1 / 20

>> [ ax,mx,stdx ]=auto(x); >> [ scores,loads,ssq,res,reslm,tsqlm,tsq ] = pca (ax,1,0,5);

>> [ ax,mx,stdx ]=auto(x); >> [ scores,loads,ssq,res,reslm,tsqlm,tsq ] = pca (ax,1,0,5); Percent Variance Captured by PCA Model Principal Eigenvalue % Variance % Variance Component of Captured Captured Number Cov (X) This PC Total

kimball
Download Presentation

>> [ ax,mx,stdx ]=auto(x); >> [ scores,loads,ssq,res,reslm,tsqlm,tsq ] = pca (ax,1,0,5);

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. >> [ax,mx,stdx]=auto(x); >> [scores,loads,ssq,res,reslm,tsqlm,tsq] = pca(ax,1,0,5); PercentVarianceCapturedby PCA Model Principal Eigenvalue % Variance % Variance Component of CapturedCaptured NumberCov(X) This PC Total --------- ---------- ---------- ---------- 1 9.29e+00 46.44 46.44 2 2.55e+00 12.75 59.18 3 1.85e+00 9.24 68.42 4 1.48e+00 7.41 75.83 5 1.34e+00 6.70 82.53 6 1.14e+00 5.70 88.23 7 8.57e-01 4.29 92.52 8 5.06e-01 2.53 95.05 9 3.99e-01 2.00 97.04 10 1.78e-01 0.89 97.93

  2. >> plot(loads(:,2)) >> hline(0) >> text([1:20]',loads(:,2),namevarall);

  3. >> plot(scores(:,2)) >> hline(0) >> text([1:22]',scores(:,2),lakenames(:,1:5));

  4. >> plot(loads(:,1),loads(:,2),'+r') >> hline(0) >> vline(0) >> text(loads(:,1),loads(:,2),namevarall);

  5. >> plot(scores(:,1),scores(:,2),'ob') >> hline(0) >> vline(0) >> text(scores(:,1),scores(:,2),lakenames(:,1:5));

  6. >> nscores(:,1)=scores(:,1)/norm(scores(:,1)); >> nscores(:,2)=scores(:,2)/norm(scores(:,2)); >> plot(nscores(:,1),nscores(:,2),'ob') >> hline(0) >> vline(0) >> text(nscores(:,1),nscores(:,2),lakenames(:,1:5)); >> hold Currentplotheld >> plot(loads(:,1),loads(:,2),'+r') >> text(loads(:,1),loads(:,2),namevarall);

  7. Modelo de correlación entre HCB y variables/parámetros no-químicos >> [b,ssq,p,q,w,t,u,bin] = pls(axv,ay,5,1); Percent Variance Captured by PLS Model -----X-Block----- -----Y-Block----- LV # This LV Total This LV Total ---- ------- ------- ------- ------- 1 30.36 30.36 57.63 57.63 2 21.06 51.41 17.24 74.88 3 10.63 62.05 7.68 82.56 4 14.61 76.66 1.11 83.67 5 9.87 86.52 0.58 84.25

  8. Modelo para 1 comp. PLS >> plot(b(1,:)') >> hline(0) >> text([1:8]',b(1,:)',namevarpar)

  9. >> plot(w(:,1)) >> hline(0) >> text([1:8]',w(:,1),namevarpar)

  10. vip_scores1 = vipr(t(:,1),p(:,1),w(:,1),b(1,:)',1,8,namevarpar);

  11. >> plot(b(2,:)') >> hline(0) >> text([1:8]',b(2,:)',namevarpar)

  12. >> plot(w(:,2)) >> hline(0) >> text([1:8]',w(:,2),namevarpar)

  13. vip_scores2 = vipr(t(:,2),p(:,2),w(:,2),b(2,:)',1,8,namevarpar);

  14. >> plot(b(3,:)') >> hline(0) >> text([1:8]',b(3,:)',namevarpar)

  15. >> plot(w(:,3)) >> hline(0) >> text([1:8]',w(:,3),namevarpar)

  16. vip_scores3 = vipr(t(:,3),p(:,3),w(:,3),b(3,:)',1,8,namevarpar);

More Related