-
I build model and save her. Then I want use this model for forecast new dataset. I test how it is work
> from statsmodels.tsa.statespace.sarimax import SARIMAX
> model = SARIMAX(history, order=(7, 1…
-
I am using a series with a datetimeindex to forecast. I get the error "ValueError: Must provide freq argument if no data is supplied" if I try to predict out of sample for some of my variables. I can'…
-
I am trying to wrap my mind around the MA results in my SARIMAX model (p,d,q)=(0,1,10). Basically, I used 4 exogenous variables to explain 1 endogenous variables in its seasonal cycle. From the materi…
-
Hello Chad,
I have implemented a load forecast model using only endogenuous hourly data that is running on a rasberry pi computer. The Sarimax is relatively time and memory consuming for such a weak …
-
Can you look at the code at the "**In[7]**" (below) in the documentation https://www.statsmodels.org/dev/examples/notebooks/generated/statespace_sarimax_stata.html
```python
# In[7]
#Fit the model
…
-
#### Describe the bug
`Process finished with exit code 137 (interrupted by signal 9: SIGKILL)` while fitting `sm.tsa.SARIMAX(y, order=(10, 1, 40), seasonal_order=(0, 0, 0))`.
More info:
I hav…
-
Hello everyone. I have some problem with SARIMAX documentation.
https://www.statsmodels.org/dev/examples/notebooks/generated/statespace_sarimax_stata.html
In first exampe, you write about model AR…
-
I know `statsmodels.tsa.ar_model.AR` will be deprecated but at the moment I am seeing differences in the fitted parameter values of this and the SARIMAX equivalent. For example, according to me these …
-
```
def _aicc(model_results, nobs, add_constant):
"""Compute the corrected Akaike Information Criterion"""
aic = model_results.aic
# SARIMAX counts the constant in df_model if there …
-
SARIMAX `params` in results is pandas.Series even if I don't use pandas.
`bse` is not