xgb.py 文件源码

def sub(flags):
    X,y,Xt,_,_ = build_feature(flags)
    if '4c' in flags.task:
        y = np.argmax(to4c(onehot_encode(y)),axis=1)
    print(X.shape,Xt.shape,y.shape)
    params['num_class'] = np.max(y)+1
    params['num_round'] = 90 
    params["early_stopping_rounds"] = None
    params['verbose_eval'] = 100
    yp = np.zeros([Xt.shape[0],9])
    m = 5 if 'bag' in flags.task else 1
    for i in range(m):
        params['seed'] = i*9
        model = xgb_model(params)
        model.fit(X,y,print_fscore=False)
        tmp = model.predict(Xt)
        print(i,np.mean(tmp))
        yp += tmp
    yp/=m
    s = pd.DataFrame(yp,columns=["class%d"%i for i in range(1,yp.shape[1]+1)])
    s['ID'] = 1+np.arange(yp.shape[0])
    s.to_csv(flags.pred_path,index=False)