimators=33, silent=False, objective='binary:logistic', booster='gbtree', n_jobs=4, gamma=0, min_child_weight=9, subsample=0.8, colsample_bytree=0.8, seed=7)
而后继续网格调参
param_grid = {'gamma':[1,2,3,4,5,6,7,8,9]} grid_search = GridSearchCV(xgb1,param_grid,scoring='roc_auc',iid=False,cv=5) grid_search.fit(train[feature_name],train['label']) print('best_params:',grid_search.best_params_) print('best_score:',grid_search.best_score_)
param_grid = {'subsample':[i/10.0 for i in range(5,11)], 'colsample_bytree':[i/10.0 for i in range(5,11)]} grid_search = GridSearchCV(xgb1,param_grid,scoring='roc_auc',iid=False,cv=5) grid_search.fit(train[feature_name],train['label']) print('best_params:',grid_search.best_params_) print('best_score:',grid_search.best_score_)
param_grid = {'reg_lambda':[i/10.0 for i in range(1,11)]} grid_search = GridSearchCV(xgb1,param_grid,scoring='roc_auc',iid=False,cv=5) grid_search.fit(train[feature_name],train['label']) print('best_params:',grid_search.best_params_) print('best_score:',grid_search.best_score_)
最后咱们使用较低的学习率以及使用更多的决策树,能够用CV
来实现这一步骤
xgb1 = XGBClassifier(max_depth=2, learning_rate=0.01, n_estimators=5000, silent=False, objective='binary:logistic', booster='gbtree', n_jobs=4, gamma=2.1, min_child_weight=9, subsample=0.8, colsample_bytree=0.8, seed=7, )
具体的关于调参的知识请看如下连接:
https://www.cnblogs.com/TimVerion/p/11436001.html
http://www.pianshen.com/article/3311175716/