-
-
Simple time series to predict next few months.
-
Getting this error on AutoARIMA model implementation have some 25000 datapoints over 12 months of data.
-
I try running backtesting on a sarimax forecaster...
```
best_sarimax_forecaster_total_defaults_increasing_training_size = ForecasterSarimax(
regressor = ARIMA(order=(2, 1, 2), seasonal_order=(1, 0…
-
I trained my ARIMA model by doing the following
`from statsmodels.tsa.arima.model import ARIMA`
`model_ar = ARIMA(data.Num_Passengers, order=(1,0, 0))`
`results_ar = model_ar.fit()`
`results_a…
-
I am doing sanity checks for 0.6.0 DLCs and getting the following line in logs about cublas:
```
Training timeseries model DeepAR.
Could not load symbol cublasGetSmCountTarget from libcublas.so.11.…
-
* Orion version: 0.4.1
* Python version: 3.8.10
* Operating System: Running on Colab
### Description
Hi! First of all let me praise the work you've been doing. Really appreciate it!
I was try…
-
I was trying to figure out if statsmodel also offers some kind of update function, where one can update the model with new y and X data. The update function of the statsmodel module does not fulfill …
-
Should we expect the results from statsmodels.tsa.arima_model ARMA to mirror the results for statsmodels.tsa.arima.model.ARIMA with order 1, 0, 1?
-
This is needed for ARIMAX models, where ARIMA states are backcasted and X is optimised.