August 2019
Intermediate to advanced
342 pages
9h 35m
English
In formal terms, PCA consists of selecting the hyperplane of space along which the data (represented by points in the space) are mostly spread out; this translates, in mathematical terms, into the search for the axis in which the variance assumes the maximum value.
The following screenshot depicts the principal components of a dataset:

To identify this axis, we will need to calculate the covariance matrix associated with our data, identifying the largest Eigenvectors within the matrix, which correspond to the axes associated ...
Read now
Unlock full access