Choosing the best k value for the k-NN classification of the WDBC data set

The process determines the best value for the parameter k for the k-NN classification of the Breast Cancer Wisconsin (Diagnostic) data set available in the UCI Machine Learning Repository. The optimal k is computed by using 10-fold cross-validation. (To get better results each cross-validation is repeated 10 times and the averages of the runs are considered.) Finally, a k-NN classifier is built and evaluated on the entire data set using the optimal k. During the process the resulting average performances are logged for each k.