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, Cookpad, for supplying the venue, Adlib for the scrumptious pizza, and thirst-quenching refreshments, along with additional sponsorship.

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

📚 Three 25-minute talks:

• Talk 1: Open Sourcing AutoML - Greg Michaelson
• Talk 2: Building online learners with RiverML - Anna Andersson
• Talk 3: Cooking up a new search system: Inside recipe search at Cookpad - Matt Williams

📢 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. Open Sourcing AutoML - Greg Michaelson

When AutoML was popularised, there was a great hope that the citizen data scientist would take over machine learning and that business analysts everywhere would soon be building thousands of advanced AI-based solutions, ushering in the age of AI in business. Not only did that not happen, but even the name “AutoML” has become sullied along with the myth of the citizen data scientist. In this talk, Greg will discuss the launch of a brand new open source project that promises to deliver AutoML as it should have been: open, flexible, code-based, and targeted at the only people generating value from machine learning — data science experts.

# 2. Building online learners with RiverML - Anna Andersson

Anna found themselves working on a project with very little data available for training. As the anticipated data was going to be a stream, one of the approaches they explored was to build an online learner or stream learner that would give the models a chance to improve as they were exposed to data from the actual process. Building the online learner models, they had to take a different approach to my entire workflow. Here, they will share what they learnt about working with models that improve over time, how to evaluate them, deal with drift and how to use multi-armed bandits for model selection.

3. Cooking up a new search system: Inside recipe search at Cookpad - Matt Williams

Cookpad's recipe search helps cooks everywhere find tasty dishes to cook within an ever-growing catalogue of six million recipes created by everyday cooks. As a global recipe search with over 40m monthly users – optimising search quality is a critical and challenging task. Over the course of 2 years, the team embarked on a technological and cultural transition, with the aim of giving engineers greater ownership of the search experience. This included a shift to a Python-based stack and a data-driven approach to experimentation. This talk will give a brief intro to search relevance, and cover Cookpad Global's search journey, along with the trials, tribulations, and successes along the way.

🕖 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).