Colt Allen

What's left on getting this merged? I'm planning a LinkedIn post.

Hey @HM9N, Development on `lifetimes` has been discontinued; [pymc-marketing](https://github.com/pymc-labs/pymc-marketing) is the successor project. To answer your question, the conventional definition of recency is used in RFM analysis, which is about...

What pytensor version do you have? Latest version of pymc requires `pytensor>=2.28.2,

I'm a bit confused by the AWS instance. Are you working locally in your MacBook, or in the cloud?

Also, I use MacOS 15.3.2 myself without any issues. You might be running an outdated version of XCode, which is where these constant folding errors always originate on Macs.

Can you also check if `_mkl` or `CGer` shows up anywhere in the error trace you're getting? We've occasionally had problems where dependencies assume an x86 (the old Intel) architecture...

Hey @iliaskior, Development on the `lifetimes` project ceased nearly 3 years ago. Here's the link to the successor library, which should see a beta release in the next few months:...

Hey @dames-nxlink, These issues are likely due to API changes in `matplotlib`, but unfortunately development on `lifetimes` ceased some time ago. Here's the link to the successor library: https://github.com/pymc-labs/pymc-marketing I'm...

Hey @rachelyee, the best workaround for the `BetaGeoFitter` would be to increment the `T` array input into `conditional_probability_alive()`. This notebook contains an example for an individual customer: https://www.pymc-marketing.io/en/stable/notebooks/clv/clv_quickstart.html#customer-probability-histories `pymc-marketing` is...

Hey @KollyT, Have you created an equivalent model yet with the `pymc-marketing` library? > * If I wanted to identify lapsing consumers faster would a drop in the probability alive...