我正在寻找一种将自定义参数传递给auto_arima的方法,以找到最佳的AIC值。我手动发现p,q值在15到20之间给了我最好的结果。现在,我想检查AIC值在10到20之间。我尝试了GridsearchCV,但要花费太多时间才能达到最佳拟合。
我尝试了start_p
,start_q
,max_q
和max_P
选项10至20个范围。但是经过几次组合后,auto_arima不会继续执行。可能是earlystopping
auto_arima(df['Count'], exogenous=df['X'], start_p=10, d=None, start_q=10, max_p=20, max_d=2, max_q=20, start_P=1, D=None, start_Q=1, max_P=2, max_D=1, max_Q=2, max_order=100, m=7, seasonal=True, stationary=False, information_criterion='aic', alpha=0.05, test='kpss', seasonal_test='ch', stepwise=True, n_jobs=1, start_params=None, trend='c', method=None, transparams=True, solver='lbfgs', maxiter=50, disp=0, callback=None, offset_test_args=None, seasonal_test_args=None, suppress_warnings=False, error_action='warn', trace=False, random=False, random_state=None, n_fits=10, return_valid_fits=False, out_of_sample_size=0, scoring='mse', scoring_args=None, **fit_args)
我正在寻找类似的东西
cust_params ={................}
auto_arima(cust_params)