-
I am not sure if its just part of the source code that doesnt handle NANs but I've noticed if I input a variable with NANs in a dataframe as part of the exogenous variables, it will not properly fit t…
-
#### Describe the bug
SARIMAX is great as it supports pandas series. However, it can be a bit "wrong" with seasonal series in real cases. That's because sometimes the seasonality is based on "time …
-
Thank you for the great work on statsmodels.
I would like to fit the SARIMAX model via "Conditional Least Square Estimation" not just via "MLE".
SAS Arima has this functionality but does the S…
-
It seems that the only way to use a trained ARMA model on new data is to use this internal function: `_arma_predict_out_of_sample`. Furthermore, it's not obvious how to do so.
I would assume that f…
-
Hi,
First of all thanks for putting this ARIMA summary online.
Second, I have a question. How would someone make predictions on the future (test set) if observed data are still unknown (NaN). Here is…
-
I created this gramex.yaml
```yaml
url:
mlhandler/forecast:
pattern: /$YAMLURL/forecast
handler: MLHandler
kwargs:
data:
url: $YAMLPATH/inflation.csv # Inflation dataset
…
-
**Describe the bug**
When using `ColumnTransformer` in `ForecastingPipeline`,
- model.predict gives `ValueError: If passed as a pd.DataFrame, X must be a nested pd.DataFrame, with pd.Series or np.…
-
### Describe the bug
Pasting some breaking code, reduced from `sktime` code posted there by @garrus990, here: https://github.com/alan-turing-institute/sktime/issues/1871
A seemingly innocuous appl…
-
## Motivation
We currently use a formulation that looks directly at past values ("autoregressive" AR).
We could generalize this to..
- handle expected model prediction errors: "moving average"…
-
It is impossible to specify state disturbance variances for exogeneous regressors in `UnobservedComponents` (passed by `exog` parameter). Currently, coefficients of exogeneous parameters can only be c…