Principal Component Analysis is an important technique in statistical machine learning.
Principal Component Analysis (PCA) transforms the original data into an orthogonal data set with each feature known as a component.
The first component explains the most variability,
The remaining components are orthogonal to the first component and explain the remaining variability in the original data.
Principal Component Analysis is done to reduce the dimension of the original data set.
Read this new blog post in which I use Python to do Principal Component Analysis of Dow Jones Index DJI.
There are 30 stocks in the index that have been chosen to represent the different sectors in US economy.
Using PCA we can reduce the dimension of the original data comprising 30 stocks to just 5 components which explain almost 94% of the index.
These 5 components are orthogonal to each other.