Benjamin T. Vincent

Results 185 issues of Benjamin T. Vincent

There was a recent refresh of the [`pymc-marketing`](https://www.pymc-marketing.io/) docs homepage, and it's looking quite nice. Let's make the following changes: - [ ] Add download stats badges (@juanitorduz might be...

documentation

### Describe the issue: There is a bug where it is possible to define a coord name which is also the same name as a data variable. So we are...

bug

Addition of new notebook (beginner level) covering Bayesian Hypothesis Testing. Demand for content on hypothesis testing was established in https://github.com/pymc-devs/pymc-examples/issues/349. This PR is intended to form a beachhead, to get...

This is a cool notebook. But just some thoughts for improvement as I was going through it: ## Clarify overall structure Fewer L2 headers to really emphasise core logical steps....

MMM

There are a bunch of different choices that can be made in terms of scaling. We should enumerate what these are and list out their pro's and con's. We could...

docs
MMM

Currently, the Bass Diffusion Model is hidden away with low discoverability. All there is (aside from the code) is an example notebook https://www.pymc-marketing.io/en/latest/notebooks/bass/bass_example.html. So we are missing an opportunity by...

docs
Bass model

This PR modernizes our `pyproject.toml` configuration and enables stricter linting rules to catch potential bugs and improve code quality. ### Changes to `pyproject.toml` - **Added project URLs**: Documentation, Changelog, and...

devops

## Background We recently added stricter ruff linting rules (#571) to the codebase (B, F, UP, C4, SIM) to catch potential bugs and enforce modern Python patterns. However, documentation notebooks...

documentation
devops

#473 should now be merged, but as an experimental new feature. It introduced a bunch of technical debt because the feature branch (off main) was done a long time ago...

refactor

This PR introduces Transfer-Function Interrupted Time Series (TF-ITS), a powerful new experiment class that extends CausalPy's causal inference capabilities to handle graded (non-binary) interventions in single-market time series data. One...

enhancement
major