ISSUE 414  ·   November 29, 2022

Organizational Insights

The important purple people outside the data team

It's not just "data people" who work with data. These days, data is commonly used by people throughout an organization and many are highly skilled. In this post, Mikkel Dengsøe takes a look at bringing these people into the data team and what to consider before doing it. 
Mikkel Dengsøe

Sponsored Link

Look ahead to the future of BI and a new way to Mode

Join Mode founder, Benn Stancil, and Adam Smith, Analytics Manager at Imperfect Foods, at this special event to learn how Imperfect Foods gained the trust of stakeholders with data teams at the center. We'll talk about the future of Mode and reveal exciting new product updates focused on modern business intelligence in 2023. 

Tutorials, Projects & Opinions

Demystifying Fourier analysis

Great explainer that takes a bottoms-up approach to show how the Fourier transform works. Includes several interactives to play with.
Davorin Šego

The Betting Equation

In this step-by-step guide, David Sumpter walks through the maths and coding needed to build a betting model for the World Cup. This is excerpted from his book, The Ten Equations That Rule The World.
David Sumpter

First impressions of DataFrames.jl and accessories

DataFrames.jl is a Julia package for data wrangling. If you're curious about Julia and/or are interested in how Julia does things differently, this post explores DataFrames.jl from an R-user perspective. 
June Choe

Tools & Code

SkyPilot

SkyPilot is an open-source framework that lets you run ML and Data Science jobs on any cloud through a unified interface. It's designed to save you money by choosing the cloud service that's currently the most cost-effective, regardless of where it is. This post is a good overview of how it works, use-cases in the wild, and how to get started.
UC Berkeley | Zongheng Yang

CausalPy - causal inference for quasi-experiments

CausalPy is a Python package for causal inference in quasi-experimental settings. The package allows for sophisticated Bayesian model fitting, in addition to traditional Ordinary Least Squares (OLS).
PyMC Labs | Benjamin Vincent

Name Match

Trying to link records that refer to the same person? Name Match uses probabilistic linking to identify and link records that refer to the same person. It's an open-source python package that works within and across datasets.
GitHub | University of Chicago Urban Labs

Resources

The Turing Way

The Turing Way is a handbook to reproducible, ethical and collaborative data science. The goal is to provide all the information that researchers and data scientists in academia, industry and the public sector need at the start of their projects to ensure that they are easy to reproduce at the end. There's a community here too and the online book is free.
Alan Turing Institute

Career

Goodbye, Data Science

"Data Science" has been widely hyped over the past several years but it's not without its issues. This post is a rant from the trenches that sure has struck a nerve in the community. It's a rant but there are useful insights here if you've been thinking about career moves.
ryxcommar

Looking for Ambitious Machine Learning Engineers

Ratio is a revenue-generating startup that's looking for ambitious machine learning engineers to help automate a big part of the advertising space. The product is "like a self-driving car of marketing" and largely uses existing models from OpenAI. Remote OK.
Data Elixir Talent Collective

Outlier

Stable Diffusion 2.0 

Things are moving fast in the text-to-image space. Stable Diffusion 2.0 is already live and the results are stunning! For details, check out the release notes at the link above. To play with it, create a free account on DreamStudio and select "v2.0" from the Model dropdown. For advanced playing, this post by Sicho Catmus is the best I've seen.
GitHub | Stability AI

How did you like this issue of Data Elixir?

👎    1     2     3     4     5   👍

Was this email forwarded to you?  Sign up here >>