0
$\begingroup$

I'm having trouble trying to understand the output of the prcomp function from package stats in R.

Below is the output of the function. My concern is if PC1 means column 1 and so on.

This is since I am trying to understand the variance of the columns through the columns so my clustering algorithm can use less columns.

             PC1         PC2         PC3         PC4         PC5         PC6
column1      -0.1182514  0.46119191 -0.59081719 -0.06185461  0.355082373  0.15779136
column2       0.1327832 -0.38247607 -0.56927572  0.36595097  0.382311915 -0.21166970
column3       0.3911240  0.31724820 -0.30998334 -0.17641298 -0.464012126 -0.49115595
column4       0.3283022 -0.31804337  0.14057974 -0.61262993  0.502428689 -0.02037630
column5       0.4385145  0.25196223  0.03869783  0.25461395  0.018291891  0.70032718
column6       0.6248343  0.08194069 -0.01284221 -0.16182097 -0.009914833  0.01535703

Thank you,

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

PC1 means the first principal component, the direction that carries the most variance.

You can project your data onto the first few components and perform clustering. You might like to look at sdev output to read off the standard deviation.

Improve this answer
$\endgroup$
3
  • $\begingroup$ Thank you Siong for the response. Do you have any resource that explain how to project the data based on the pca result? $\endgroup$
    – nariver1
    Commented Aug 18, 2019 at 17:51
  • $\begingroup$ This might help. $\endgroup$
    – Siong Thye Goh
    Commented Aug 18, 2019 at 17:55
  • $\begingroup$ Thank you. I'm marking your answer as correct. $\endgroup$
    – nariver1
    Commented Aug 18, 2019 at 21:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.