AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Data Preparation and Feature Engineering - What Are the Features Present in the Data?
There's this boundary between what we call data preparation and feature engineering. Many of these tools fail when dickan they are not able to distinguish between egoricals and numericals. So many categorical data are stored as integers because people like to incude them. And it turns out that there's a semantic cap there. How do you figure out something as a categorical? We're looking at some more, and have published a common vision paper laying out some task that take place.