Stratified sampling is imporant when you have extremely unbalanced machine learning datasets to ensure that each class is evenly distributed across your train/test/validation splits. While there are several solutions for multi-class data, there are few for multi-classs and multi-label datasets. So, I’m sharing my solution below.
[Read More]
Automatically creating Kedro dataset directories
Avoiding IO errors at the end of pipelines with a simple hook.
If you use Kedro for data pipelines, you may have had issues saving datasets if the dataset directory does not already exist. Instead of manually creating these data folders, here is a hook which automatically creates any missing directories. In the process, it’ll also automatically generate a .gitkeep file.
[Read More]
Installing Mosh server on AWS
Also works for other VPS
These instructions were were on a fresh instance of an Ubuntu AMI.
[Read More]
Installing X2go server for i3
I tried to follow this guide for creating a remote Linux workstation on a VPS.
[Read More]
AI for Social Good Podcast Series
The This Week in Machine Learning and AI Podcast just did a series of interviews with Microsoft researchers working on making the world a better place with AI.
[Read More]