Write a Python or Perl program that determines the best regularization 
value from the set

{ 10^-8, 10^-7, 10^-6, 10^-5, .0001, .001, .01, .1, 1, 10, 100 }

for the linear support vector machine. Use the svm_learn and svm_classify 
programs from the SVM-light software suite.

The input would be a dataset with all specified labels in the same format as 
given earlier. Your program would create 10 random training validation splits 
and for each split run svm_learn with the above values of C. It would then 
output the value of C that has the lowest average balanced error along
with the error.
 
For example for the breast cancer dataset the cross-validated value would be 
100 with average error of 5%. You may not have the exact same answer due to 
different splits but it should be in the ballpark.

Submit your assignment by copying it into the directory
/afs/cad/courses/ccs/f14/cs/675/001/<ucid>.
For example if your ucid is abc12 then copy your Perl script into 
/afs/cad/courses/ccs/f14/cs/675/001/abc12.

Submit a hardcopy in class as well.

Your completed script is due before 2:30pm on Nov 18th 2014. Submit a hardcopy 
in class. 

Usman