From the course: Python: Working with Predictive Analytics
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Feature scaling - Python Tutorial
From the course: Python: Working with Predictive Analytics
Feature scaling
- [Instructor] On our road map, we're are still preparing our data. We need to apply feature scaling to our data, mainly to prevent the features with larger magnitudes from dominating the prediction model. Lets go back to the dinosaurs age and imagine we will need to count the number of living species in an island from top down, with a drone. When we look down from a higher distance bigger animals like dinosaurs, will be quite visible. However, it will be rather difficult to count the smaller animals, like ants. In order to have a fair glass to see all variables from the same lands, we will apply some methods. This way the prediction models will preform better. Two methods we will discuss here are called normalization and standardization. These methods are commonly applied to the variables X, and scaling the target values Y, is commonly not required. Let us start with the first method, normalization. Also referred as min max scaling. Subtract the minimum value from the number and…
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.