Schedule

Saturday, November 7th

Time (UTC)	Major Events
	Humble Data Workshop - Session 1
	Humble Data Workshop - Session 2

Wednesday, November 11th

Time (UTC)	Major Events	Extracurriculars	Sponsor Events	Talk Watch Parties (Room 1)	Talk Watch Parties (Room 2)
	Talks released
				Quickly deploying explainable AI dashboards
				Is a neural network better than Ash at detecting Team Rocket? If so, how?
				TimeSeries Forecasting with ML Algorithms and there comparisons
				Visions: An Open-Source Library for Semantic Data
				Autonomous Vehicles See More With Thermal Imaging: Multi-modal thin cross section Object Detection
	Track Q&A Panel: Data Visualization and Interpretability #1			Accelerating Differential Equations in R and Python using Julia’s SciML Ecosystem
				An introduction to DataFrames.jl for pandas users
	Tutorial Office Hours, Solving large-scale inverse problems in Python with PyLops
			Neo4j: Graph databases for machine learning (Sponsor talk room #1)
				Why I didn’t use deep learning for my image recognition problem
			Neo4j: Graph databases for machine learning (Sponsor talk room #1)
				Feature drift monitoring as a service for machine learning models at scale
					Quickly deploying explainable AI dashboards
	Track Q&A Panel: Julia For Python & Julia Users			DevOps for science: using continuous integration for rigorous and reproducible analysis
					Is a neural network better than Ash at detecting Team Rocket? If so, how?
				Skinny Pandas Riding on a Rocket
					TimeSeries Forecasting with ML Algorithms and there comparisons
				Using Algorithm X to re-analyse the last UK general election
			Neo4j: Graph databases for machine learning (Sponsor talk room #1)
					Visions: An Open-Source Library for Semantic Data
				Taking Care of Parameters So You Don’t Have to with ParamTools
					Autonomous Vehicles See More With Thermal Imaging: Multi-modal thin cross section Object Detection
	Keynote Watch Party: Is Coding Science? An interview with Wolfgang Kerzendorf			FlyBrainLab: An Interactive Open Computing Platform for Exploring the Drosophila Brain
					Accelerating Differential Equations in R and Python using Julia’s SciML Ecosystem
				Ensemble-X: Your personal strataGEM to build Ensembled Deep Learning Models for Medical Imaging
	Short Talks Watch Party #1
					An introduction to DataFrames.jl for pandas users
					Why I didn’t use deep learning for my image recognition problem
					Feature drift monitoring as a service for machine learning models at scale
	Keynote Fireside Chat with Wolfgang Kerzendorf and Jane Herriman
					DevOps for science: using continuous integration for rigorous and reproducible analysis
		Poster Session
					Skinny Pandas Riding on a Rocket
	Track Q&A Panel: Lessons from Industry #1				Using Algorithm X to re-analyse the last UK general election
					Taking Care of Parameters So You Don’t Have to with ParamTools
	Tutorial Office Hours, Probability Calibration: Latest Techniques
			MetroStar Systems: Distributed Model Scoring with BERT (Sponsor talk room #1)
					FlyBrainLab: An Interactive Open Computing Platform for Exploring the Drosophila Brain
			IBM: AutoML with IBM (Sponsor talk room #2)
					Ensemble-X: Your personal strataGEM to build Ensembled Deep Learning Models for Medical Imaging

Thursday, November 12th

Time (UTC)	Major Events	Extracurriculars		Sponsor Events	Talk Watch Parties (Room 1)	Talk Watch Parties (Room 2)
	Talks released
					ipywidgets for Education! Using Jupyter tools to make Math Visualization applets for the classroom
					COVID-19 Visualizations, the Good, the Bad and the Malicious
	Tutorial Office Hours, Computer shows why: Visualizing deep learning for fun and profit
				OVHcloud: Accelerate the data-science journey with AI Training (Sponsor talk room #1)
					Opening the Black Box
		Supply Chain Bot Tournament kick-off (Unconference Room)
					Uncertainty Quantification for Online Learning via Hierarchical Incremental Gradient Descent
	Track Q&A Panel: Open Science #1	TerminusDB Sprint and VolEsti Sprint			What cyber security can teach us about COVID-19 testing
					ML-Based Time Series Regression: 10 concepts we learned from Demand Forecasting	ipywidgets for Education! Using Jupyter tools to make Math Visualization applets for the classroom
	Short Talks Watch Party #2				Basic Pitfalls in Waveform Analysis	COVID-19 Visualizations, the Good, the Bad and the Malicious
				Neo4j: Getting started with graph databases (Sponsor Talk Room #1)	Entity matching at scale	Opening the Black Box
				Mozn: Focal: Using Natural Language Processing (NLP) for sanctions screening. (Sponsor Talk Room #1)
					Building a Successful Data Science Team	Uncertainty Quantification for Online Learning via Hierarchical Incremental Gradient Descent
				Neo4j: Getting up and running with Graph Data Science Library (Sponsor Talk Room #2)
					The Big Benefits of Small Data	What cyber security can teach us about COVID-19 testing
				When Data Science goes Enterprise: Inside views of Blue Yonder (Sponsor Talk Room #2)
					Monitoring machine learning models in production	ML-Based Time Series Regression: 10 concepts we learned from Demand Forecasting
				Neo4j: Getting started with graph databases (Sponsor Talk Room #1)
					Better Code for Data Science	Basic Pitfalls in Waveform Analysis
				Neo4j: Getting up and running with Graph Data Science Library (Sponsor Talk Room #1)
			Kedro Sprint and Napari Sprint		Thrifty Machine Learning	Entity matching at scale
					Leveraging python and open-source for data-science on the buy-side.	Building a Successful Data Science Team
				Apple: What is coremltools? (Sponsor Talk Room #1)
		Poster Session				The Big Benefits of Small Data
						Monitoring machine learning models in production
	Tutorial Office Hours, Panel: Dashboards for PyData					Better Code for Data Science
						Thrifty Machine Learning
						Leveraging python and open-source for data-science on the buy-side.
	Track Q&A Panel: Data Visualization and Interpretability #2

Friday, November 13th

Time (UTC)	Major Events	Extracurriculars	Sponsor Events	Talk Watch Parties (Room 1)	Talk Watch Parties (Room 2)	Unconference
	Talks released					Sign up for an unconference slot
	Track Q&A Panel: Causal and Statistical Methods #1			Climate Change: analyzing remote sensing data with Python
				Using EOLearn to build a machine learning pipeline to detect plastics in the ocean.
	Tutorial Office Hours, Beautiful (ML) Data: Patterns & Best Practice for effective Data solutions with PyTorch
				Cardinal: A metrics based Active Learning framework
				Streamlit: The Fastest Way to build Data Apps
	Track Q&A Panel: Lessons from Industry #2			Data processing pipelines for Small Big Data
				Transformation from Research Oriented Code into Machine Learning APIs with Python	Climate Change: analyzing remote sensing data with Python
				How to review a model	Using EOLearn to build a machine learning pipeline to detect plastics in the ocean.
			Elm: From Documents to Traffic Enforcement: Applying an object detection framework with YOLOV5/PyTorch (Sponsor Talk Room #1)	Speed Up Your Data Processing: Parallel and Asynchronous Programming in Data Science	Cardinal: A metrics based Active Learning framework
		Executives at PyData		Snap ML: Accelerated, Accurate, Efficient Machine Learning	Streamlit: The Fastest Way to build Data Apps
			Neo4j: A NetworkX vs Neo4j drag race (Sponsor Talk Room #1)
			Quansight: QHub Demonstration (Sponsor Talk Room #2)	Parallel processing in Python: The current landscape	Data processing pipelines for Small Big Data
	Short Talks Watch Party #3					Ask Me Anything about Non-English NLP Tools\/Embeddings
			Dataiku: An Introduction to Dataiku (Sponsor Talk Room #1)
				Visual data: abundant, relevant, labelled, cheap. Pick two?	Transformation from Research Oriented Code into Machine Learning APIs with Python
				pandas.(to/from)_sql is simple but not fast	How to review a model
	Keynote Watch Party: Multi-Label Classification with Human Rights Data, by Maria Gargiulo and Megan Price, PhD
		Flow Forecast Sprint and SKtime Sprint		pyodide: scientific Python compiled to WebAssembly	Speed Up Your Data Processing: Parallel and Asynchronous Programming in Data Science
	Keynote Fireside Chat with Maria Gargiulo and Megan Price, PhD
				Dirty Data science: machine-learning on non-curated data	Snap ML: Accelerated, Accurate, Efficient Machine Learning
				What’s new in pandas?	Parallel processing in Python: The current landscape
	Track Q&A Panel: Data Science in Production #1
				Growing Machine Learning Platforms in the Enterprise	Visual data: abundant, relevant, labelled, cheap. Pick two?
	Live Tutorial, Why and What If – Causal Analysis for Everyone				pandas.(to/from)_sql is simple but not fast
					pyodide: scientific Python compiled to WebAssembly
					Dirty Data science: machine-learning on non-curated data
	Track Q&A Panel: Open Science #2
					What’s new in pandas?
		Hypothesis Sprint (Continues below)			Growing Machine Learning Platforms in the Enterprise

Saturday, November 14th

Time (UTC)	Major Events		Extracurriculars		Talk Watch Parties (Room 1)	Talk Watch Rooms (Room 2)	Unconference
			Hypothesis Sprint				Sign up for an unconference slot
	Talks released
	Track Q&A Panel: Miscellaneous #1				Taking a Close Look in the Mirror: Data Literacy for Data Experts
			Lightning Talks #1				Lightning Talks #1
					Complex Network Analysis with NetworkX
	Tutorial Office Hours, A Gentle Introduction to Multi-Objective Optimisation
					Separation of ~concerns~ scales in software
			PyData Pub Quiz
					Computational Social Science with Python, and how Open Source transforms Academia and Research
	Track Q&A Panel: Data Science in Production #2				Scalable cross-filtering dashboards with Panel, HoloViews and hvPlot
					Building Large-Scale Multilingual Fuzzy Matching Framework	Taking a Close Look in the Mirror: Data Literacy for Data Experts
	Short Talks Watch Party #4				Safe, Fair and Ethical AI - A Practical Framework	Complex Network Analysis with NetworkX
					Meditations on First Deployment: A Practical Guide to Responsible Data Science & Engineering	Separation of ~concerns~ scales in software
			Poster Session		Responsible ML in Production	Computational Social Science with Python, and how Open Source transforms Academia and Research
					Geometric and statistical methods in systems biology: the case of metabolic networks	Scalable cross-filtering dashboards with Panel, HoloViews and hvPlot
					When features go missing, Bayes’ comes to the rescue
			Pandas Sprint
					Uncertainty Quantification in Neural Networks with Keras	Safe, Fair and Ethical AI - A Practical Framework
	Tutorial Office Hours, Exploratory Data Analysis with Pandas and Matplotlib				Bayesian Decision Science: A framework for making data informed decisions under uncertainty	Meditations on First Deployment: A Practical Guide to Responsible Data Science & Engineering	PyData Organizers Meet
					Modelling the extreme using quantile regression	Responsible ML in Production
				Lightning Talks #2	Scalable cross-filtering dashboards with Panel, HoloViews and hvPlot	Geometric and statistical methods in systems biology: the case of metabolic networks	Lightning Talks #2
	Track Q&A Panel: Miscellaneous #2	Track Q&A Panel: Algorithmic Accountability
					Building Large-Scale Multilingual Fuzzy Matching Framework	When features go missing, Bayes’ comes to the rescue
	Tutorial Office Hours, From 0 to Virtual Assistant (now with Human Handoff!)		Modin Sprint	PyData Pub Quiz	Modern Time Series Analysis with STUMPY	Uncertainty Quantification in Neural Networks with Keras
						Bayesian Decision Science: A framework for making data informed decisions under uncertainty
						Modelling the extreme using quantile regression
	Track Q&A Panel: Causal and Statistical Methods #2
						Scalable cross-filtering dashboards with Panel, HoloViews and hvPlot
						Building Large-Scale Multilingual Fuzzy Matching Framework
						(See one more talk below!)

Sunday, November 15th

Time (UTC)	Major Events	Extracurriculars		Sponsor Events	Talk Watch Parties (Room 1)	Talk Watch Parties (Room 2)
						Modern Time Series Analysis with STUMPY
	Talks released
					Scalable cross-filtering dashboards with Panel, HoloViews and hvPlot
					Supercharge Scientific Computing in Python with Numba
	Tutorial Office Hours, Mine your own data - Analyze your Facebook Timeline
					Inventing Curriculum using Python and spaCy
					How to guarantee your machine learning model will fail on first contact with the real world.
	Track Q&A Panel: Miscellaneous #3				Rethinking Software Testing for Data Science
					Building one (multi-task) model to rule them all!
		PyTorch Ignite Sprint
					Hosting Dask: Challenges and Opportunities
				Mozn: Using Natural Language Processing (NLP) for sanctions screening (Sponsor talk room #1)
						Scalable cross-filtering dashboards with Panel, HoloViews and hvPlot
					What Lies in Word Embeddings
						Supercharge Scientific Computing in Python with Numba
					Building fairer models for finance
						Inventing Curriculum using Python and spaCy
					Games, Algorithms, and Social Good
						How to guarantee your machine learning model will fail on first contact with the real world.
	Short Talks Watch Party #5				Open Source Fairness
		Matplotlib Sprint				Rethinking Software Testing for Data Science
	Closing notes at Short Talks Room in Gather
						Building one (multi-task) model to rule them all!
	Keynote Watch Party: Tangible Steps Towards Algorithmic Accountability by Ayodele Odubela
						Hosting Dask: Challenges and Opportunities
	Keynote Fireside Chat with Ayodele Odubela
						What Lies in Word Embeddings
	Track Q&A Panel: Data Science in Production #3					Building fairer models for finance
						Games, Algorithms, and Social Good
	Tutorial Office Hours, Scaling Up Your Data Work With Dask	NetworkX Sprint
						Open Source Fairness
	Track Q&A Panel: Algorithmic Accountability
			Bokeh Sprint (Continues below)

Monday, November 16th

Time (UTC)	Extracurriculars
	Bokeh Sprint (continued)