Here is a set of sample input data and the associated labels. Once you have installed the Gist software, you can train an SVM using a command line like this:

gist-train-svm -train sample.mtx -class sample.labels > sample.weightsThe file sample.weights contains SVM weights associated with each example. Using these weights, you can classify a test data set like this:gist-classify -train sample.mtx -learned sample.weights -test test.mtx > test.predictHere are the resulting predictions. You can assess the accuracy of your predictions, using these labels and this command line:gist-score-svm -test test.labels test.predict sample.weightsHere is the resulting output:Number of training examples: 1644 (24 positive, 1620 negative) Number of support vectors: 60 (14 positive, 46 negative) 3.65% Number of bounded support vectors: 6 (5 positive, 1 negative) 0.365% Training results: FP=0 FN=3 TP=21 TN=1620 Training ROC: 0.99874 Test results: FP=12 FN=1 TP=9 TN=801 Test ROC: 0.99397See the documentation for gist-core-svm for an explanation of these results.

Gist