- PCA or Principal Component Analysis is a method to reduce the initial dataset size to a smaller one with fewer independent variables/attributes, and mostly applied in classification problems. For regression, we have PCR or Principal Component Regression.
- Each principal component is a linear combination of the original variables:
PC = w1X1 + w1X2 + ... + wnXn
where X is the original variable and w is weight/coefficient
- Complete PCA concept tutorial https://medium.com/analytics-vidhya/understanding-principle-component-analysis-pca-step-by-step-e7a4bb4031d9