xgb_param_fit2.py 文件源码

def modelfit(alg, predictors, target, useTrainCV=True, cv_folds=5, early_stopping_rounds=50):

    if useTrainCV:
        xgb_param = alg.get_xgb_params()
        xgtrain = xgb.DMatrix(predictors.values, label=target.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])

    #Fit the algorithm on the data
    alg.fit(predictors, target, eval_metric='auc')

    #Predict training set:
    dtrain_predictions = alg.predict(predictors)
    dtrain_predprob = alg.predict_proba(predictors)[:, 1]

    #Print model report:
    print("\nModel Report")
    print("Accuracy : %.4g" % metrics.accuracy_score(target.values, dtrain_predictions))
    print("AUC Score (Train): %f" % metrics.roc_auc_score(target, dtrain_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')

# examples of usage
# 1