MCRconfusion           package:MCRestimate           R Documentation

_S_u_m_m_a_r_y _t_a_b_l_e_s _f_o_r _M_C_R_e_s_t_i_m_a_t_e _o_b_j_e_c_t_s

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

     'MCRwrongsamples' returns a matrix with all the samples that have
     a higher frequency of being predicted as a member of a wrong class
     than of the correct class for at least one classification method.
     'MCRconfusion' summarizes the result of the vote matices

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

     MCRwrongsamples(x,
              col.names=names(x),
              rownames.from.object=TRUE,
              subgroup=NULL,
              freq=FALSE)

     MCRconfusion(x,
                  col.names=names(x),
                  row.names=NULL)     

_A_r_g_u_m_e_n_t_s:

       x: List of objects of S3 class 'MCRestimate'

col.names: Vector of strings used for column names. The length must
          match the number of objects in 'x'

rownames.from.object: Logical. If TRUE then the sample names of the
          'MCRestimate' object in 'x' are used as row names

subgroup: Logical. If TRUE then only the samples which belongs to the
          specified group are listed in the table

    freq: Logical. If TRUE then the frequency with which each sample in
          the table has been misclassified will be printed.

row.names: Vector of strings used for row names. If not specified the
          names of the groups are used

_V_a_l_u_e:

     'MCRwrongsamples' returns a matrix and 'MCRconfusion' returns a
     confusion matrix.

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

     Markus Ruschhaupt <URL: mailto:m.ruschhaupt@dkfz.de>

_S_e_e _A_l_s_o:

     'MCRestimate'

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

     library(MCRestimate)
     library(golubEsets)
     data(Golub_Train)
     exSet <- Golub_Train[1:500,]
     result1 <- MCRestimate(exSet,"ALL.AML",classification.fun="RF.wrap",cross.outer=3,cross.repeat=2)
     result2 <- MCRestimate(exSet,"ALL.AML",classification.fun="PAM.wrap",poss.parameters=list(threshold=c(0.5,1)),cross.inner=3,cross.outer=3,cross.repeat=2)
     MCRwrongsamples(list(result1,result2),subgroup="AML",col.names=c("Random Forest","PAM"))
     MCRconfusion(list(result1,result2),col.names=c("Random Forest","PAM"))

