-
Since the update to v0.11, `statsmodels.tsa.AR` has been deprecated in favor of `statsmodels.tsa.AutoReg` and `statsmodels.tsa.SARIMAX`.
the tsmodel.py module, and the various functions herein (e…
-
#### Is your feature request related to a problem? Please describe
I'm trying to read a statsmodels.tsa.statespace.sarimax.SARIMAXResults pickle file I've saved. I'd like to pass a pathlib.Path objec…
-
Hello,
Hope all is well with you.
I'm using ARIMA model to deal with SPY price. I found the first element in the model residuals is very large. I don't know if I select some parameters of the mo…
-
On exercise Q1, in the cell starting with `# get in sample predictions`, I obtain `mean_predictions` whose sum is different from the one in the `assert` and the error propagates to all the subsequent …
-
## Describe the bug
Unittest may fail depending on the version of pmdarima and statsmodels.
## System (please complete the following information)
- Python version : 3.8.2
- darts version : 0.2…
-
I have trained a SARIMAX model using Jupyter notebook, pmdarima few weeks ago, and then closed the file. After reopen the file, can I directly use the trained SARIMAX model, which I already built?
I…
-
I have created a pipeline using following code
`pipe = Pipeline([
('boxcox', BoxCoxEndogTransformer(lmbda2=1e-6)),
('arima', pmd.AutoARIMA(trace=True,
suppress_…
cjmki updated
4 years ago
-
Hello,
I have a short Question concerning Trends in the "auto_arima" command.
Suprisingly I couldn't find anything in other issues, the documentation or blog Posts, so ist probably obvious but I'm n…
-
**Question**
I have a timeline with number of some reports per week. When I try to fit a model with `auto_arima`, I receive an error `ValueError: Found array with 0 sample(s) (shape=(0,)) whi…
-
statsmodels.tsa.statespace.mlemodel MLEResults.summary uses ljungbox with default maxlag which is most likely too large.
`lb = self.test_serial_correlation(method='ljungbox')`
see #286
relat…