pymc
pymc copied to clipboard
Bayesian Modeling and Probabilistic Programming in Python
### Description This seems to be an old transform that was replaced by the Simplex transform.
### Describe the issue: When using mutable coords in a model then calling `set_data` to change the coordinates to values that are a different size than the original results in...
### Description The model fgraph functionality (used by `do` and `observe`) doesn't work with GP variables because those are not represented as pure PyTensor objects and make use of variables...
### Issue with current documentation: _No response_ ### Idea or request for content: ## Beginner friendly issues Here are the beginner friendly issues for pytensor, most recently updated first Click...
**What is this PR about?** Closes #7041 This is a draft to add convergence checks to the JAX samplers. Right now I'm just calling `run_convergence_checks` after sampling. It might be...
Closes #6972 This PR provides a new model transform that freezes RV dims that depend on coords as well as mutable data, for those worried about performance issues or incompatibilities...
### Description It is currently possible to create dims without coords via `pm.Data`: ```python import pymc as pm with pm.Model() as m: x = pm.MutableData("x", [0, 1, 2], dims=("dim_without_coord",)) y...
### Before I’ve started using PyMC’s variational inference to fit my models. I have no prior experience with this, but I guess there’s parallels with training neural networks, where the...
### Description PyMC users are used to getting an immediate report when there are divergences in the standard NUTS sampler. I suggest we print (log) this information when we call...
### Describe the issue: Working through some examples and done some tests. In some cases pymc just stops without any error message. ### Reproduceable code example: ``` for examples running...