Question

What Would You Do In PCA To Get The Same Projection As SVD?

Answer 1

Answer:

Then recall that SVD of is where contains the eigenvectors of and contains the eigenvectors of . is a called a scatter matrix and it is nothing more than the covariance matrix scaled by . Scaling doesn't not change the principal directions, and therefore SVD of can also be used to solve the PCA problem.

Answer 2

Answer-

SVD of is where contains the eigenvectors of and contains the eigenvectors of is a called a scatter matrix  and it is nothing more than the covariance matrix scaled by . Scaling doesn't not change the principal directions, and therefore SVD of can also be used to solve the PCA problem.

Explanation:

When the data has a zero mean vector PCA will have same projections as SVD, otherwise you have to centre the data first before taking SVD.