From the course: More Python Tips, Tricks, and Techniques for Data Science
Join today to access over 22,500 courses taught by industry experts or purchase this course individually.
Feature engineering - Python Tutorial
From the course: More Python Tips, Tricks, and Techniques for Data Science
Feature engineering
- [Instructor] So up until now, we have seen data that was tidy and cleaned out for us. But in the real world, data is rarely clean and correctly formatted. So with this in mind, one of the more important steps in practicing machine learning is feature engineering, and here in this video we'll cover a few commonly occurring data types, and we'll talk about what are the methods to transform each of those types. So first of all, we have numerical features. Our numerical data is the easiest to work with and it's ready to be fed to the model for training. So feature engineering here mostly means that we are dealing with missing values or we want to derive new features out of the existing ones. For example, I have two arrays over here, two features. Distance and time. Both of them are numpy arrays. Now we can actually create a new feature. Let's say we want to create speed. Now this would be very simple. We could actually…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.