search

zhaokg / Rbeast

Bayesian Change-Point Detection and Time Series Decomposition
208 stars 36 forks source link

RBeast issue -Assuming a complexity prior distribution on the number of change-points with `gammaParameter = 2` #3

Closed Maglisa closed 2 years ago

Maglisa commented 3 years ago

Hi,

It seems that there is an issue with Rbeast, it is not running today. My code worked perfectly fine the previous day but today I am getting an error . (see the error output below "=====")

Assuming a complexity prior distribution on the number of change-points with gammaParameter = 2. Computing posterior parameters... Error in numeric(nTime) : invalid 'length' argument Is this a temporally thing? Can you help?

Thank you,

zhaokg commented 2 years ago

Hi Maglisa, Sorry for not get a chance to see your issue report earlier and for my belated reply. Not sure if my reply is still relevant. In any case, I am not sure if you are using the right package. I mean there are multiple packages called Rbeast. I am not sure if you are doing time-series analysis or revolutionary tree analysis. But in my Rbeast package, 'gammaParameter' is never a parameter in the model.

My best guess is that you are using the beast function from the beast package (it seems to have a parameter called gammaParameter), which has nothing to do with Rbeast. Sorry about the confusion. I'd like to name my package as beast, but apparently that name has been taken when I released it.