Will Dean
Will Dean
If the posterior is intact but the data is not built (because there is no data set to rebuild) would any of the methods work? I am confused
@ColtAllen , how do you expect this to work? There needs to be some data to build the model. Would there be a subset of the training data in order...
Take a look @walkerke and let me know your thoughts. Large ammount of changes are automated or wouldve been caught at commit
@relausen interested in making a PR?
I lean a bit more to the separation between to the two and the default MMM being linear regression isn't very convincing to me. Only to it though. What do...
Us humans had a discussion before and landed on Marketing Mix Model as well. I am for that and that explanation is some good rational to support
Many of the params should be logged before the `pm.sample` in the autologging. This way, the UI gets information about the run before a long function call happens
Parameters will act like strings. So storing number of sample would not allow for comparisons like: params.posterior_samples >= 2000 Thus, it might make sense to store as a metric for...
Yes, *not just* type hints. In my mind, there is some information that should be attached to the Distributions and some information to the variables. And there might be an...
If you need any support, feel free to tag me. I will be happy to help where I can!