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

    %% Select Naive Bayes Classifier Features by Comparing Test Sample Edges
% The classifier edge measures the average of the classifier margins. One
% way to perform feature selection is to compare test sample edges from
% multiple models.  Based solely on this criterion, the classifier with the
% highest edge is the best classifier.
%%
% Load Fisher's iris data set.

% Copyright 2015 The MathWorks, Inc.

load fisheriris
X = meas;    % Predictors
Y = species; % Response
rng(1);
%% 
% Partition the data set into training and test sets.  Specify a 30%
% holdout sample for testing.
Partition = cvpartition(Y,'Holdout',0.30);
testInds = test(Partition); % Indices for the test set
XTest = X(testInds,:);
YTest = Y(testInds,:);
%%
% |Partition| defines the data set partition.
%%
% Define these two data sets:
%
% * |fullX| contains all predictors.
% * |partX| contains the last two predictors.
%
fullX = X;
partX = X(:,3:4);
%%
% Train naive Bayes classifiers for each predictor set.  Specify the
% partition definition.
FCVMdl = fitcnb(fullX,Y,'CVPartition',Partition);
PCVMdl = fitcnb(partX,Y,'CVPartition',Partition);
FCMdl = FCVMdl.Trained{1};
PCMdl = PCVMdl.Trained{1};
%%
% |FCVMdl| and |PCVMdl| are
% |ClassificationPartitionedModel| classifiers. They contain the property
% |Trained|, which is a 1-by-1 cell array holding a
% |CompactClassificationNaiveBayes| classifier that the software trained using the
% training set.
%%
% Estimate the test sample edge for each classifier.
fullEdge = edge(FCMdl,XTest,YTest)
partEdge = edge(PCMdl,XTest(:,3:4),YTest)
%%
% The test-sample edges of the classifiers are nearly the same.  However,
% the model trained using two predictors (|PCMdl|) is less complex.