Adrian Price-Whelan

Oh right (and for context, this was an email I got from a user). Do you have an example you could share?

@astrosong Strange! Could you share a minimum working example script, and send the versions of schwimmbad & thejoker that you are using? What platform are you on? Thanks! ```bash python...

Hi @AstroJLin - here's a small example: https://gist.github.com/56707a370423d883a33bcc9049bdbf7a

What versions of cython, numpy, and thejoker do you have installed?

What type is your variable `P`? You should probably name it something else, like `period` or `_P` since you redefine it as a model parameter. What if you try: ```python...

Oh interesting - there is something weird about the way `pm.Constant()` is storing the value (it keeps it internally as an int, so the period becomes 0, which is invalid)....

For your data, `thejoker` returns many samples -- i.e., your `samples` variable has 256 posterior samples. When you run `setup_mcmc()`, you should only pass one sample. Here you can do...

It all comes down to how you want to parametrize and deal with phase. I think the current implementation uses a fixed reference time and M0 specifies the phase angle...

Hi @guosufen! Thanks for the issue. Could you try installing the latest development version instead? ``` pip install git+https://github.com/adrn/thejoker ``` and see if it has the same issue?

If you use conda, could you dump your environment info with: `conda list > conda_env.txt` and send that to me? Also, it'd be handy if you could send me a...