Machine learning models are often inscrutable and it can be difficult to know whether you are making progress. To improve feedback and speed up iteration cycles Benjamin Bengfort and Rebecca Bilbro built Yellowbrick to easily generate visualizations of model performance. In this episode they explain how to use Yellowbrick in the process of building a machine learning project, how it aids in understanding how different parameters impact the outcome, and the improved understanding among teammates that it creates. They also explain how it integrates with the scikit-learn API, the difficulty of producing effective visualizations, and future plans for improvement and new features.
One of the biggest issues facing us is the availability of sustainable energy sources. As individuals and energy consumers it is often difficult to understand how we can make informed choices about energy use to reduce our impact on the environment. Electricity Map is a project that provides up to date and historical information about the balance of how the energy we are using is being produced. In this episode Olivier Corradi discusses his motivation for creating Electricity Map, how it is built, and his goals for the project and his other work at Tomorrow Co.
Data mining and visualization are important skills to have in the modern era, regardless of your job responsibilities. In order to make it easier to learn and use these techniques and technologies Blaž Zupan and Janez Demšar, along with many others, have created Orange. In this episode they explain how they built a visual programming interface for creating data analysis and machine learning workflows to simplify the work of gaining insights from the myriad data sources that are available. They discuss the history of the project, how it is built, the challenges that they have faced, and how they plan on growing and improving it in the future.
Jake Vanderplas is an astronomer by training and a prolific contributor to the Python data science ecosystem. His current role is using Python to teach principles of data analysis and data visualization to students and researchers at the University of Washington. In this episode he discusses how he got started with Python, the challenges of teaching best practices for software engineering and reproducible analysis, and how easy to use tools for data visualization can help democratize access to, and understanding of, data.
Do you know what is happening in your production systems right now? If you have a comprehensive metrics platform then the answer is yes. If your answer is no, then this episode is for you. Jason Dixon and Dan Cech, core maintainers of the Graphite project, talk about how graphite is architected to capture your time series data and give you the ability to use it for answering questions. They cover the challenges that have been faced in evolving the project, the strengths that have let it stand the tests of time, and the features that will be coming in future releases.
What’s the weather tomorrow? That’s the question that meteorologists are always trying to get better at answering. This week the developers of MetPy discuss how their project is used in that quest and the challenges that are inherent in atmospheric and weather research. It is a fascinating look at dealing with uncertainty and using messy, multidimensional data to model a massively complex system.
Wouldn’t it be nice to be able to generate interactive 3D visualizations of physical systems in a declarative manner with Python? In this episode we spoke with Ruth Chabay and Bruce Sherwood about the VPython project which does just that. They tell us about how the use VPython in their classrooms, how the project got started, and the work they have done to bring it into the browser.
Ian Ozsvald and Emlyn Clay are co-chairs of the London chapter of the PyData organization. In this episode we talked to them about their experience managing the PyData conference and meetup, what the PyData organization does, and their thoughts on using Python for data analytics in their work.
Yves Hilpisch is a founder of The Python Quants, a consultancy that offers services in the space of quantitative financial analysis. In addition, they have created open source libraries to help with that analysis. In this episode we spoke with him about what quantitative finance is, how Python is used in that domain, and what kinds of knowledge are necessary to do these kinds of analysis.
Because of its easy learning curve and broad extensibility Python has found its way into the realm of algorithmic trading at Quantopian. In this episode we spoke with Scott Sanderson about what algorithmic trading is, how it differs from high frequency trading, and how they leverage Python for empowering everyone to try their hand at it.