<p>我编写这些实用函数是为了直接计算pdq值
<em>get_PDQ_parallel</em>需要三个输入数据,这些数据是以时间戳(datetime)为索引的序列。n_作业将提供并行处理器的数量。输出将是索引中aic和bic值为order=(P,D,Q)的数据帧
p和q的范围是[0,12],而d是[0,1]</p>
<pre><code>import statsmodels
from statsmodels import api as sm
from sklearn.metrics import r2_score,mean_squared_error
from sklearn.utils import check_array
from functools import partial
from multiprocessing import Pool
def get_aic_bic(order,series):
aic=np.nan
bic=np.nan
#print(series.shape,order)
try:
arima_mod=statsmodels.tsa.arima_model.ARIMA(series,order=order,freq='H').fit(transparams=True,method='css')
aic=arima_mod.aic
bic=arima_mod.bic
print(order,aic,bic)
except:
pass
return aic,bic
def get_PDQ_parallel(data,n_jobs=7):
p_val=13
q_val=13
d_vals=2
pdq_vals=[ (p,d,q) for p in range(p_val) for d in range(d_vals) for q in range(q_val)]
get_aic_bic_partial=partial(get_aic_bic,series=data)
p = Pool(n_jobs)
res=p.map(get_aic_bic_partial, pdq_vals)
p.close()
return pd.DataFrame(res,index=pdq_vals,columns=['aic','bic'])
</code></pre>