1

I am fitting an ARIMA/SARIMAX model for a large dataset. When running the code I get the following output on my screen -

RUNNING THE L-BFGS-B CODE

           * * *

Machine precision = 2.220D-16
 N =            4     M =           10

At X0         0 variables are exactly at the bounds

At iterate    0    f=  5.69245D+00    |proj g|=  1.98922D-01

At iterate    5    f=  5.64524D+00    |proj g|=  3.32004D-03

At iterate   10    f=  5.64521D+00    |proj g|=  1.27724D-03

At iterate   15    f=  5.64389D+00    |proj g|=  2.03358D-02

At iterate   20    f=  5.60506D+00    |proj g|=  4.45951D-02

At iterate   25    f=  5.60207D+00    |proj g|=  5.31460D-04

           * * *

Tit   = total number of iterations
Tnf   = total number of function evaluations
...
    4     28     32      1     0     0   1.993D-06   5.602D+00
  F =   5.6020645399394908     

CONVERGENCE: NORM_OF_PROJECTED_GRADIENT_<=_PGTOL            
 This problem is unconstrained.

Since my dataset is quite large and I fit the ARIMA/SARIMAX models iteratively, I get multiple outputs as above which take up quite the screen space.

How do I hide/remove this output?

I tried using model.fit(iprint=-1) and model.fit(disp=-1) but I get error when I use either. I guess I am using the latest version of statsmodels where disc and iprint are deprecated. Is there another way to do this without downgrading to an earlier version of the statsmodels library?

My imports are as follows -

from statsmodels.tsa.arima.model import ARIMA
from statsmodels.tsa.statespace.sarimax import SARIMAX
wjandrea
  • 28,235
  • 9
  • 60
  • 81
sriv05
  • 33
  • 5
  • 1
    The docs for the current development still show disp, and don't say anything about deprecation. https://www.statsmodels.org/devel/generated/statsmodels.tsa.statespace.sarimax.SARIMAX.fit.html#statsmodels.tsa.statespace.sarimax.SARIMAX.fit What's the deprecation message you get? – Nick ODell Aug 08 '23 at 02:23
  • I was using `ARIMA.fit(disp=-1)` and hence got the error `TypeError: ARIMA.fit() got an unexpected keyword argument 'disp'`. However when I used it with `SARIMAX.fit()` there was no error. – sriv05 Aug 08 '23 at 04:38

0 Answers0