/// <summary>
/// Moves an example from the training set to
/// the testing set. If the supplied example number
/// is out of range no example is moved.
/// </summary>
public void moveToTestingSet(int exampleNum)
{
if (exampleNum < 0 || exampleNum > (TrainingSet.Count - 1))
{
return;
}
TestingSet.Add((int[])TrainingSet.ElementAt(exampleNum));
TrainingSet.RemoveAt(exampleNum);
}
/// <summary>
/// Creates a random testing dataset. Calling this
/// method will destroy any previously built testing set.
/// </summary>
/// <param name="percentage">Percentage of the entire dataset to use for testing.</param>
/// <param name="balanced">to create a balanced
/// testing set, where the testing set and the
/// remaining training set have the same proportion
/// of each class.</param>
public void createRndTestSet(int percentage, bool balanced)
{
if (percentage < 0 || percentage > 100)
{
throw new Exception("Percentage value out of range.");
}
// Move any examples that are part of the current testing
// set back to the training set.
for (int i = 0; i < TestingSet.Count; i++)
{
TrainingSet.Add((int[])TestingSet[i]);
}
TestingSet.Clear();
// Calculate the number of examples that should be
// in the testing set.
int totalNumExamples = TrainingSet.Count;
int numTestingExamples = (int)Math.Round(totalNumExamples * ((float)percentage) / 100.0f);
Random rand = new Random();
// If the set doesn't have to be balanced, then just
// pick examples at random.
if (!balanced)
{
for (int i = 0; i < numTestingExamples; i++)
{
int temp = rand.Next(TrainingSet.Count);
TestingSet.Add((int[])TrainingSet[temp]);
TrainingSet.RemoveAt(temp);
}
}
else
{
// We have the target value distribution for the dataset,
// so reference it.
for (int i = 0; i < TargetSums.Length; i++)
{
int numExamplesToMove =
(int)Math.Round(TargetSums[i] / ((float)totalNumExamples) * numTestingExamples);
for (int j = 0; j < numExamplesToMove; j++)
{
// Attempt to randomly pick examples from the
// dataset that have the required target classification.
int[] example = null;
while (true)
{
example = (int[])TrainingSet[rand.Next(TrainingSet.Count)];
if (example[0] == i)
{
break;
}
}
int temp = TrainingSet.IndexOf(example);
TestingSet.Add((int[])TrainingSet[temp]);
TrainingSet.RemoveAt(temp);
}
}
}
}
