Principal Component Analysis – PCA is the process of projecting variance of data using minimal dimensions.
The direction of dimension along which the variance is maximised(highest) will be chosen as the first principal component. The next best direction as the second P.C. and should be orthogonal to the first P.C, and so on each being orthogonal to the rest.
- There are as many P.C.s as there are dimensions.
If the variance of any P.C. is small enough you can ignore it and all the rest after it, and use only the previous P.Cs which in return reduces the data and computation in expense of a little loss of small significant data.