clusteringOutput-class     package:MLInterfaces     R Documentation

_c_o_n_t_a_i_n_e_r _f_o_r _c_l_u_s_t_e_r_i_n_g _o_u_t_p_u_t_s _i_n _u_n_i_f_o_r_m _s_t_r_u_c_t_u_r_e

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

     container for clustering outputs in uniform structure

_O_b_j_e_c_t_s _f_r_o_m _t_h_e _C_l_a_s_s:

     Objects can be created by calls of the form
     'new("clusteringOutput", ...)'.

_S_l_o_t_s:


     '_p_a_r_t_i_t_i_o_n': Object of class '"integer"', labels for observations
          as clustered 

     '_s_i_l_h_o_u_e_t_t_e': Object of class '"silhouette"', structure from
          Rousseeuw cluster package measuring cluster membership
          strength per observation

     '_d_i_s_t_F_u_n': Object of class '"environment"' not in use 

     '_p_r_c_o_m_p': Object of class '"prcompObj"' a wrapped instance of
          stats package prcomp output 

     '_c_a_l_l': Object of class '"call"' for auditing 

     '_l_e_a_r_n_e_r_S_c_h_e_m_a': Object of class '"learnerSchema"', a formal
          object indicating the package, function, and other attributes
          of the clustering algorithm employed to generate this object  

     '_R_O_b_j_e_c_t': Object of class '"ANY"', the unaltered output of the
          function called according to learnerSchema 

     '_c_o_n_v_e_r_t_e_r': for auditing purposes

_M_e_t_h_o_d_s:


     _R_O_b_j_e_c_t 'signature(x = "clusteringOutput")': extract the unaltered
          output of the R function or method called according to
          learnerSchema 

     _p_l_o_t 'signature(x = "clusteringOutput", y = "ANY")':  a 4-panel
          plot showing features of the clustering, including the scree
          plot for a principal components transformation and a display
          of the partition in PC1xPC2 plane.  For a clustering method
          that does not have a native plot procedure, such as kmeans,
          the parameter y should be bound to a data frame or matrix
          with feature data for all records; an image plot of robust
          feature z-scores (z=(x-median(x))/mad(x)) and the cluster
          indices is produced in the northwest panel.  

     _s_h_o_w 'signature(object = "clusteringOutput")': concise report 

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

     VJ Carey <stvjc@channing.harvard.edu>

_E_x_a_m_p_l_e_s:

     showClass("clusteringOutput")

