🚀 PyMC 5.8.0 is here, packed with some fantastic updates and improvements. 🎉

🆕 New Features:
1️⃣ Causal inference: added the do operator for modeling interventions
3️⃣ Added ICAR distribution
3️⃣ Added JAX implementation for MatrixIsPositiveDefinite Op

📒 New example NB 👉 Faster Sampling with JAX and Numba, https://www.pymc.io/projects/examples/en/latest/samplers/fast_sampling_with_jax_and_numba.html
... And many more exciting updates, view the summary of changes here 👉 https://github.com/pymc-devs/pymc/releases/tag/v5.8.0

#PyMC #datascience #machinelearning #statistics #opensource

🚀 Just wrapped up an insightful session at PyMCon Web Series! 💡

Missed it? No worries! Here's the recording of Bill Engels' talk on "Introduction to Hilbert Space GPs (HSGPs) in PyMC" 👉 https://www.youtube.com/watch?v=ri5sJAdcYHk

🌟 In this talk, Bill introduced a PyMC Hilbert Space Gaussian Process (HSGP) implementation and showed via case studies how it fills a few key gaps in the PyMC GP library: fast GPs as model subcomponents, and fast GPs with non-Gaussian likelihoods 📊💡.

#PyMCon #bayesian #PyMC #python

📢 The PyMC community team will be holding office hours to provide an outlet for the community to ask questions, get help, discuss, etc. Office hours are open to everyone, and anyone should feel welcome to attend.

📅 Date: Thursday, Sept 14, 2023
⏰ Time: 17 UTC / 10 am PT / 1 pm ET
👉 Register (for Zoom link): www.meetup.com/pymc-online-meetup/events/295908813

Office hours will last about an hour, so don't worry if you can't make it at exactly this time! see you there

#pymc #bayesian #statistics

In case you missed the live session on "Automatic Probability - Q&A" by Ricardo Vieira at the PyMCon Web Series, The recording is now available on YouTube.

🎥Recording: https://youtu.be/IdHAST6hgds

Don't miss out on this insightful talk, for more detailed information
🔗 Visit the Discourse post: https://discourse.pymc.io/t/12274
🌐 Explore the official website: https://pymcon.com/events/

#PyMConWebSeries #pymc #datascience #event #python

My first blog post using #bayesian modelling (with #pymc) on estimating tenure effects: https://aurimas.eu/blog/2023/04/modeling-tenure-effects-the-bayesian-way/

I couldn't have done it without going through the fantastic Statistical Rethinking class earlier this year by @rlmcelreath. Highly highly recommend it!

Pleased to announce the release of #PyMC-Marketing: A new open-source library to do #Bayesian media mix and customer lifetime value modeling (successor of the lifetimes library).

https://pymc-labs.io/blog-posts/pymc-marketing-a-bayesian-approach-to-marketing-data-science/

By @pymc_labs

As part of the #PyMCon Web Series, we will be holding #PyMC office hours tomorrow, with a focus on Gaussian processes (GPs) of all types. Hosts will be PyMC & GP experts Danh Phan, Bill Engels, & @fonnesbeck . Come ask all your GP+PyMC questions! https://www.meetup.com/pymc-online-meetup/events/292211190/

On Thursday afternoon (15:45) I'll host panel discussion on probabilistic programming (and what does it require to ge a new algorithm added to some PPL package) with panelists
- Mitzi Morris, #Stan / Columbia University
- Junpeng Lao @junpenglao, TFP / #PyMC / Google
- Tor Fjelde, #TuringLang / University of Cambridge
- Henri Pesonen @henri_pesonen, #ELFI / Oslo University Hospital

#BayesComp2023 #Bayes #MCMC

In about an hour I be live streaming as I update a set of #PyMC notebooks that accompanies Kruschke's introductory "Doing #Bayesian Data Analysis" book (aka "the puppy book"). Come say hi. Or just lurk. https://youtube.com/live/iBBlPdZ3OVs?feature=share

📢Calling all #python 🐍 enthusiasts and industry leaders!

Become a sponsor for #PyMCon and help us build the future of Bayesian Modeling. Showcase your brand to a highly engaged community and unlock opportunities for growth and collaboration.

Check out our sponsorship levels and benefits: 👉 http://pymcon.com/sponsors

#PyMCon2023 #PyMC #BayesianModeling #Bayesian

@tylerjburch Yes, I hear you 😓

You've likely already fixed your installation and I'm not sure whether you're using #jupyter, but I found this guide really helpful:

https://pkseeg.com/post/jupyter-venv/

Now, I always warn people to never mess with the base installation of #python on a machine but use (virtual) environments instead.

Good luck with the #GaussianProcesses, I'm going through the #pymc tutorials for it right now 😎

I will be hosting PyMC office hours on Feb. 28 (Tuesday) to provide an outlet for the community to ask questions, get help, discuss, etc. Office hours are open to everyone and anyone should feel welcome to attend.

15:00 UTC/10 am NYC/12 noon Rio de Janeiro/3 pm London/4 pm Barcelona

Registration and details on Meetup: https://www.meetup.com/pymc-online-meetup/events/291777336/

@pymc #pymc #statistics #bayesian #bayes

The PyMCon Web Series continues tomorrow with a live webinar.

An Introduction to Multi-Output Gaussian Processes Using PyMC
Danh Phan
Feb 21st 2023 22:00 UTC

Registration and more details on Meetup: https://www.meetup.com/pymc-online-meetup/events/291618626/

Danh has provided an entire repository of code to go along with the talk as well as a pretty cool dashboard providing data on US/AU/UK interest rates, both past and future. Links to everything on Meetup 👆
@pymc #PyMCon #statistics #pymc #bayesian #bayes

The PyMCon Web Series continues rolling along!

Danh Phan will present "An Introduction to Multi-Output Gaussian Processes using PyMC"

Code associated with Danh's talk is already available. The synchronous portion of the event (Danh's talk) will take place next week (Tuesday or Wednesday depending on your timezone).

Registration and full details here: https://www.meetup.com/pymc-online-meetup/events/291618626/

@pymc #PyMCon #statistics #pymc #bayesian #bayes

The PyMCon Web Series is kicking off this Thursday!

Dante Gates will present "The Power of Bayes in Industry: What Is a Data Generating Process and Why Does It Matter?

Dante's notebook and pre-event discussion: https://discourse.pymc.io/t/pymcon-web-series-the-power-of-bayes-in-industry-your-business-model-is-your-data-generating-process-feb-9-2023/11264

Subscribe to the Meetup event: https://www.meetup.com/pymc-online-meetup/

@pymc #PyMCon #statistics #pymc #bayesian #bayes

Each event in the series will be mostly-asynchronous and completely free. Speakers are #PyMC community members presenting the cool (likely #Bayesian) stuff they have been working on. We have an incredible lineup of speakers.

We are in the midst of launching the brand new #PyMCon Web Series! Our first event will be in just a few weeks.

https://pymcon.com now has preliminary details of the first events, with more to come soon. To get all the updates, bookmark the site and/or join the #PyMC Meetup group (meetup.com/pymc-online-meetup/). @pymc @canyon289 #statistics #bayesian

Noticias sobre Python científico de la semana, episodio 61 🐍⚙️

En resumen: Versiones nuevas de Ibis y Fugue, análisis bayesiano de retención de cohortes, el futuro de la paquetería en Python, reuniones de PyData en Madrid y Granada, y ChatGPT escribiendo artículos https://astrojuanlu.substack.com/p/episodio-61 Apoya el noticiero suscribiéndote por correo 📫

#noticieropythoncientifico #ibis #fugue #pymc #chatgpt #pydata #python

we're kicking the New Year off with a very #Bayesian episode 🎆
#NUTS 🌰sampling, a new #ZeroSumNormal #distribution, #PyMC, the Bayesian workflow and more is all covered in episode 74 with @aseyboldt @pymc_devs #BayesianStats #modelling

https://learnbayesstats.com/episode/74-optimizing-nuts-developing-zerosumnormal-distribution-adrian-seyboldt/

Almost as beautiful as the feeling of looking at those data and realizing that @EricaJYoon@twitter.com @mhtessler@twitter.com, Noah Goodman, and I produced that graph. So happy to hear it worked first try!!

RT @CarcassiFausto@twitter.com

Beautiful feeling: reproducing the same modelling results as a paper (https://direct.mit.edu/opmi/article/doi/10.1162/opmi_a_00035/95942/Polite-Speech-Emerges-From-Competing-Social-Goals) with a totally independent implementation (in #pymc) based just on the description in the text (first: paper, second: mine)

🐦🔗: https://twitter.com/CarcassiFausto/status/1610347036674592768