talk-data.com

Venue: Carnival House, 100 Harbour Parade, Southampton, SO15 1ST 📢 Want to speak 📢: submit your talk proposal

Main Talks 1️⃣ Searching for Shady Patterns: Shining a light on UK corporate ownership - Adam Hill In June 2016 the UK government launched the world’s first “beneficial ownership” register; a requirement for all UK companies to register who were the “persons of significant control”, PSCs, who actually controlled the company. Recent investigative journalism has made headlines with the leaking of the Panama and Paradise papers and it is clear that transparency in corporate ownership needs to be a significant factor within modern democracy. In a partnership between DataKind UK and Global Witness we have built the worlds first network graph mapping all of the UK public data on those who control corporate interests in the UK; it comprises in excess of 4.5 million companies and 4 million individual people. It has been enriched with company officer data and metrics of financial secrecy based upon geographic regions.

The goal of the project was to enable Global Witness to search for "shady patterns" within corporate ownership networks to act as leads for investigative journalism to expose corrupt practices. Further more, we were able to analyse the completeness of the register and identify ways of improving such data structures to inform other world governments how to best build similar public registers of corporate ownership.

We present here how we built this amazing data structure using Python tools for cleaning and data processing and a Neo4j graph database storing the network graph itself. In addition, we share the first insights derived from this process.

2️⃣ 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 ⚡ ⚡1️⃣ TBA ⚡2️⃣ TBA

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. You MUST use your initial/first name and surname on your meetup profile, otherwise, you will NOT make it on the guest list! 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event.

If your RSVP status says "You're going" you will be able to get in. No further confirmation required. You will NOT need to show your RSVP confirmation when signing in. If you can no longer make it, please unRSVP as soon as you know so we can assign your place to someone on the waiting list.

*** Code of Conduct: This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct. *** There will be pizza & drinks, generously provided by our host, Carnival UK. ***

Logistics Doors open at 6.30 pm, talks start at 7 pm. For those who wish to continue networking and chatting we will move to a nearby pub/bar for drinks from 9 pm.

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!

Follow @pydatasoton (https://twitter.com/pydatasoton) for updates and early announcements. We are also on Instagram/Threads as @pydatasoton, and find us on LinkedIn.

Venue: Carnival House, 100 Harbour Parade, Southampton, SO15 1ST 📢 Want to speak 📢: submit your talk proposal

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. You MUST use your initial/first name and surname on your meetup profile, otherwise, you will NOT make it on the guest list! 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event.

If your RSVP status says "You're going" you will be able to get in. No further confirmation required. You will NOT need to show your RSVP confirmation when signing in. If you can no longer make it, please unRSVP as soon as you know so we can assign your place to someone on the waiting list.

*** Code of Conduct: This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct. *** There will be pizza & drinks, generously provided by our host, Carnival UK. ***

Mastering Data Flow: Prefect Pipelines Workshop - Adam Hill & Chris Frohmaier Join us for an engaging workshop where we'll dive deep into the world of data engineering with Prefect 3. Throughout the session, participants will explore the following key topics:

• Overview of Prefect and its core features
• Understanding the Prefect ecosystem and its integration with popular data science tools
• Setting up a Prefect environment: Installation, configuration, and project setup

Building Data Pipelines:

• Data ingestion: Fetching data from various sources including RSS feeds, APIs, and databases
• Data transformation and manipulation using Prefect tasks and flows
• Data storage and persistence: Storing processed data into local databases such as MongoDB or SQL
• Integrating machine learning models for advanced data processing and analysis within Prefect workflows

Advanced Techniques and Best Practices:

• Implementing error handling and retry strategies for fault tolerance and reliability
• Exploring Prefect's advanced features such as parallel execution, versioning, and dependency management

By the end of the workshop, attendees will have gained a comprehensive understanding of Prefect 3 and its capabilities, empowering them to design, execute, and optimise data pipelines efficiently in real-world scenarios.

We invite you to join us on this exciting journey of mastering data flows with Prefect!

Instructions to prepare in advance Workshop Materials and Requirements: In advance of the workshop please visit the github repo here: https://github.com/Cadarn/PyData-Prefect-Workshop. Clone a copy of the repository and follow the setup instructions in the README file including:

• Setting up a new Python environment with all the required modules
• Installing Docker and Docker Compose if necessary and then running the docker compose file so that local copies of the software images are downloaded in advance.
• Create a free MongoDB Atlas account and setup a project/database for the workshop

Please follow the instructions in advance of attending the workshop/

Please note this is a practical session and you will need to bring your own laptop. We recommend you bring it fully charged, if you can, as there may not be enough plug sockets for everyone to use at the same time.

Logistics Doors open at 6.30 pm, talks start at 7 pm. For those who wish to continue networking and chatting we will move to a nearby pub/bar for drinks from 9 pm.

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!

Follow @pydatasoton (https://twitter.com/pydatasoton) for updates and early announcements. We are also on Instagram/Threads as @pydatasoton; and find us on LinkedIn.

Venue: Carnival House, 100 Harbour Parade, Southampton, SO15 1ST 📢 Want to speak 📢: submit your talk proposal

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. You MUST use your initial/first name and surname on your meetup profile, otherwise, you will NOT make it on the guest list! 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event.

If your RSVP status says "You're going" you will be able to get in. No further confirmation required. You will NOT need to show your RSVP confirmation when signing in. If you can no longer make it, please unRSVP as soon as you know so we can assign your place to someone on the waiting list.

*** Code of Conduct: This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct. *** There will be pizza & drinks, generously provided by our host, Carnival UK. ***

Main Talks 1️⃣ Kafka Kickstart: Simplifying Messaging Queues with Python and Upstash - Adam Hill Discover the power of Kafka messaging queues in a beginner-friendly session designed to demystify this robust data streaming platform. Join us at the next PyData Southampton meetup as we delve into the fundamentals of Kafka, all through the approachable lens of Python. You'll learn:

• The core concepts of Kafka, including producers, consumers, and topics.
• How to leverage Upstash, a cloud service with a free-tier Kafka setup, perfect for experiments and prototyping.
• Practical insights through a live demo, showcasing how to publish and consume event data with ease.

We'll also explore real-world applications of Kafka to illustrate how it can solve complex data streaming challenges across various industries. Whether you're new to Kafka or looking to solidify your understanding, this talk will equip you with the foundational knowledge and hands-on experience to start incorporating Kafka into your projects.

2️⃣ Appeasing fandoms by dissecting books for RAG with Google Gemini - Lisa Carpenter Where are all the passages that prove my theory that in the next book the hero will finally achieve the goal? Let's explore how RAG will help us retrieve information from our favourite books to prove our theories!

Lightning Talks ⚡ ⚡1️⃣ Freelancing: a quick guide - Robin Wilson ⚡2️⃣ TBA

Logistics Doors open at 6.30 pm, talks start at 7 pm. For those who wish to continue networking and chatting we will move to a nearby pub/bar for drinks from 9 pm.

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!

Follow @pydatasoton (https://twitter.com/pydatasoton) for updates and early announcements. We are also on Instagram/Threads as @pydatasoton; and find us on LinkedIn.

Venue: Carnival House, 100 Harbour Parade, Southampton, SO15 1ST

Please note:

1. 🚨🚨🚨A valid photo ID is required by building security. You MUST use your initial/first name and surname on your meetup profile, otherwise, you will NOT make it on the guest list! 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event.

If your RSVP status says "You're going" you will be able to get in. No further confirmation required. You will NOT need to show your RSVP confirmation when signing in. If you can no longer make it, please unRSVP as soon as you know so we can assign your place to someone on the waiting list.

*** Code of Conduct: This event follows the NumFOCUS Code of Conduct, please familiarise yourself with it before the event. Please get in touch with the organisers with any questions or concerns regarding the Code of Conduct. *** There will be pizza & drinks, generously provided by our host, Carnival UK. ***

Main Talks 1️⃣ OpenAI's Function Calling: What is it and how can we take advantage of it? - Anoop Tatti Imagine if ChatGPT could seamlessly schedule meetings, offer real-time public transport updates or provide current weather information. Well, thanks to OpenAI's 'Function Calling' feature, all of this is possible.

Here's how Function Calling works: We define available functions and train the OpenAI model to recognise user intent. When a user asks a question or makes a request, the model identifies their intention and matches it to the appropriate function. The system then executes the function, producing raw output, which is transformed into a user-friendly natural language response by the model. This session explores Function Calling through practical examples, including a 'Digital Personal Assistant' for calendar and task retrieval and a chatbot providing real-time TfL (Transport for London) underground train information. Demonstrations will take place in Teams and on SharePoint pages, providing attendees with a solid understanding of Function Calling.

2️⃣ Building a data science solution for an NGO when you don’t know what infrastructure it will run on: a case study predicting tutor supply and demand mismatch - Adam Hill The Brilliant Club is an NGO focused on two goals: student access and student success. TBC wants more pupils from less advantaged backgrounds to access university; their aim is to work with 100,000 pupils on their flagship Scholars Programme over the next five years. To achieve these aims, TBC needs to ensure that they have the right number of PhD researcher volunteers in the right areas to meet school demand.

A team of 6 DataKind volunteers worked to explore the data, and make a maintainable, functional set of models that could help in the prediction of TBC’s tutor supply and demand using the latest available data and visualising it in an easy-to-use manner. We built our solution around various open-source tools and technologies including: Python; Scikit-learn; Jupyter; Docker; PostgreSQL; dbt; Prefect. In this talk, we will discuss how we designed the solution to deliver it in an accessible way and demonstrate how we implemented the various technologies.

Lightning Talks ⚡ ⚡1️⃣ Cruising Through Soton: Optimising Your Journey for a Satisfyingly Speedier Commute - Austen Wallis ⚡2️⃣ TBA

Logistics Doors open at 6.30 pm, talks start at 7 pm. For those who wish to continue networking and chatting we will move to a nearby pub/bar for drinks from 9 pm.

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!

Follow @pydatasoton (https://twitter.com/pydatasoton) for updates and early announcements. We are also on Instagram/Threads as @pydatasoton; and find us on LinkedIn.