— Insight —
This interview with Catherine D’Ignazio and Lauren Klein is a great introduction to their recent book, Data Feminism. Don't be fooled by the title. Their book covers broad questions about power and ethics in data science and has been getting rave reviews around the web.
20 years ago, a psychology experiment showed that people tend to miss obvious things if they're specifically looking for something else. It was called a "selective attention test" and it's become a psychology classic. Now, a similar phenomenon has been shown to occur in data analysis. When given a specific hypothesis to test, students tended to miss the gorilla in the data.
— Tools and Techniques —
Airbnb is widely known as a data-driven organization but it wasn't always that way. Just two years ago, the company made a deep commitment to data quality and embarked on a major rebuilding effort. This first in a series of posts explores the issues and the key components of what became Airbnb's Data Quality initiative.
When doing time-series modeling, it's not uncommon to want to make long-term predictions for multiple, related, time-series. This is a great talk that shows how to build a hierarchical version of Facebook’s Prophet package to do exactly that.
Deepnote is a new type of notebook for data science that's Jupyter-compatible, has real-time collaboration and runs in the cloud. This introduction shows how it can help you work more efficiently.
The pointblank R package makes it easy to methodically validate your data whether in the form of data frames or as database tables. In addition to the validation tools, the package gives you the ability to stay up-to-date with the information that defines your tables.
Now that companies understand the importance of a data driven culture, leaders are searching for practical ways to reinforce this new mindset. Join Metis to learn how spreadsheets can help employees get comfortable with data and empower them to perform their own analysis without hand holding by your advanced analytics team.
— Resources —
Looking for a conference to attend, sponsor or submit a talk to? This latest list from Tryolabs includes 40 machine learning conferences around the world. Most have gone virtual and offer good discounts.
Great introduction to linear algebra, especially with regards to machine learning. This is very well-organized and includes a detailed list of linked topics, lots of diagrams, and links to useful resources around the web.
— Data Viz —
Cameron Beccario's live weather application just got a major upgrade. What started as a small project to refresh the menu turned into a rewrite of nearly the entire site. This is one of the best applications you'll find for visualizing wind, waves, temperatures and more using weather data from around the world.