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

    %% Find Good Lasso Penalty Using _k_-fold Margins
% To determine a good lasso-penalty strength for a linear classification
% model that uses a logistic regression learner, compare distributions of
% _k_-fold margins.
%%
% Load the NLP data set.  Preprocess the data as in
% <docid:stats_ug.bu622gg>.
load nlpdata
Ystats = Y == 'stats';
X = X'; 
%%
% Create a set of 11 logarithmically-spaced regularization strengths from
% $10^{-8}$ through $10^{1}$.
Lambda = logspace(-8,1,11);  
%%
% Cross-validate a binary, linear classification model using 5-fold
% cross-validation and that uses 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)
%%
% |CVMdl| is a |ClassificationPartitionedLinear| model.  Because |fitclinear|
% implements 5-fold cross-validation, |CVMdl| contains 5
% |ClassificationLinear| models that the software trains on each fold.
%%
% Estimate the _k_-fold margins for each regularization strength.
m = kfoldMargin(CVMdl);
size(m)
%%
% |m| is a 31572-by-11 matrix of cross-validated margins for each
% observation. The columns correspond to the regularization strengths.
%%
% Plot the _k_-fold margins for each regularization strength.  Because
% logistic regression scores are in [0,1], margins are in [-1,1]. Rescale
% the margins to help identify the regularization strength that maximizes
% the margins over the grid.
figure;
boxplot(10000.^m)
ylabel('Exponentiated test-sample margins')
xlabel('Lambda indices')
%%
% Several values of |Lambda| yield _k_-fold margin distributions that are
% compacted near $10000^1$.  Higher values of lambda lead to predictor
% variable sparsity, which is a good quality of a classifier.
%%
% Choose the regularization strength that occurs just before
% the centers of the _k_-fold margin distributions start decreasing.
LambdaFinal = Lambda(5);
%%
% Train a linear classification model using the entire data set and specify
% the desired regularization strength.
MdlFinal = fitclinear(X,Ystats,'ObservationsIn','columns',...
    'Learner','logistic','Solver','sparsa','Regularization','lasso',...
    'Lambda',LambdaFinal);
%%
% To estimate labels for new observations, pass |MdlFinal| and the new data
% to |predict|.