Ben Letham
Ben Letham
From @humphreyapplebee: I was able to find another example of a series that exhibits this behaviour: ``` from fbprophet import Prophet import pandas as pd y = [800, 5700, 8200,...
If we have other time series as regressors that are being forecasted using Prophet, then cross validation should also forecast those regressors. Right now it would use the true future...
I'm creating this issue as a place to discuss supporting non-Gaussian likelihoods. There's been a fair amount of discussion on this for Poisson / Negative Binomial likelihoods (#337). This comes...
Includes the license fail in MANIFEST.in so it will be in the package on pypi. This is requested by conda forge, to which I am adding this package (https://github.com/conda-forge/staged-recipes/pull/10885).
Summary: Sign the Sobol sensitivity according to the average gradient, so we know the direction of the effect the parameter is having. Update the feature importance plot so that sign...
Summary: Style tensors can be specified via a method override, and from there are correctly passed along in the call to the PFN torch model. Differential Revision: D87847406