机器学习之xgbboost调参（网格搜索和交叉验证） |
您所在的位置：网站首页 › 网格搜索调参的优点 › 机器学习之xgbboost调参（网格搜索和交叉验证） |
|
调参步骤：
n_estimatorsmax_depth 、min_child_weightgammasubsample、colsample_bytreereg_alpha、reg_lambdalearning_rate
下面这段网上摘抄的，应该要加上 预测测试集 import xgboost as xgb from xgboost.sklearn import XGBClassifier from sklearn.model_selection import train_test_split from sklearn import metrics from sklearn.model_selection import GridSearchCV import pandas as pd import return_data from xgboost import plot_importance from matplotlib import pyplot as plt import warnings warnings.filterwarnings("ignore") #alg传入XGBOOST,X_train传入训练数据特征信息，Y_train传入训练数据标签信息 X_test 最后要预测的值 def XGBmodelfit(alg, X_train, Y_train,X_test=None,Y_test=None,X_predictions=None,useTrainCV=True, cv_folds=5, early_stopping_rounds=200): if useTrainCV: xgb_param = alg.get_xgb_params() xgtrain = xgb.DMatrix(X_train, label=Y_train) cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds, metrics='auc', early_stopping_rounds=early_stopping_rounds, show_stdv=False) alg.set_params(n_estimators=cvresult.shape[0]) #训练模型 alg.fit(X_train, Y_train,eval_metric='auc') #预测结果: dtrain_predictions = alg.predict(X_test) #输出 0 或 1 # dtrain_predprob = alg.predict_proba(X_test)[:,1] #输出概率 #打印报告信息: print("\nModel Report") print("Accuracy (Train) : %.4g" % metrics.accuracy_score(Y_test, dtrain_predictions)) print("AUC Score (Train): %f" % metrics.roc_auc_score(Y_test, dtrain_predictions)) print(alg) print("the best:") print(cvresult.shape[0]) plot_importance(alg) plt.show() # feat_imp = pd.Series(alg.booster().get_fscore()).sort_values(ascending=False) # feat_imp.plot(kind='bar', title='Feature Importances') # plt.ylabel('Feature Importance Score') #dataset_X,dataset_Y=return_data.return_tarin_data() X_train, X_test, y_train, y_test = train_test_split(dataset_X, dataset_Y, test_size=0.2, random_state=45) xgb1 = XGBClassifier( learning_rate =0.1, n_estimators=1000, max_depth=5, min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.8, objective= 'binary:logistic', nthread=4, scale_pos_weight=1, seed=27) # XGBmodelfit(xgb1,X_train,y_train,X_test,y_test) param_grid = { 'max_depth':range(3,10,2), 'min_child_weight':range(1,6,2) } #这里根据输出结果可以继续微调 # param_grid = { # 'max_depth':[7,8], # 'min_child_weight':[4,5] # } gsearch1 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=140, max_depth=9, min_child_weight=1, gamma=0, subsample=0.8,colsample_bytree=0.8, objective= 'binary:logistic', nthread=4,scale_pos_weight=1, seed=27), param_grid=param_grid,cv=5) gsearch1.fit(X_train,y_train) print(gsearch1.best_params_,gsearch1.best_score_) model_best = gsearch1.best_estimator_ model_best.fit(X_train,y_train) # 训练最优模型 y_posb=model_best.predict_proba(X_test)[:,1] # ypred=model_best.predict(X_test) #下面就是混淆矩阵 auc评估之类的了
两种XGBoost： xgb - 直接引用xgboost。接下来会用到其中的“cv”函数。XGBClassifier - 是xgboost的sklearn包。这个包允许我们像GBM一样使用Grid Search 和并行处理。开头这个函数改改，后面参照寒小阳就差不多了，但调参效果提升不大，还是要尝试特征工程，stacking，模型融合 test_results = pd.read_csv('test_results.csv') def modelfit(alg, dtrain, dtest, predictors,useTrainCV=True, cv_folds=5, early_stopping_rounds=50): ''' 功能：训练，测试，输出AUC，画出重要特征的功能 参数：alg是分类器,dtrain是训练集(包括label),dtest是测试集(不包括label),predictors是要参与训练的特征(不包括label), useTrainCV是是否要交叉验证,cv_folds是交叉验证的折数,early_stopping_rounds是到指定次数就停止继续迭代 ''' if useTrainCV: xgb_param = alg.get_xgb_params() xgtrain = xgb.DMatrix(dtrain[predictors].values, label=dtrain[target].values) xgtest = xgb.DMatrix(dtest[predictors].values) cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds, metrics='auc', early_stopping_rounds=early_stopping_rounds, show_progress=False) alg.set_params(n_estimators=cvresult.shape[0]) #训练 alg.fit(dtrain[predictors], dtrain['Disbursed'],eval_metric='auc') #预测 dtrain_predictions = alg.predict(dtrain[predictors]) dtrain_predprob = alg.predict_proba(dtrain[predictors])[:,1] #输出accuracy、AUC分数 print "\nModel Report" print "Accuracy : %.4g" % metrics.accuracy_score(dtrain['Disbursed'].values, dtrain_predictions) print "AUC Score (Train): %f" % metrics.roc_auc_score(dtrain['Disbursed'], dtrain_predprob) #预测测试集,输出测试集的AUC分数 dtest['predprob'] = alg.predict_proba(dtest[predictors])[:,1] results = test_results.merge(dtest[['ID','predprob']], on='ID') print 'AUC Score (Test): %f' % metrics.roc_auc_score(results['Disbursed'], results['predprob']) feat_imp = pd.Series(alg.booster().get_fscore()).sort_values(ascending=False) feat_imp.plot(kind='bar', title='Feature Importances') plt.ylabel('Feature Importance Score')
参考：模型融合---Xgboost调参总结 https://www.cnblogs.com/nxf-rabbit75/p/10595551.html 寒小阳 机器学习系列(12)_XGBoost参数调优完全指南（附Python代码）https://blog.csdn.net/han_xiaoyang/article/details/52665396 XGboost-网格调参法 https://blog.csdn.net/zllnau66/article/details/81980876
|
| CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |