XGBoost訓練流程

1.調用流程

import xgboost as xgb
from xgboost.sklearn import XGBClassifier
from sklearn.grid_search import GridSearchCV
from sklearn import metrics

def modelfit(alg, dtrain, dtest, predictors,useTrainCV=True, cv_folds=5, early_stopping_rounds=50):
    
    if useTrainCV:
        xgb_param = alg.get_xgb_params()
        xgtrain = xgb.DMatrix(dtrain[predictors], label=dtrain[target])
        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)
        print (cvresult.shape[0])
        alg.set_params(n_estimators=cvresult.shape[0])
    
    #Fit the algorithm on the data
    alg.fit(dtrain[predictors], dtrain['Disbursed'],eval_metric='auc')
        
    #Predict training set:
    dtrain_predictions = alg.predict(dtrain[predictors])
    dtrain_predprob = alg.predict_proba(dtrain[predictors])[:,1]
        
    #Print model report:
    print ("\nModel Report")
    print ("Accuracy : %.4g" % metrics.accuracy_score(dtrain['Disbursed'].values, dtrain_predictions))#alg.score(dtrain[predictors], dtrain['Disbursed'])也行
    print ("AUC Score (Train): %f" % metrics.roc_auc_score(dtrain['Disbursed'], dtrain_predprob))   
    feat_imp = pd.Series(alg.get_booster().get_fscore()).sort_values(ascending=False)#booster所有弱分類器、F值、排序
    feat_imp.plot(kind='bar', title='Feature Importances')
    plt.ylabel('Feature Importance Score')

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)
modelfit(xgb1, train, test, predictors)

2.訓練

2.1.大learning_rate，小n_estimators

2.2.網格調參

2.3.分類器數量調整

2.4.重複2.2與2.3

2.5.小learning_rate，大n_estimators

 

還有另一種方法，但無法網格調參

import xgboost as xgb
params={'....'}
trains = xgb.DMatrix(trains_x,label=trains_y)

#訓練模型
watchlist = [(dataset1,'train')]#監視作用
model = xgb.train(params,trains,num_boost_round=3500,evals=watchlist)