Compute learning from multilevel clustering classification
E = MCLUSTLCURVE(LABC,LABT)
E = MCLUSTLCURVE(LABC,A)
E = LABC*MCLUSTLCURVE(LABT)
E = LABC*MCLUSTLCURVE(A)
| LABC|| Index array, size [M,K], indices of cluster prototypes for M objects in K clusterings.|
| LABT|| Vector of M elements with true object labels.|
| A|| PRTools labeled dataset used for the clustering.|
| E|| Structure with classification error and numbers of labeled objects, ready to plot by PLOTE |
This routines calls MCLUSTCERR to create a learning curve ready to be plot by PLOTE. This learning curve evaluates active learning in which objects are assigned to the class of cluster prototypes after combining the multilevel clustering.
If no output (E) is requested CLUSTLCURVE calls PLOTE internally and thereby produces automatically a figure with a learning curve.
dset = gendatm(30000);
labc = dset*clustm;
datasets, mappings, knnc, cluste, clusth, clustk, clustkh, clustm, clustf, clustr, dcluste, dclustf, dclusth, dclustk, dclustm, dclustr, clusteval, clustc, clustnum, mclustcerr, plote,
|This file has been automatically generated. If badly readable, use the help-command in Matlab.|