www.gusucode.com > stats 源码程序 matlab案例代码 > stats/CreateKNearestNeighborsTemplateForECOCMulticlassLearningExample.m

    %% Create a _k_-Nearest Neighbors Template for ECOC Multiclass Learning
% Create a nondefault _k_-nearest neighbor template for use in 
% |fitcecoc|.
%%
% Load Fisher's iris data set.

% Copyright 2015 The MathWorks, Inc.

load fisheriris
%%
% Create a template for a 5-nearest neighbor search, and specify to
% standardize the predictors.
t = templateKNN('NumNeighbors',5,'Standardize',1)
%%
% All properties of the template object are empty except for
% |NumNeighbors|, |Method|, |StandardizeData|, and |Type|. When you specify
% |t| as a learner, the software fills in the empty properties with their
% respective default values.
%%
% Specify |t| as a binary learner for an ECOC multiclass model.
Mdl = fitcecoc(meas,species,'Learners',t);
%%
% By default, the software trains |Mdl| using the one-versus-one coding
% design.
%%
% Display the in-sample (resubstitution) misclassification error.
L = resubLoss(Mdl,'LossFun','classiferror')