-
-
Notifications
You must be signed in to change notification settings - Fork 1.7k
Open
Labels
bugSomething isn't workingSomething isn't workingmodule:forecastingforecasting module: forecasting, incl probabilistic and hierarchical forecastingforecasting module: forecasting, incl probabilistic and hierarchical forecasting
Description
Describe the bug
In nixtla statsforecast version 1.6.0, the parallel argument has been deprecated in AutoARIMA. This causes the sktime wrapper to fail.
Nixtla/statsforecast#576
Nixtla/statsforecast@478e774
To Reproduce
!pip install sktime
!pip install statsforecast==1.6.0
from sktime.datasets import load_airline
from sktime.forecasting.statsforecast import StatsForecastAutoARIMA
y = load_airline()
forecaster = StatsForecastAutoARIMA(
sp=12, d=0, max_p=2, max_q=2
)
forecaster.fit(y)
y_pred = forecaster.predict(fh=[1,2,3])
!pip install statsforecast==1.5.0
forecaster = StatsForecastAutoARIMA(
sp=12, d=0, max_p=2, max_q=2
)
forecaster.fit(y)
y_pred = forecaster.predict(fh=[1,2,3])
This works
Expected behavior
Should work with latest version of statsforecast
Additional context
First found in pycaret unit tests
Versions
latest install - 0.22.0
psteinb and ali-ramadhan
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't workingmodule:forecastingforecasting module: forecasting, incl probabilistic and hierarchical forecastingforecasting module: forecasting, incl probabilistic and hierarchical forecasting
Type
Projects
Status
Needs triage & validation