What comes after sorting eigenvalues in PCA?

I'm a student, I have to build PCA from scratch using Matlab on iris data. Iris data have 4 features i want to reduce them to 2. I reached the sorting of eigenvalues step. What is the next step?

Answer 1

[arushi]

Hi Shahd,

Steps to Perform PCA from Scratch -

1. Load the Iris Dataset

2. Standardize the Data - Standardize the features to have zero mean and unit variance.

3. Compute the Covariance Matrix - Compute the covariance matrix of the standardized data.

4. Compute Eigenvalues and Eigenvectors - Compute the eigenvalues and eigenvectors of the covariance matrix.

5. Sort Eigenvalues and Corresponding Eigenvectors - Sort the eigenvalues in descending order and sort the eigenvectors accordingly.

6. Select Top `k` Eigenvectors - Select the top `k` eigenvectors (where `k` is the number of dimensions you want to reduce to, in this case, 2).

7. Transform the Data - Transform the original data to the new subspace using the selected principal components.

Hope this helps.