From the course: Machine Learning with Data Reduction in Excel, R, and Power BI
Join today to access over 24,800 courses taught by industry experts.
PCA projection space
From the course: Machine Learning with Data Reduction in Excel, R, and Power BI
PCA projection space
- [Instructor] Once we've solved for our eigenvalues and eigenvectors, we can use them to create a projection plane for the PCA model. The PCA algorithm lets us remove the correlation in the model so we can visualize the projection space on a new plane. If we had a third axis in the form of a z-axis, this would represent PC3, and be orthogonal to the other axes. Four is impossible to visualize but even three can be hard to visualize because we're still only plotting on a two-dimensional space. In the Excel PCA file, I've added a new set of columns for the city, and for the projected points for the PCA model for PC1 and PC2 that we're now going to create using the eigenvectors we just calculated. Our eigenvectors are going to take our existing data points that we've transformed and rotate them around the origin based on their relationship to one another in the model. We're going to use matrix multiplication…
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.