“10 ways to debug Python code”

Christoph Deil; Talk- 30 Min.

Are your debugging skills limited to "print", or do you sometimes think there must be a better way to figure out what's going on? I will show 10 ways to debug Python code, and share tips and tricks for effective debugging.

“6 Years of Docker: The Good, the Bad and Python Packaging”

Sebastian Neubauer; Talk- 30 Min.

Local development of python code inside a docker container is surprisingly broken. In this talk I will walk you through the proper setup of a local python development environment using docker.

“A Bayesian Workflow with PyMC and ArviZ”

Corrie Bartelheimer; Talk- 30 Min.

Bayesian Modelling has several advantages such as the handling of uncertainty. While the advantages are well known, implementing a Bayesian model can be a bit more involved and some care needs to be taken to check whether the model converged.

“Abridged metaprogramming classics - this episode: pytest”

Oliver Bestwalter; Talk- 30 Min.

This talk is not about how to use pytest. pytest is a good project to explore metaprogramming techniques like introspection and code as data in the context of solving real world problems.

In this case: implementing a test framework.

“Active Learning with Bayesian Nonnegative Matrix Factorization for Recommender Systems”

Gönül Aycı; Talk- 30 Min.

In most of the systems, collecting data is not always free. I will talk about an approach for a matrix completion problem that learns a distribution of data where information is incomplete or collecting it has a cost.

“AI Intentions and Code Completion”

Vasily Korf; Talk- 30 Min.

Datalore supports intentions – code suggestions based on what you’ve just written. They cover a wide range of situations from generating code to warnings and optimization suggestions.

“Airflow: your ally for automating machine learning and data pipelines”

Enrica Pasqua, Bahadir Uyarer; Tutorial - 90 Min.

Now that you finally have your Machine Learning model trained, what’s the next step for moving to production?
Orchestrating, scheduling and monitoring ML inference pipelines is a big challenge.
Airflow can be your ally for handling this complexity.

“Algo.Rules - How do we get the ethics into the code?”

Carla Hustedt; Keynote

In the keynote I will present our Algo.Rules, 9 rules for the design of algorithmic systems and address the questions “What standards of quality should algorithms be held to?” and “How can we make sure that these standards are actually being implemented?”

“A Medieval DSL? Parsing Heraldic Blazons with Python”

Lady Red; Talk- 30 Min.

Medieval people invented one of the first domain specific languages to describe how to paint Coats of Arms. We'll learn how to write our own parse grammar to parse this language, and then look at the parse grammar of Python itself!

“An Introduction to Concurrency and Parallelism using Python Programming Language”

Tanmoy Bandyopadhyay; Tutorial - 90 Min.

Python concurrency and parallelism concepts like Multiprocessing, Multithreading, Coroutine, Asynchronous
I/O will be explained. We will learn to write simpler code with improved response time and throughput.

“🌈Apache Airflow for beginners”

Deleted User; Talk- 30 Min.

This talk gives an introduction to Apache Airflow, that facilitates workflow automation and scheduling. You will learn about the core concepts in Airflow and how they fit together to form a data pipeline.

“Applying deployment oriented mindset for building Machine Learning models”

Marianna Diachuk; Talk- 30 Min.

Developing ensemble model with hundreds of features? And getting stuck for months trying to deploy the model and fighting with data inconsistency and bugs? This talk will introduce the way to build the development process with deployment in mind.

“Are you sure about that?! Uncertainty Quantification in AI”

Florian Wilhelm; Talk- 45 Min.

There is a strong need in many AI applications to state the certainty about their predictions. This talk elaborates on different ways to perform uncertainty quantification in deep learning and classical methods.

“A Tour of JupyterLab Extensions”

Jeremy Tuloup, QuantStack; Talk- 30 Min.

JupyterLab can be extended via third-party extensions written by developers from the Jupyter community.

This is a tour of 20 of these extensions, in 20 minutes. Demos included!

“Automated Feature Engineering and Selection in Python”

Franziska Horn; Talk- 30 Min.

Careful feature engineering and selection can be just as important as choosing the right ML model & hyperparameters. I will present several options for automating the feature engineering and selection process with a focus on the autofeat library.

“Automating feature engineering for supervised learning? Methods, open-source tools and prospects.”

Dr. Thorben Jensen; Talk- 30 Min.

Feature engineering is crucial for supervised learning (SL), but labor-intensive. Automating this task is less established, compared to other steps of SL. We therefore present and compare approached and open-source libraries for automating this task.

“Avoiding ML FOBO”

Rachel Berryman, Dânia Meira; Talk- 30 Min.

Everyday there is a new package or algorithm to use- it can be hard to determine what is useful and what is only hype. The speakers offer a practical roadmap and checklist to help you cut through the hype and focus on developing useful ML products.

“Beyond Paradigms: a new key to grok Python & other languages”

Luciano Ramalho; Talk- 45 Min.

Focus on features, not paradigms. This new approach to the study of programming languages offers practical advice for programmers learning a new language, adopting coding idioms, and choosing suitable design patterns.

“Birds of a feather flock together - Tracking pigeons with Python and OpenCV”

Neslihan Edes; Talk- 30 Min.

In this talk I want to demonstrate how to use OpenCV to implement basic animal movement tracking use cases. And everything without any fancy machine learning or neuronal networks ;)

“Boosting simulation performance with Python”

Eran Friedman; Talk- 30 Min.

In this talk I will present the architecture of our simulation (written in Python) which allows us to simulate hours of real-life in only minutes of simulation. I will describe challenges we encountered and how we handled them.

“Break your API gently - or not at all”

Tim Hoffmann; Talk- 30 Min.

As hard as we try to write good code, there will always be cases in which we wish we had designed a different function signature, chosen another attribute name, ... But you can't change it anymore because it's public API - or can you?

“Build a Machine Learning pipeline with Jupyter and Azure”

Daniel Heinze; Tutorial - 90 Min.

With increasing focus on Machine Learning systems in almost every business it is important, to build a great pipeline to train, test and deploy your models. In this session we will show a way to do that with Jupyter and Azure

“CANCELED: Create CUDA kernels from Python using Numba and CuPy.”

Valentin Haenel; Tutorial - 90 Min.

Get well, soon, Valentin!

We'll explain how to do GPU-Accelerated numerical computing from Python using the Numba Python compiler in combination with the CuPy GPU array library.

“CANCELLED: First steps in Julia”

Felicia Burtscher; Talk- 30 Min.

Cancelled - get well soon, Felicia!

The community of Julia has been growing and the much anticipated 1.0 release of Julia is out since last summer.
Targeted to Julia beginners and Python users, we will especially highlight Julia's benefits and its major differences to Python.

“CANCELLED: Fresh New Pythonic Database: EdgeDB (And Why It's the Future)”

Bruno Gelb; Talk- 45 Min.

Get well soon, Dmitry!

This is an EdgeDB talk. EdgeDB is a new database from Python core developer and uvloop and asyncpg author Yuri Selivanov. It's nor NoSQL nor it a NewSQL. Looks very promising!

“Chips Made From Python”

Dan Fritchman; Talk- 45 Min.

Introduction to Python hardware description libraries, and how they are being used to design modern silicon, including open-source RISC-V CPUs.

“Commenting code — beyond common wisdom”

Stefan Schwarzer; Talk- 45 Min.

Good code comments are important for software maintenance. This talk
goes beyond the common wisdom you find in most books and online and
explains when this common wisdom falls short.

“Creating an Interactive ML Conference Showcase”

Harald Bosch; Talk- 30 Min.

Our goal is to create a simple yet interactive showcase for computer vision using a Python notebook. In a trade fair setup, we want to learn new object classes quickly using very few training examples. Thus, we rely on pretrained neural networks for

“Current affairs, updates, and the roadmap of scikit-learn and scikit-learn-contrib”

Adrin Jalali; Talk- 30 Min.

As a scikit-learn core developer, I'd give an update on recent changes, current affairs, and the roadmap of the package and the community packages included in scikit-learn-contrib. I'd also briefly talk about how new method proposals are evaluated.

“Dash: Interactive Data Visualization Web Apps with no Javascript”

Dom Weldon; Talk- 30 Min.

Interactive web pages and visualizations with no JavaScript? What could go wrong? What you can, can't, should and probably shouldn't do with plotly/Dash.

“Data Literacy for Managers”

Alexander CS Hendorf; Talk- 30 Min.

Artificial Intelligence need to be better understood in enterprises. Close the communications gap between engineers and management. Making data litteracy happen in your organisation.

“Decentralized and Privacy-Preserving ML via TensorFlow Federated”

Peter Kairouz, Amlan Chakraborty; Tutorial - 90 Min.

Federated Learning is a technology to train machine learning models and run data analytics on decentralized data. This tutorial will demonstrate step-by-step how to train largescale TensorFlow models and custom computations in federated environments.

“Deep Learning for Healthcare with PyTorch”

Valerio Maggio; Tutorial - 90 Min.

This tutorial provides a general introduction to Deep Learning using PyTorch with specific focus on challenges and solutions for Healthcare and Computational Biology.

“Detecting and Analyzing Solar Panels in Switzerland using Aerial Imagery”

Martin Christen; Talk- 30 Min.

We present a novel method for detecting solar panels and its geometry on aerial imagery. The goal is to know the exact locations, dimensions and potential of every solar installation in Switzerland.

“Developers vs. Enterprise”

Ingo Stegmaier; Talk- 30 Min.

This 30-minute talk will give you an overview about project management, success factors and specialties within enterprises. This will be a guide how you promote internal projects and bring them to success within a highly "political" environment.

“Docker and Python - A Match made in Heaven”

Dr. Hendrik Niemeyer; Talk- 45 Min.

Containers have revolutionized the way we build and ship software. This talk is aimed at newcomers and people with limited experience with Docker and will cover the basics of Docker and how it can be used alongside Python.

“Does hate sound the same in all languages?”

Andrada Pumnea; Talk- 30 Min.

How might we make social media safer and more inclusive? Tackling hate speech online is not easy, especially if it’s in a language less circulated. This talk describes detecting hate speech in Romanian from dataset creation to hate speech model.

“Driving 3D Printers with Python: Lessons Learned”

Gina Häußge; Talk- 30 Min.

OctoPrint is an open source web interface for 3D printers and deployed world wide on a large variety of devices. In this talk I explain some of the challenges in developing and maintaining such a piece of end user facing software in Python.

“Dr. Schmood's Notebook of Python Calisthenics and Orthodontia”

David Schmudde; Talk- 30 Min.

Explore the benefits of taking a functional approach when writing Python in Jupyter notebooks: reduce errors caused by out-of-order execution and hidden state while producing more readable code.

“Embrace uncertainty! Why to go beyond point estimators for valuable ML applications”

Stefan Maier; Talk- 30 Min.

Usually, uncertainties of Machine Learning predictions are just regarded as a sign of poor prediction accuracy or as a consequence of lacking input features. This talk illustrates how modeling uncertainties can improve ML based decisions.

“Equivariance in CNNs: how generalising the weight-sharing property increases data-efficiency”

Marysia Winkels; Talk- 30 Min.

In this talk, we will explore how the weight-sharing property of the convolutional layer can be generalised to achieve equivariance towards transformations beyond just translation, how to implement this, and the results on real-world data.

“Event-Sourced Story”

Jacek Kołodziej; Talk- 45 Min.

After three years of utilizing event sourcing in Growbots, I want to introduce to you its basics and share our experience acquired over that time - including complexity involved - so you can better assess whether it's a tool wo

“Extended Ligthning Talks CANCELLED: Crunching Numbers Like a Journalist”

Marie-Louise Timcke; Keynote

Get well soon Marie-Louise!

As our world becomes more and more data-driven, journalists are equipping themselves with data science and programming skills to turn numbers into headlines.

“Fairness in decision-making with AI: a practical guide & hands-on tutorial using Aequitas”

Pedro Saleiro; Tutorial - 90 Min.

In this tutorial, we are going to deep dive into algorithmic fairness, from metrics and definitions to practical case studies, including bias audits using Aequitas (http://github.com/dssg/aequitas) in real policy problems where AI is being used.

“Friend or Foe: Comparison of R & Python in Data Wrangling & Visualisation”

Yuta Kanzawa; Talk- 30 Min.

R and Python are partially overlapping but different as a whole: community and language. Still, comparing them in their common fields such as data wrangling and visualisation, useRs and Pythonistas will deepen mutual understanding.

“From body and code <programming in times of acceptance>”

Paloma Oliveira; Talk- 30 Min.

This talk is meant to bring awareness about the need of diversity from theoretical to practical day by day actions. Diversity not only as social justice, but to reclaim knowledge proficiency, critical perspective and new ideas.

“Gaussian Process for Time Series Analysis”

Dr. Juan Orduz; Talk- 30 Min.

The aim of this talk is to introduce the notion of Gaussian process and describe
how to use it to solve regressions problems and time series forecasting.

“Gaussian Progress”

Vincent Warmerdam; Talk- 45 Min.

This talk is an attempt at explaining the power of the Gaussian[tm] by stepping up the ladder from Naive Bayes to Mixtures to Neural Mixtures to Gaussian Processes.

“Getting started with FPGA with Python”

Olga; Talk- 30 Min.

In this review, we'll look into frameworks that will help Python developer start working with FPGA without prior knowledge of Verilog or VHDL.

“Get to grips with pandas and scikit-learn”

Sandrine Pataut; Tutorial - 90 Min.

This session will be an exposition of data wrangling with pandas and machine learning with scikit-learn for Python Programmers. This hands-on workshop will cover a classification project, from importing the data to evaluating model performance.

“Hidden Markov Models for Chord Recognition - Intuition and Applications”

Caio Miyashiro; Tutorial - 90 Min.

This tutorial describes the intuition behind Hidden Markov Models, with less mathematical formulas and with an application on Music Analytics - Chord Recognition

“Hide Code, Minimize Dependencies, Boost Performance - The PyTorch JIT”

Tilman Krokotsch; Talk- 30 Min.

PyTorch makes developing, training and debugging deep neural networks convenient. Learn how to export your trained model using its just-in-time (JIT) compiler to hide your network architecture, minimize code dependencies and use it in the C++ API.

“How MicroPython went into space”

Christine Spindler; Talk- 30 Min.

MicroPython is a lean and efficient implementation of the Python 3 programming language, optimised to run on microcontrollers and in constrained environments. One of these environments is on a spacecraft.

“How strong is my opponent? Using Bayesian methods for skill assessment”

Darina Goldin; Talk- 30 Min.

Being able to correctly estimate a competitors' skill is a crucial question in sport forecasting and matchmaking. This talk will provide an overview of the three most common algorithms for this task: Elo, Glicko2 and Trueskill.

“How to choose better colors for your data visualizations”

Daniel Ringler; Talk- 45 Min.

Everybody is doing colorful charts with Python libraries such as matplotlib and bokeh but most people never change the basic configuration. This talk will teach you the basics of color theory to help you choose the right colors of your charts.

“How to write tests that need a lot of data?”

Sander Kooijmans; Talk- 30 Min.

In this talk Sander explains how you can write unit and integration tests that need a lot of data. As an example Sander shows how to test code of a warehouse management system (WMS). This is not about big-data, though.

“Interpretable Machine Learning: How to make black box models explainable”

Alexander Engelhardt; Talk- 30 Min.

Complex machine learning models make better predictions, but at the cost of turning into an unexplainable black-box model. In this talk, we'll look into a framework that allows us to explain why a model makes a specific prediction.

“Introduction to automated testing with pytest”

Raphael Pierzina; Talk- 45 Min.

We'll learn how to get started with developing automated tests in Python with the pytest test framework.

“Is it me, or the GIL?”

Christoph Heer; Talk- 45 Min.

People refer Python's Global Interpreter Lock as main bottleneck for their performance critical applications. But how can you test if your application really suffer from the GIL?

“Job Panel”

Christian Barra, Matteo Guzzo, Tereza Iofciu, Katharina Rasch, Sieer Angar; Panel

Panel about freelancing and the experience of moving from academia to industry, challenges, opportunities and where to start.

“Julia for Python”

Simon Danisch; Talk- 30 Min.

Julia is a new Language, that is fast, high level, dynamic and optimized for Data Science. But due to its young age, it might not be for everyone yet. Learn about Julia's strengths and how you can integrate it in your Python workflow!

“Kartothek – Table management for cloud object stores powered by Apache Arrow and Dask”

Florian Jetter; Talk- 30 Min.

Efficient data storage is an integral part of successful data applications. Cloud object stores prove to be an efficient choice but come with downsides when storing structured, tabular data. There is a way out, though.

“Kubernetes 101 for Python Developers”

Christian Barra; Tutorial - 90 Min.

Kubernetes (K8s) is an open-source system for automating deployment, scaling, and management of containerized applications.

During this training you will learn how to use it and how it can help as a Python developer.

“Law, ethics and machine learning – a curious ménage à trois”

Dr. Benjamin Werthmann; Talk- 45 Min.

The talk addresses how law and ethics can provide a framework for the “machines on the rise” that ensures fairness and societal acceptance while not interfering (too much) with the drive behind the advancement of a powerful technology.

“Lessons Learned as a Product Manager in Data Science”

Tereza Iofciu; Talk- 45 Min.

The fun part about data science is that no two people really agree on the definition of the data scientist role. So how does the role of product manager in data science look like?

“Leveraging the advantages of Bayesian Methods to build a data science product using PyMC3”

Korbinian Kuusisto; Talk- 30 Min.

Bayesian models offer greater theoretical advantages compared to non-probabilistic methods, and also allow for more flexible model design. But how can one leverage these theoretical advantages to build a successful data science product?

“Loss Function Theory 101”

David Wölfle; Talk- 30 Min.

This talk covers the theoretical background behind two common loss functions, mean squared error and cross entropy, including why they are used for machine learning at all, and what limitations you should keep in mind.

“Machine learning with little data - from digital twin to predictive maintenance”

Andreas Hantsch; Talk- 30 Min.

This talk is about the coupling of a digital twin model and a machine learning predictive maintenance algorithm in order to be able to detect anomalies in the operation of a not well-known hardware system.

“Making the complex simple in data viz”

Tania Vasilikioti; Talk- 30 Min.

Creating graphics that convey the desired message, are easily interpretable, but also beautiful can be a daunting task. This talk will demonstrate how to use The Grammar of Graphics framework to conceptualize the elements of any graphic, in Python.

“Managing the end-to-end machine learning lifecycle with MLFlow”

Tobias Sterbak; Tutorial - 90 Min.

Machine learning requires experimenting with datasets, data preparation steps, and algorithms. Deploy models to a production system and retrain it on new data. MLflow is an open source platform for managing the end-to-end machine learning lifecycle.

“Mock Hell”

Edwin Jung; Talk- 45 Min.

Mock is an easily abused tool. In perverse cases, it increases technical debt and prevents refactoring. This talk describes the history of mocking, alternatives, anti-patterns, and the connection to clean architecture.

“Monitoring infrastructure and application using Django, Sensu and Celery.”

Hari Kishore Sirivella; Talk- 30 Min.

Monitoring is a key aspect for any business. It enables us to find and be notified about our application's problems way ahead our customer notices it, which enables us to keep our businesses running and making customers happy.

“Optimizing Input: Building your own customized keyboard”

Daniel Rios; Talk- 30 Min.

Keyboards, the main way we interact with computers, have remained unchanged for a century, despite being free from mechanical necessity. Alternatives made possible by recent technology can optimize the way we input text and interact with our devices.

“Package and Dependency Management with Poetry”

Steph Samson; Tutorial - 90 Min.

Poetry is “Python packaging and dependency management made easy.”It not only packages up your libraries easily but also isolates environments and resolves dependencies — all with an intuitive command line interface.

“Panel: Turn any notebook into a deployable dashboard”

Philipp Rudiger; Talk- 30 Min.

Quickly turn your existing analyses built on the PyData stack into shareable, standalone apps and dashboards using the new open-source Panel library without learning the details of web development.

“Parallel programming for python developers – Let’s Go(lang)”

Dominik Henter, Jéssica Lins; Tutorial - 90 Min.

Despite all of python's strengths, parallel programming tends to not be one of them. Enter Go, a language that has parallel programming at its core. In this tutorial we will build an API pipeline service in Go, that calls several APIs in parallel.

“PEP 581 and PEP 588: Migrating CPython's Issue Tracker”

Mariatta Wijaya; Keynote

The acceptance of PEP 581, by Python steering council means that another big workflow change is impending. Let's hear about some of the proposed plans on improving CPython's workflow, and learn how you can help and take part in this process.

“Play Stupid Games, Win Stupid Prizes”

James Powell; Talk- 30 Min.

This is reserved for a James Powell in-promptu talk, stay tuned! This is reserved for a James Powell in-promptu talk, stay tuned!

“Practical DevOps for the busy data scientist”

Dr. Tania Allard; Talk- 45 Min.

How many times have you developed a model or a data application and tested it locally or in a staging environment just to find out that it breaks in production? This is a common issue faced by thousands of data scientists around the globe. As the wor

“Privacy-preserving Machine Learning for text processing”

Sarah Diot-Girard; Talk- 45 Min.

Privacy is something we all care about, but when it is time to put our principles into application, it is not so trivial, especially when working with text. This talk aims at presenting a few options to handle privacy when dealing with text.

“Production-level data pipelines that make everyone happy using Kedro”

Yetunde Dada; Talk- 45 Min.

Learn how easy it is to apply software engineering principles to your data science and data engineering code. Expect an overview of Kedro, a library that implements best practices for data pipelines with an eye towards productionizing ML models.

“Professional Development and Career Progression for Data Scientists”

Noa Tamir; Talk- 30 Min.

In this talk you will learn how to level up your skills, and develop your your career using on the job opportunities, as well as open source contributions

“pytest - simple, rapid and fun testing with Python”

Florian Bruhin; Tutorial - 90 Min.

The pytest tool presents a rapid and simple way to write tests for your Python code. This training gives an introduction with exercises to some distinguishing features.

“Python 2020+”

Łukasz Langa; Keynote

While very successful, Python's peculiarly missing in some spaces like mobile devices, client-side Web, or gaming. Should we do something about it? How could we go about changing that?

“Python Panel”

Alexander CS Hendorf, Stefan Behnel, Mariatta Wijaya, Hynek Schlawack, Łukasz Langa; Panel

Panel about Python, core-devs, development, challenges, community and the future! And: how can become a part of it! Join the discussion!

“Python-Powered OSINT! Modernising Open Source Intelligence for Investigating Disinformation”

Mx Chiin-Rui Tan, Dare Imam-Lawal; Talk- 30 Min.

OSINT, the discipline of gathering intelligence from open sources, is critical for state & citizen interest but has lacked modernisation. We present a socio-technical maturity model using Python to update legacy OSINT for disinformation investigation

“Quantum computing with Python”

James Wootton; Tutorial - 90 Min.

Frameworks for quantum computing are a new way to use Python for cutting-edge science, and to plan for future applications of this new technology. This session will serve as an introduction to quantum computing as a whole, and also to Qiskit, the most well-developed and well-used quantum Python framework.

And to make sure I don't get too complex, we'll do it all on a microcontroller!

“Refactoring in Python: Design Patterns and Approaches”

Tin Marković; Talk- 30 Min.

Experiences and lessons learned from tackling extremely demanding code. How to bring order to mismanaged code and elevate the code base to a standard that's acceptable in today's tech environment.

“Rethinking Open Source in the Era of Cloud & Machine Learning”

Peter Wang; Keynote

By some measures, Open Source is a wildly successful and crucial part of many areas of modern technology. However, the ’sustainability crisis’ and the age of cloud computing have threatened its core mechanisms. Peter will present some alternative ways of looking at this crucial moment in the evolution of the open source movement, and suggest some ways to think about the future of open source.

“Running An Open Source Project Like A Start Up”

Cheuk Ting Ho; Talk- 30 Min.

Not so long ago, I started an open source project - PicknMIx. It feels like running a start up if you are serious about it. Want to know my story? Want to check if you can do it as well? I will tell you. (Stickers not guaranteed though)

“Should I stay or should I go? Optimal exercise decisions using the Longstaff-Schwartz algorithm”

Benedikt Rudolph; Talk- 30 Min.

This talk presents a Python implementation of the Longstaff-Schwartz algorithm for financial exercise option valuation. The technical problems of optimal exercise decisions and exercise option valuation are demonstrated using code examples.

“skorch: A scikit-learn compatible neural network library that wraps pytorch”

Benjamin Bossan; Talk- 30 Min.

This talk is about the open source package skorch, a wrapper library that allows you to combine the best of sklearn and PyTorch. It covers when it makes sense to use skorch and highlights interesting features.

“Static Typing in Python”

Dustin Ingram; Talk- 30 Min.

In this talk, we'll discuss the advantages and disadvantages to a static type system, as well as recent efforts to introduce static typing to Python via optional "type hints" and various tools to aid in adding types to Python code.

“Strawberry: a dataclasses inspired approach to GraphQL”

Patrick Arminio; Talk- 30 Min.

Over the past few years, GraphQL has gained much traction, especially in the JavaScript world. Python is getting on board this trend with new interesting libraries. In this talk, we will see how Strawberry makes uses of dataclasses and type hints to

“Tackle the problems that really matter - leverage the power of data science in the service of humanity”

Eva Schreyer, Lisa Zäuner; Talk- 30 Min.

Data Science for Social Good Berlin (DSSG) brings together data scientist volunteers and nonprofit organisations that need support in tackling various data challenges. In this talk we will tell you how data science can be used for social good.

“Take control of your hearing: Accessible methods to build a smart noise filter”

Peggy Sylopp, Aislyn Rose; Talk- 30 Min.

Have you ever wanted more control over what you do or don't hear? This talk explores the potential of Python, deep learning, and open databases to bring you towards that goal, without needing expensive licenses or software.

“The Sound of Silence: Online Misogyny and How we Model it”

Teresa Ingram; Talk- 45 Min.

Female-identifying people are being attacked and silenced online. Social media platforms act as neutral bodies and law enforcement can’t stop the abuse. When you can’t trust that your safety will be protected online, what can you do? We say, Opt Out.

“Time Series Anomaly Detection for Bottling Machine Maintenance”

Andrea Spichtinger; Talk- 30 Min.

This talk discusses time series anomaly detection methods for predictive maintenance of machines in bottling plants and their implemention on AWS edge devices.

“Time series modelling with probabilistic programming”

Sean Matthews, Jannes Quer; Talk- 45 Min.

This talk focuses on a Bayesian approach of advanced time-series forecasting in the case of small data. We describe the stages of modelling from simple smoothing to advanced forecasting by applying Gaussian Processes and State Space Models.

“Tools that help you get your experiments under control”

Katharina Rasch; Talk- 45 Min.

There is now a wealth of tools that support data science best practices (e.g. tracking experiments, versioning data). Let’s take a look at which tools are available and which ones might be right for your project.

“Transforming a Legacy System into a Bias-Mitigating AI Solution for Debt Repayment”

Avaré Stewart; Talk- 30 Min.

We present Phoenix, a modernization of a legacy, German rule-based system based on Tesseract and SpaCy, and uses AI Fairness 360 to build tunable, Bias-Minimizing AI solutions to offer payment incentives to debtors.

“Using adversarial samples to break and robustify your Vision Neural Network Models”

Irina Vidal Migallón; Talk- 30 Min.

We will cover several techniques to expose weaknesses and robustify neural network models for computer vision, from basic precautions to more advanced adversarial training.

“Using machine learning for Level Generation in Snake (video-game)”

Filipe Silva; Tutorial - 90 Min.

As a practical example, this tutorial uses machine learning models to predict where to best place the apple in Snake. By using datasets that contain different plays we can obtain different game experiences or models that can adapt to the style of a player.

“Using Micropython to develop an IoT multimode sensor platform with an Augmented Reality UI”

Nicholas Herriot; Talk- 45 Min.

Building a sensor platform that is flexible and intuitive is hard! This talk takes you through a journey how a sensor platform was developed to create a sensor farm for the purpose of capturing and acquiring data to be used in AI systems for Samsung.

“Version Control for Data Science”

Alessia Marcolini; Talk- 45 Min.

Are you versioning your Machine Learning project as you would do in a traditional software project? How are you keeping track of changes in your datasets?

“Visualizing Interactive Graph Networks in Python”

Jan-Benedikt Jagusch; Talk- 30 Min.

In this talk you will learn how to visualize graph networks in Python, using networkx, traitlets, ipywidgets and plotly. The resulting plot will be fully interactive, which makes it easy to filter edges, find nodes by their name and update the graph's layout.

“vtext: text processing in Rust with Python bindings”

Roman Yurchak; Talk- 30 Min.

In this we talk present how to write Python extensions in Rust, and discusse advantages and limitation of such approach. We then illustrate this approach on the vtext project, that aims to be a high-performance library for text processing.

“Want to have a positive social impact as a data scientist?”

Ellen König; Talk- 30 Min.

Discover your individual approach towards more positive social impact by conducting experiments. I'll show you how! I’ll also share my learnings from doing such experiments over the last 15 years.

“What if I tell you that your specs are broken”

Samuele Maci; Talk- 45 Min.

This talk is going to be about Swagger Specs and their changes. We're going to examine what Backward Incompatible changes are and how you can deal with them.
The talk will also introduce you to a tool that will help you on having safer changes.

“What’s new in Python 3.8?”

Stéphane Wirtel; Talk- 30 Min.

In few months, there will be the release of Python 3.8! As a core dev I would like to show you the new features of this version.

“What we learned from scraping 1 billion webpages every month”

Samet Atdag; Talk- 30 Min.

Web is broken. We learned the hard way. Developers tend to hack, hacks tend to break the web. In this talk, I share what we learned how websites don't obey the protocols and how developers had caused the web became a chaotic medium.

“Where Linguistics meets Natural Language Processing”

Mariana Capinel; Talk- 30 Min.

This talk explains how linguistics describes language - via phonetics-phonology, morphology, syntax, semantics and pragmatics. We will combine linguistic concepts with models through examples for NLP newbies.

“Why you don’t see many real-world applications of Reinforcement Learning.”

Yurii Tolochko; Talk- 45 Min.

Reinforcement learning is the closest thing to a general AI system that we have. When it works, that is. The problem is, it often doesn’t. In this talk we will discuss the difficulties of RL as well as what to look for in the future.

“Why you should (not) train your own BERT model for different languages or domains”

Marianne Stecklina; Talk- 30 Min.

Language models like BERT can capture general language knowledge and transfer it to new data and tasks. However, applying a pre-trained BERT to non-English text has limitations. Is training from scratch a good (and feasible) way to overcome them?

“Write your Own Decorators”

Mike Müller; Tutorial - 90 Min.

Decorators are really useful. Using them is simple. Writing your own is bit more involved. Learn in this hands-on workshop how to write decorators for many different purposes. The emphasis is on best practices and practical examples.

“Your Name Is Invalid!”

Miroslav Šedivý; Talk- 30 Min.

About people with first names, middle names, last names, one-word names, multiple names, and changing names, about names with characters beyond ASCII, and about using Python to handle them correctly, because names of people cannot be invalid.