RJT1990 / pyflux

Open source time series library for Python
BSD 3-Clause "New" or "Revised" License
2.1k stars 240 forks source link

Something wrong with EGARCH priors #114

Closed yongsua1989 closed 6 years ago

yongsua1989 commented 6 years ago

AttributeError Traceback (most recent call last)

in () ----> 1 model.list_priors() AttributeError: 'EGARCHM' object has no attribute 'list_priors' In [20]: model.adjust_prior([0,1,2,3,4,5], pf.Uniform()) --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in () ----> 1 model.adjust_prior([0,1,2,3,4,5], pf.Uniform()) AttributeError: 'module' object has no attribute 'Uniform'

I got the following error when I followed the examples given by the documentation.

yongsua1989 commented 6 years ago

Ooops, I realized that there wasn't any uniform prior anymore. Only Normal and Flat priors for EGARCH.

Index Latent Variable Prior Prior Hyperparameters V.I. Dist Transform ======== ========================= =============== ========================= ========== ========== 0 Vol Constant Normal mu0: 0, sigma0: 3 Normal None
1 p(1) Normal mu0: 0, sigma0: 0.5 Normal logit
2 q(1) Normal mu0: 0, sigma0: 0.5 Normal logit
3 v Flat n/a (non-informative) Normal exp
4 Returns Constant Normal mu0: 0, sigma0: 3 Normal None
5 GARCH-M Normal mu0: 0, sigma0: 3 Normal None

yongsua1989 commented 6 years ago

I think the default priors work well for most of the cases.

RJT1990 commented 6 years ago

Yep, possibly my bad in updating some of the old documentation. Thanks!