PyData London

Up next: @hevansdev.bsky.social Answering a dumb question with a smart bird feeder.

Is this robin abnormally large?

Now hearing HangMAN vs AI - Kavit Tolia

Learnings building a custom transformer to play hangman.

Next up Why Python is the best language for algorithmic trading from @richardhickling.bsky.social

Now hearing from Victor Zommers on his experiments getting LLMs to play Go. They were not good, not only losing to KataGo but also Wally, developed in 1981 with just 7 rules.

Next up we have Sam Joseph LLMs can tell jokes, but they’re pretty bad. Sam found he can breed better jokes using ideas from evolutionary computing—with pretty decent results!

Our first talk tonight is from PyDatalondon founder @ianozsvald.bsky.social on his playgroup: a collaborative space to explore really difficult but interesting problems together like ARC AGI, diagnosing bugs agenically and making LLMs funny.

From small beginnings to great things! @emlynclay.bsky.social tells us the history of PyData London.

It’s finally time! 🥳 PyData London 100 is here! 💯

It’s nearly time for our 100th Meetup! 🥳

Looking forward to a full roster of lightning talks, reflections from organisers past and present (including many of the OG crew!) and of course well-deserved celebrations--maybe even with cake! 🎂

YouTube video by CultRepo Python: The Documentary | An origin story

Python: The Documentary | An origin story

What began as a side project in the 1990s now powers AI, data science and some of the world's biggest companies. But Python almost disappeared at one point.

Featuring Guido van Rossum, Travis Oliphant, Barry Warsaw, and many more!

youtu.be/GfH4QL4VqJ0?...

Craig's slides on breaking blackbox evals for AI agents

github.com/Python-Test-...

Unsupported client – Canva Unsupported client – Canva

Slides for Imamuddin Shaik's talk on context engineering.

www.canva.com/design/DAGxx...

Thanks for sharing!

Skrub: machine-learning with dataframes

Presentation at @pydatalondon.bsky.social, discussing how skrub facilitates data transformations & wrangling on dataframes for machine learning
and introducing the exciting "DataOps" to tune and re-apply any wrangling code
speakerdeck.com/gaelvaroquau...

You don’t need a degree to get into data science: apprenticeships are also great.

And there are many benefits. Empowered and loyal, apprentices drive plenty of fresh thinking with real world impact: 87% of employers say apprentices boost team innovation.

Last but definitely not least we have Ruby Waller on Apprenticeships in Data: a practical pathway into the profession.

There are many unresolved problems with agents.

Context engineering helps. Designing the entire informational environment not just the prompt so the model can "plausibly" complete the task.

Our first lightning talk from Imamuddin Shaik on Reliable Agents: Context Engineering, Roles, and What 1M-Token Windows Don’t Fix.

One surprisingly effective way to evaluate outputs is using an LLM as a judge.

Observability is key. Focus on process not tools.

Why use evals?

Ensure TRUST and CAPABILITIES of our AGENTS so that somebody will pay for them.

Next up we have Craig West on Breaking the Black Box — evaluating AI agents!

It looks like a date frame, but Skrub stores the whole transformation pipeline in the magic skb attribute!

@skrub-data.bsky.social DataOps lets you wrap your pandas (or other!) data wrangling code as sklearn transforms that can now be transferred to production.

And we can also cross validate and optimise our data wrangling!

@skrub-data.bsky.social’s text encoders find latent categories for you. It has several different text encoders depending on accuracy / fit time trade off you want. Or it will choose the best for you!

Our first talk tonight is from @gaelvaroquaux.bsky.social on @skrub-data.bsky.social.

Real tables are too messy for sklearn - skrub preprocesses them for you.

Excited to kick off PyData London 99 with an amazing lineup tonight!

YouTube video by PyData Keynote- Tony Mears | PyData London 25

PyData London 2025 keynote: Tony Mears -- Innovation is Dead

Innovation gets stifled in the public sector by risk aversion and punishment for failure.

But there is hope: Tony shares a way forward, drawing on his experience directing operations in the NHS and UK Space Agency.

youtu.be/XMLbJYM46xo

We also have two great lightning talks lined up

From RNNs to Reliable Agents: Context Engineering, Roles, and What 1M-Token Windows Don’t Fix - Imamuddin Shaik

The Apprenticeship Pathway Into Data Science - Ruby Waller

Update: Victor can't make it so we're excited to hear from Craig West on "Breaking the Black Box - How to Evaluate Your Agents... in Real Time Too!'

With LLMs, high quality evaluations are amongst the most impactful things you can do. Craig looks at deterministic, human and LLM as Judge strategies.

PyData London - 99th Meetup, Tue, Sep 2, 2025, 7:00 PM | 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 **[Nu

Join us at the 99th PyData London Meetup — with a talk from a genuine PyData celebrity! 🤩

Tue 2 September 19:00

Skrub: machine-learning with dataframes — @gaelvaroquaux.bsky.social

Model Context Protocol: is refactoring tool calls worth your time? — Victor Zommers

meetu.ps/e/Pt20x/5p7c...