Machine Learning with R Cookbook - Second Edition

How to do it...

Perform the following steps to perform nonlinear dimension reduction with LLE:

1. First, you need to install and load the package, lle:

        > install.packages("lle")
        > library(lle)  

2. You can then load ll_scurve_data from lle:

        > data( lle_scurve_data ) 

3. Next, perform lle on lle_scurve_data:

        > X = lle_scurve_data
        > results = lle( X=X , m=2, k=12,  id=TRUE)
        Output
        finding neighbours
        calculating weights
        intrinsic dim: mean=2.47875, mode=2
        computing coordinates  

4. Examine the result with the str and plot function:

 > str( results ) Output List of 4 $ Y :num [1:800, 1:2] -1.586 -0.415 0.896 0.513 1.477 ... $ X :num [1:800, 1:3] 0.955 -0.66 -0.983 0.954 0.958 ... $ choise: NULL $ id :num [1:800] 3 3 2 3 2 2 2 3 3 3 ... > plot( results$Y, ...