ISSUE 427  ·   March 7, 2023

Projects

Suspicion Machines Methodology

Wired Magazine recently released a four-part series about the inner workings of a welfare fraud detection system. They got access to not just the algorithms but also the data that powered the system and the handbook that was used by the data scientists who ran it. This post is a detailed explainer on what the researchers did and how they did it.
Lighthouse Reports

Using ML to Aid Survivors and Race through Time

A few hours after the recent earthquakes in Turkey, a group of data scientists and engineers built a machine learning application to help search and rescue teams find survivors. This a great post that details the problems they helped solve, the issues they encountered along the way, and how they ultimately succeeded.
Hugging Face | Merve Noyan and Alara Dirik

Sponsored Link

Gain productivity, accelerate innovation, and improve customer experiences.

You're invited!

Experts in financial data showcase how to utilize rich third-party data in our upcoming events. Discover why wealth advisory firms, banks, and business lenders leverage cloud-based technology and data-driven insights to make important business decisions. 

Webinar: How to harness financial data to help drive improved analytics and insights with Envestnet & AWS

Date: March 22^nd

Time: 10:00 AM (PST), 10:00 AM (BST), AND 10:00 AM (SGT)

Register now >

Tutorials & Opinions

Predicting wine quality using chemical properties

Nice step-by-step tutorial for building a model to predict wine quality in Python. Covers data normalization, Pytorch basics, training, visualization, model evaluation, and how to use the model to make predictions. There's a link at the bottom of the post to a notebook.
Alfredo González-Espinoza

Onboarding is an art, not a science

Effectively onboarding new members onto a data team can go a long way to set them up for success. This post breaks down what new team members need to know and a timeline for coming up to speed. The considerations here apply to both sides of the table so if you're the one joining a new team, this is a good framework for learning your new job. 
Locally Optimistic | Jerrie Kumalah

Julia and Python better together

Here's how to use Julia and keep using the Python packages you like as a part of your Julia workflow.
Bogumił Kamiński

Sharpen your math, CS and data skills in 15 minutes a day

For professionals and lifelong learners alike, Brilliant is one of the best ways to learn. The deets: Bite-sized interactive lessons make it easy to level up in everything from math and data science to AI and beyond. Join 10+ million people building skills every day. Start your 30-day free trial today!
// Data Elixir Partner

Tools & Code

Mathesar

Mathesar is a new open source tool that provides a spreadsheet-like interface to a PostgreSQL database. It's a self-hosted web application, which gives you privacy and control of your data. Check out the live demo. This is nice!
GitHub | Center of Complex Interventions

sqlean - All the Missing SQLite Functions

There are a lot of SQLite extensions out there, but they are incomplete, inconsistent and scattered across the internet. sqlean brings them together, neatly packaged into domain modules, documented, tested, and built for Linux, Windows and macOS.
GitHub | Anton Zhiyanov

Meerkat

Meerkat is an open-source Python library that helps to interactively wrangle images, videos, text documents and more with foundation models. With Meerkat, you can pull in unstructured data, wrangle it with foundation models, and build custom, interactive workflows, all from Python.
GitHub | HazyResearch

Resources

Datasets at your fingertips in Google Search

Dataset Search is a search engine for datasets. Using just keywords, users can search from a variety of sources, including scientific government, and commercial datasets. There are more than 45 million datasets here and everything is well documented and easy to find.
Google Research

How did you like this issue of Data Elixir?

👎    1     2     3     4     5   👍

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