Posted By

benjamin on 10/29/09

Tagged

support

Versions (?)

Last Edited at 10/29/09 02:09pm

Statistics

Viewed 967 times

Favorited by 0 user(s)

svmlight-wrapper.m

/ Published in: MatLab

please leave comments on my blog. you need awk installed (obviously). Files are stored in the "/tmp/" directory, if you are on windows you might want to change that to the current directory (".").

Expand | Embed | Plain Text

Copy this code and paste it in your HTML

function Y=svmlight(training,test,params)
% (very) simple wrapper for svmlight
% write matrices in sparse format to data file that can be used by svmlight.
% Columns are variables, rows are observations. 
% It is assumed that the first column of the matrix is the target. Targets are elements of {-1,1}.
%
% These steps are made: 
% 1. output matlab matrix to text file
% 2. format text file for svm (awk)
% 3. create classification model (svm_learn)
% 4. apply classification model (svm_classify)
%
% All files are written in the /tmp/ directory, if you are on windows you might want to change that to the current directory ("."). Obviously you need awk installed for this function to work. Assumes svm-light perf is installed in the svmlight subdirectory (change path if necessary). 
%
% Example: 
% Y=svmlight(data(traininds,:),data(testinds,:),'-c 1 -w 3 -l 10 ');
% (if you set parameters for svmlight don't forget to include the learning options!)
%
% (c) Benjamin Auffarth, 2008
% licensed under CC-by-sa (creative commons attribution share-alike)
if nargin<3
  params='-c 1 -# 1 -w 3 -l 10 ';
end
trainfile=sparse_write(training);
[s,w]=system(['./svmlight/svm_perf_learn ' params trainfile '.svm2 ' trainfile '.model']);
if s 
  disp('error in executing smv-light!');w,
  error('svm_perf_learn not found or returned error');
end
testfile=sparse_write(test);
[s,w]=system(['./svmlight/svm_perf_classify -v 0  ' testfile '.svm2 ' trainfile '.model ' testfile '.dat']);
if s 
  disp('error in executing smv-light!');w,
  error('svm_perf_classify not found or returned error');
end
Y=dlmread([testfile '.dat']);
end
 
function fname=sparse_write(M)
  [a,fname]=system('date +/tmp/_svm_%F_-%H:%M_%S%N');
  fname=fname(1:end-1); % get rid of newline character
  dlmwrite([fname '.svm1'],M,'delimiter',' '); 
  system(['awk -F" " ''{printf $1" "; for (i=2;i<=NF;i++) {printf i-1":"$i " "}; print ""}'' ' fname '.svm1 > ' fname '.svm2']);
end

URL: http://www.myoutsourcedbrain.com/2008/11/matlab-svmlight-interface.html

Report this snippet Tweet

Comments

Subscribe to comments

Comment:

You need to login to post a comment.