Skip to main content

Imbalanced set problems: Tools review to solve


1. Weka (Java Based)


  • You can subsample the majority class (try the filter SpreadSubsample ,
    GSVM-RU ).  
  • You can oversample the minority class, creating synthetic examples (try SMOTE).  
  • You can make your classifier cost sensitive (try the metaclassifier CostSensitiveClassifier).  
http://weka.wikispaces.com/space/content?tag=cost-sensitive

Each of the methods has it's own strengths and weaknesses, refer to the papers referenced in the documentation of each one.  If you use any of these and you need accurate probability estimates, you can use an isotonic regression to calibrate the output.

2. MATLAB


 3. KELL tool (Java Based)

http://sci2s.ugr.es/keel/software/prototypes/openVersion/Algorithms_20130703.pdf

4. LASVM

http://leon.bottou.org/projects/lasvm

publication: Fast Kernel Classifiers with Online and Active Learning



Comments

Post a Comment

Popular posts from this blog

MATLAB cross validation

// use built-in function samplesize = size( matrix , 1); c = cvpartition(samplesize,  'kfold' , k); % return the indexes on each fold ///// output in matlab console K-fold cross validation partition              N: 10    NumTestSets: 4      TrainSize: 8  7  7  8       TestSize: 2  3  3  2 ////////////////////// for i=1 : k    trainIdxs = find(training(c,i) ); %training(c,i);  // 1 means in train , 0 means in test    testInxs  = find(test(c,i)       ); % test(c,i);       // 1 means in test , 0 means in train    trainMatrix = matrix (  matrix(trainIdxs ), : );    testMatrix  = matrix (  matrix(testIdxs  ), : ); end //// now calculate performance %%  calculate performance of a partiti...
5 comments
Read more

MATLAB confusion matrix

%  test_class  & predicted_class must be same dimension % 'order' - describes the order of label. Here labels are 'g' as positive and 'h' as negative [C,order] = confusionmat( test_class(1: noSampleTest), predicted_class, 'order', ['g' ;'h'] ) tp = C(1,1); fn = C(1,2); fp = C(2,1); tn = C(2,2); sensitivity = tp /( tp + fn ) specificity = tn /( fp + tn ) accuracy = (tp+tn) / (tp+fn+fp+tn) tpr = sensitivity fpr = 1-specificity precision = tp /( tp + fp ) fVal = (2*tpr*precision)/(tpr+precision)
6 comments
Read more

Feature subset selection Using Genetic Algorithm in MATLAB

function callGeneticAlgo global mat global trainInd global testInd [trainInd,~,testInd] = dividerand(1420,0.7,0,0.3); global counter global errList counter = 1; errList = []; fileName=  '../features/alltopPNPDMF.feature' ; mat = load(fileName); [x,fval,exitflag,output,population,score] = gaFeaSelection(1588,100,10800); % param1 = #feature excludig label % param2 =  population size % param3 = sec to test (3 hour = 10800 sec) dlmwrite('selected.GA',x,'delimiter','\n'); display('Done'); end function [x,fval,exitflag,output,population,score] = gaFeaSelection (nvars,PopulationSize_Data,TimeLimit_Data) % This is an auto generated MATLAB file from Optimization Tool. % Start with the default options options = gaoptimset; % Modify options setting options = gaoptimset(options,'PopulationType', 'bitString'); options = gaoptimset(options,'PopulationSize', PopulationSize_Data); options = gaoptimset(options,'TimeLimit', T...
2 comments
Read more