PyData Manchester

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.

Eventbrite link

DO NOT SIGN UP ON MEETUP!!

Official Description

HER+Data MCR is a community working to connect, inspire, support and empower the NW UK’s Women in Data. Our goal is to bring together women who work in data or who would like to work in data - to support one another, share experiences and talk data - big or small! Whether you’re a student just embarking on a career or a seasoned data professional, this group is for you. We want to connect and inspire amazing data women with diverse expertise and experience.

For our August 2023 event, our friends Code and Stuff, Open Data Manchester, PyData MCR, and R-Ladies Manchester will join us to host a Manchester Data [and Tech] Community Summer Social to bring everyone together again and hear more about each of these groups and their activities. So please register to come along to connect and network with others in the Manchester data/tech community - everyone welcome!

The venue, food and drinks are very generously provided by Infinity Works. The event will take place at their Manchester hub: 5th Floor, No.2 Circle Square, 1 Symphony Park, Manchester, M1 7FS.

Code and Stuff are a coding and networking community for women and non-binary developers and code newbies in Manchester, with bi-weekly events. We believe that diversity in tech is really important and to balance the scale we are building a collaborative agile learning community to support more women and non-binary people getting into tech. Our ambition is to show women and non-binary developers and code newbies that anything is possible - and that with a bit of help and confidence they can realise their potential and enjoy a thriving career in tech.

Open Data Manchester is a not-for-profit formed from a diverse group of open data advocates in 2010 that supports organisations to release data and helps people use it. We bring people together to share expertise and ideas, and think more about how we might use data to make Greater Manchester a better place to live. We run events, training and workshops, do research and create new projects that get the community involved, all designed to help more people understand data.

PyData MCR is the Manchester chapter of the International PyData Community. For Manchester based data people, to share and learn new things. All open data tooling welcome, we are not python focused.

R-Ladies Manchester are part of the global network of R-Ladies Meet-ups whose mission is to promote gender diversity within the R User community. Whilst we’ve been on hiatus over the course of the pandemic we have two fabulous new organisers, Zoe and Jasmine, joining Ellen to pick up the reigns and get events happening once again. When we are able to meet, we welcome anything and everything R related and have previously hosted show and tell presentations, networking events, coding surgeries and social quizzes. We’re really looking forward to coming back and seeing what everyone’s been working on – please reach out if you’ve been doing anything amazing or want to know more!

Is your data/tech meetup community interested in joining us? Please email herplusdatamcr@gmail.com to get involved with this event!

By registering for this event, you agree to abide by our Code of Conduct.