PyDataMCR August

PyDataMCR August Talks

THE TALKS

Pydantic: Too young to learn C, too old to learn Rust, just in time for LLMs - Pantelis Hadjipantelis (he/him)

When working with Large Language Models (LLMs), how do we ensure a probabilistic blob of text is something our code can actually use? In this talk, we explore how Pydantic emerged at a perfect moment exactly for this task; bridging Python's flexibility with the structured data needs of modern AI applications. We will introduce Pydantic and then demonstrate practical applications of it; from prompt engineering and parsing responses, to example of robust function calling and tool chaining via APIs.

Pantelis is an ML Scientist whose journey spans applied statistics, biostatistics, quantitative analysis, and data science consulting. In his free time, he thinks the Internet is (still) wrong, so he spends his time answering modelling assumptions online. In his work, he uses Pydantic to bring type safety and validation discipline to real-world ML pipelines, especially when working with LLMs that like to get creative.

Lies, damn lies, and statistics in social deduction games - Grace Wilding (they/she)

Focusing on the game Mafia, this talk explores some common methods relied upon by players to solve the game. Is the first player to reach 3 votes really mafia? Can you really find mafia off voting patterns alone? And when you apply these methods in a game, how accurate are they in finding a wolf?

Inspired by a desire to prove players on their homesite that people place too much faith in these methods, examples of how these methods have been applied in past games will be unpacked, and whether these principles should really be relied upon.

After all, it is a social deduction game for a reason – statistics can only get you so far.

Grace has been a forum mafia player since January 2024, and a lifelong data nerd. Outside of mafia, she has experience in data science and data analysis before switching to data engineering. They currently work as the Data Solutions Lead at Beever and Struthers in Manchester.

LOCATION
We'll be at Krakenflex, who are also kindly supplying catering. The capacity is limited to 90.

After the talks we'll all head somewhere local for some post-event socialising.

EVENT GUIDELINES
PyDataMCR is a strictly professional event, as such professional behaviour is expected.

PyDataMCR is a chapter of PyData, an educational program of NumFOCUS and thus abides by the NumFOCUS Code of Conduct

https://pydata.org/code-of-conduct.html

Please take a moment to familiarise yourself with its contents.

ACCESSIBILITY
Under 16s welcome with a responsible guardian. There is a quiet room available if needed. Toilets are accessible.

SPONSORS
Thank you to NUMFocus for sponsoring Meetup and further support.
Thank you to Autotrader, Krakenflex and Horsefly Analytics for their ongoing support and sponsorship of PyDataMCR.