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

    %% Find Good Lasso Penalty Using _k_-fold Classification Loss
% To determine a good lasso-penalty strength for a linear classification
% model that uses a logistic regression learner, compare test-sample
% classification error rates.
%%
% Load the NLP data set.  Preprocess the data as in
% <docid:stats_ug.bu7kw58-1>.
load nlpdata
Ystats = Y == 'stats';
X = X'; 
%%
% Create a set of 11 logarithmically-spaced regularization strengths from
% $10^{-6}$ through $10^{0.5}$.
Lambda = logspace(-6,-0.5,11);  
%%
% Cross-validate binary, linear classification models using 5-fold
% cross-validation, and that use each of the regularization strengths.
% Solve the objective function using SpaRSA. Lower the tolerance on the
% gradient of the objective function to |1e-8|.
%
rng(10); % For reproducibility
CVMdl = fitclinear(X,Ystats,'ObservationsIn','columns',...
    'KFold',5,'Learner','logistic','Solver','sparsa',...
    'Regularization','lasso','Lambda',Lambda,'GradientTolerance',1e-8)
%%
% Extract a trained linear classification model.
Mdl1 = CVMdl.Trained{1}
%%
% |Mdl1| is a |ClassificationLinear| model object. Because |Lambda| is a
% sequence of regularization strengths, you can think of |Mdl| as 11
% models, one for each regularization strength in |Lambda|.
%%
% Estimate the cross-validated classification error.
ce = kfoldLoss(CVMdl);
%%
% Because there are 11 regularization strengths, |ce| is a 1-by-11 vector
% of classification error rates.
%%
% Higher values of |Lambda| lead to predictor variable sparsity, which is a
% good quality of a classifier.  For each regularization strength, train a
% linear classification model for each regularization strength using the
% entire data set and the same options as when you cross-validated the
% models.  Determine the number of nonzero coefficients per model.
Mdl = fitclinear(X,Ystats,'ObservationsIn','columns',...
    'Learner','logistic','Solver','sparsa','Regularization','lasso',...
    'Lambda',Lambda,'GradientTolerance',1e-8);
numNZCoeff = sum(Mdl.Beta~=0);

%%
% In the same figure, plot the cross-validated, classification error rates
% and frequency of nonzero coefficients for each regularization strength.
% Plot all variables on the log scale.
figure;
[h,hL1,hL2] = plotyy(log10(Lambda),log10(ce),...
    log10(Lambda),log10(numNZCoeff)); 
hL1.Marker = 'o';
hL2.Marker = 'o';
ylabel(h(1),'log_{10} classification error')
ylabel(h(2),'log_{10} nonzero-coefficient frequency')
xlabel('log_{10} Lambda')
title('Test-Sample Statistics')
hold off
%%
% Choose the indes of the regularization strength that balances predictor
% variable sparsity and low classification error.  In this case, a value
% between $10^{-4}$ to $10^{-1}$ should suffice.
idxFinal = 7;
%%
% Select the model from |Mdl| with the chosen regularization strength.
MdlFinal = selectModels(Mdl,idxFinal);
%%
% |MdlFinal| is a |ClassificationLinear| model containing one
% regularization strength. To estimate labels for new observations, pass
% |MdlFinal| and the new data to |predict|.