Join us once again for the next PyData Bristol Meetup!
The PyData community in Bristol continues to thrive with engaging talks, insightful lightning sessions, and lively networking. A massive thank you to our generous hosts, Amdaris, for supplying the venue, Adlib for the scrumptious pizza, and thirst-quenching refreshments, along with additional sponsorship.
Amdaris is our new host!!! Whoop whopp! Happy and excited for a new beginning :)
Sadly we say goodbye to our regular and always open host Cookpad. Thank you for hosting us for almost a year and supplying us with a good atmosphere and good vibe place.

Agenda for the evening:
🚪 6:00 pm - Doors open
🕡 6:30 pm - Talks commence (sharp!)

📚 Two 25-minute talks:

• Talk 1: Natural Language Processing - from Academic Theory to Business Application - Panashe Jerry Mundondo
• Talk 2: Slient Intrusion - How LLM Infiltrating Enterprises - Manish Sharma

📚 Two 10-minute lightning talks:

• TBD
• TBD

📢 Community announcements
🤝 Relaxed networking over beers and soft drinks

Interested in sharing your knowledge or experience at this or a future event? Fill out this form to submit your talk proposal: https://goo.gl/forms/8lsz1WA1986Ahbbs1
We look forward to seeing you there for another fantastic evening of Python, Data Science, and camaraderie!

Talks

1. Natural Language Processing - from Academic Theory to Business Application - Panashe Jerry Mundondo

This talk will centre around the contrast between academic data science, as experienced during my MSc in Data Science & AI, and the adaptability required in real-world data scenarios.
Using an NLP tool I developed for Fourth Floor Creative (a video game marketing company) as a case study, I will discuss the challenges in adapting from data science in theory, to the creativity and solution-oriented approach needed in the real world.
The aim of the NLP tool was to evaluate both sentiment and semantic themes in customer comments about specific video games. Initial attempts using off-the-shelf models like TextBlob and Bert were not accurate enough due to the unique language in the gaming domain.
Holding onto my academic mindset, I contemplated creating a bespoke sentiment classifier, only to discover the lack of clean, labelled data specific to my domain—a stark contrast to academic settings. My next step was to ask colleagues at my workplace to label some data, but as they are not data scientists they did not understand the aim and importance of this leading to poorly labelled data.
Ultimately, rather than building a tool from scratch, the solution lay in fine-tuning existing models from Hugging Face, augmenting data with synthetic inputs from LLMs, and capitalising on few-shot classification to address data limitations.
I believe that early-career data-scientists will benefit from this talk. It provides insights into the practical application of data science and NLP in a business context, highlighting the emphasis on speed and efficiency, as opposed to the academic focus on achieving the highest accuracy in a model.

# 2. Slient Intrusion - How LLM Infiltrating Enterprises - Manish Sharma

This talk tries to cover the how LLM are becoming need of enterprise but really are enterprises ready for it.

Lightning Talks

# 1. TBD

# 2. TBD

🕖 LOGISTICS
Talks kick off at 18:30 sharp; then networking in The Knights Templar from 20:40.
If you realise you can't make it, please un-RSVP in good time to free up your place for your fellow community members.
Follow @pydatabristol (https://twitter.com/pydatabristol) for updates on this and future events, as well as news from the global PyData community.

📜 CODE OF CONDUCT
The PyData Code of Conduct governs this meetup (https://pydata.org/code-of-conduct/). To discuss any issues or concerns relating to the code of conduct or behaviour of anyone at the PyData meetup, please contact the PyData Bristol organisers, or you can submit a report of any potential Code of Conduct violation directly to NumFOCUS (https://numfocus.typeform.com/to/ynjGdT).