koplsDemo               package:kopls               R Documentation

_K-_O_P_L_S _d_e_m_o_n_s_t_r_a_t_i_o_n _p_r_o_c_e_d_u_r_e

_D_e_s_c_r_i_p_t_i_o_n:

     This script contains a demonstration of the functionality in the
     'kopls' package using a simulated data set.

_U_s_a_g_e:

     demo(koplsDemo)

_D_e_t_a_i_l_s:

     The data set is represented by 1000 spectral variables from two
     different classes and is available in the an attached data set.
     The demonstration essentially consists of two main steps.

     The first step is to demonstrate how K-OPLS handles the model
     evaluation (using cross-validation), model building and subsequent
     classification of external data from a non-linear data set. The
     second step is to demonstrate how K-OPLS works in the presence of
     response-independent ('Y'-orthogonal) variation, using the same
     data set but with a strong systematic class-specific disturbance
     added.

     The 'koplsExample' data set contains the following objects:

       'Xtr'      The training data matrix, with 400 observations
                  and 1000 spectral variables.
       'Xte'      The test data matrix, with 400 observations
                  and 1000 spectral variables.
       'Xtro'     Same data as 'Xtr', but with class-specific
                  systematic noise added.
       'Xteo'     Same data as 'Xte', but with class-specific
                  systematic noise added.
       'Ytr'      A binary matrix of class assignments for the
                  training data.
       'Yte'      A binary matrix of class assignments for the
                  test data.
       'pch.vec'  A vector with character indices
                  (for plotting).
       'col.vec'  A vector with colors (for plotting).

_A_u_t_h_o_r(_s):

     Max Bylesjo and Mattias Rantalainen

_R_e_f_e_r_e_n_c_e_s:

     Rantalainen M, Bylesjo M, Cloarec O, Nicholson JK, Holmes E and
     Trygg J. *Kernel-based orthogonal projections to latent structures
     (K-OPLS)*, _J Chemometrics_ 2007; 21:376-385.
     doi:10.1002/cem.1071.

