Conference Schedule

View past PyData event schedules here.

Tutorial Sessions — Friday July 12, 2019

  Tower Suite 1 Tower Suite 2 Tower Suite 3
8:00

Registration

9:00 Build and Deploy an End-to-end Streaming NLP Insights System Michal Mucha Maintainable Code in Data Science Kevin Lemagnen Data Analysis in Parallel Filip Ter
10:30

Break & Snacks

11:00 A Deep Dive into NLP with PyTorch Jeffrey Hsu, Susannah Klanecek Advanced Software Testing for Data Scientists Raoul-Gabriel Urma, Kevin Lemagnen Mastering Gradient Boosting with CatBoost Anna Veronika Dorogush
12:30

Lunch

13:30 Choosing the right neural generative model for your problem Dr Egor Kraev Fundamentals of image classification using PyTorch Jonathan Fernandes An Introduction to Markov chain Monte Carlo using PyMC3 Chris Fonnesbeck
15:00

Break & Snacks

15:30 Training intelligent game agents using deep reinforcement learning Imran Rashid AB-testing by clusters Bertil Hatt, João Martins A gentle introduction to Pandas timeseries and Seaborn Ian Ozsvald
17:00

General Sessions — Saturday July 13, 2019

  Tower Suite 1 Tower Suite 2 Tower Suite 3 Mortimer Room
8:00

Registration

9:00

Opening Notes

9:15 The Turing Way: A how to guide for reproducible research Kirstie Whitaker
10:00

Break & Snacks

10:15 A practical guide towards algorithmic bias and explainability in machine learning Alejandro Saucedo Data Science for Dinner: Recommending Recipes Irene Iriarte Carretero Modelling the subsurface with gamma rays and machine learning Connor Tann

Unconference

11:00 Because You Can Run, You Can't Hide: Some Musings on API Design James Powell I am telling you 3 things about Chatbot (so you don't have to learn it the hard way) Cheuk Ting Ho Active learning in the interactive python environment Jan Freyberg

Unconference

11:45 How am I going to deal with all of these cats? Liam Kirwin Embeddings! Embeddings everywhere! - How to build a recommender system using representation learning Maciej Arciuch, Karol Grzegorczyk Testing and Validating Machine Learning Models when Deploying to Production Christopher Samiullah, Soledad Galli Executives at PyData Ian Ozsvald, James Powell
12:30

Lunch
(Diversity Lunch in the lunch seating area, the Carvery)

13:30 You got served: How Deliveroo improved the ranking of restaurants Jonny Brooks-Bartlett Productionising Data Science at Scale Trevor Sidery, Guillermo Barquero On the Path to Causal Inference Mark Farragher Democracy Hackathon John Sandall, Richard Chadwick
14:15 Prophet at Scale: Using Prophet at scale to tune and forecast time series at Spotify Mahan Hosseinzadeh What Failure Taught Me About Building High-Stakes Models That Actually Work Jake Coltman, Understanding exchange network dynamics with Python Omer Yuksel
15:00 Modern Data Science: A new approach to DataFrames and pipelines Maarten Breddels, Jovan Veljanoski Image search without image captions Harrison Pim How to Validate Your Client Churn Model Elena Sharova
15:45

Break & Snacks

16:00 Bridging health inequalities through machine learning Elina Naydenova
16:45

Lightning Talks & Closing Notes

17:45

PyData Social

Reception and Pub Quiz (Exhibition foyer)

21:00

General Sessions — Sunday July 14, 2019

  Tower Suite 1 Tower Suite 2 Tower Suite 3 Mortimer Room
8:00

Registration

9:00

Opening Notes

9:15 Goofing Off with Fun (Big) Data Lynn Cherny
10:00

Break & Snacks

10:15 Combining Computer Vision and NLP for Multi-Task Fashion Attribute Modeling at Shoprunner Michael Sugimura Quantamental Investing - the future of finance Fabian Krause Interpretable AI or How I Learned to Stop Worrying and Trust AI Ajay Thampi, Text annotation role playing workshop (Interactive workshop for unconference) Lev Konstantinovskiy, Agata Sumowska, Bhargav Srinivasa Desikan, Michał Łopuszyński, w4rner
11:00 The unreasonable effectiveness of feature hashing Gianluca Campanella A Primer (or Refresher) On Linear Algebra for Data Science Ruben van de Geer Understanding of distributed processing in Python Chie Hayashida

How to make your first open source contribution

Cheuk Ting Ho

11:45 Kafka in Finance: processing >1 Billion market data messages a day Matthew Hertz, Alla Maher How to Constrain Artificial Stupidity. Vincent Warmerdam Weak supervision: a new paradigm for unreliable labels Eddie Bell

How to make Python Packages

Michal Mazurek and Igor Gotibovych

12:30

Lunch
(PyData Organisers Lunch in the lunch seating area, the Carvery)

13:30 Safer Cycling with an Edge TPU watching your back Zack Akil Data science and Internet of Things on the edge Mario Bonamigo Just ask: designing intent-driven algos Anna Schneider

Facilitated discussion on practical implementation of ethical data science

Anthony Woolcock

14:15 Data Science Frameworks and Managed Services: When to Avoid the Shiny New Toys Jon Tutcher From healthcare.hospital import datascience Pavlos Papaconstadopoulos, Patrick Gonzalez Knowledge graphs --enter--> the Hype Cycle George Cushen

Chatbots that know if you are angry

Cheuk Ting Ho

15:00 Deep Learning and Time Series Forecasting for Smarter Energy Igor Gotlibovych The anatomy of a #deepfake Eric Drass aka shardcore How good is your prediction? - Quantifying uncertainty in Machine Learning predictions Maria Navarro

Unconference

15:45

Break & Snacks

16:00 One step forward, two steps back: the frustration of diversity efforts in STEM Lorena A. Barba
16:45

Lightning Talks & Closing Notes

18:00

Subscribe to Receive PyData Updates