PyData London - 99th Meetup

Venue: Riverbank House, 2 Swan Ln, London EC4R 3AD

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct. Please familiarise yourself with it before attending.

If your RSVP status says "You're going" you will be able to get in. No need to show your RSVP confirmation when signing in.
If you can no longer make it, please unRSVP as soon as possible.
***
Code of Conduct:
This event follows the NumFOCUS Code of Conduct. Please get in touch with the organisers with any questions or concerns.
***
As always, there will be free food and drinks, generously provided by our host, Man Group.
***

Main Talks

1. Skrub: Machine Learning with DataFrames - Gaël Varoquaux

While data-science often talks about machine learning, much of the work lies in preparing and assembling DataFrames - a process that is highly manual. I'll introduce Skrub, a young package that eases machine learning with DataFrames. It provides a variety of tools to plug any scikit-learn-type model into complex and messy DataFrames with no manual effort.
I will also discuss the exciting "DataOps" features coming in the new release, which wrap and record any data assembly or wrangling pipeline, and can apply full machine-learning workflows: applying the plan on new data, cross-validation, or tuning it to maximise prediction accuracy on a task.

2. Breaking the Black Box - How to Evaluate Your Agents... in Real Time Too! - Craig West

If you are building with LLMs, creating high quality evaluations is one of the most impactful things you can do. Without evals, it can be very difficult and time intensive to understand how different model versions might affect your use case. This talk aims to provide you a roadmap that may be simpler than you think to implement.

In this talk, we will look at the two aspects of Observability and Evaluation. Using the manual evaluating-ai-agents.com, along with its code repo, we will see that observability can be done without vendor solutions but with standard Python, either during Evaluation Driven Development or after development.

We will look at three core evaluation strategies - deterministic, human and LLM as Judge - with code examples.

⚡ Lightning Talks

1. From RNNs to Reliable Agents: Context Engineering, Roles, and What 1M-Token Windows Don’t Fix - Imamuddin Shaik
2. The Apprenticeship Pathway Into Data Science - Ruby Waller

Logistics
Doors open at 6.30 pm (get there early as you'll need to sign in with building security). Talks start at 7:00 pm, with drinks afterwards from 9:00 pm at The Banker (EC4).

We have reduced capacity for this event, but there will be plenty of people to discuss data science questions with!

Please unRSVP in good time if you realise you can't make it. We're limited by building security on the number of attendees, so please free up your place for your fellow community members!