/// <summary>
/// Tests the case c using classification (majority vote) against the ensemble learner and assumes
/// that its last attribute is the target label. Also requires the target attribute so then it knows
/// how many variants there are. Unlike the ID3 node, this is a full
/// learner or something, so it actually contains its own testing functions.
/// </summary>
/// <param name="c"></param>
/// <returns></returns>
public int TestEnsembleClassificaiton(Case c, DAttribute target)
{
double[] voting = new double[target.numVariants()];
for (int i = 0; i < VoteWeights.Length; i++)
{
int currentResult = ID3Tools.TestWithTree(c, Trees[i]);
voting[currentResult] += VoteWeights[i]; //add the tree's voting power to the bucket for its answer
}
//find the majority vote in the voting pool
int max = -1;
double highest = -1;
for (int i = 0; i < target.numVariants(); i++)
{
if (voting[i] > highest)
{
max = i;
highest = voting[i];
}
}
//max should contain the winning variant number for the attribute.
return(max);
}
/// <summary>
/// Calculates the Final label (output, found in data as #attributeNum) purity for each variant of a dataset and returns it.
/// </summary>
/// <param name="Data"></param>
/// <returns></returns>
public static double[] GetLabelDistribution(List <Case> Data, DAttribute attribute)
{
int numVars = attribute.numVariants();
double[] output = new double[numVars];
double sumWeight = 0;
foreach (Case c in Data)
{
int AVal = (int)c.AttributeVals[attribute.ID]; // the varID of the attribute value held by C
if (AVal <= -1)
{
continue; //value is undefined. proceed to the next value
}
output[AVal] += c.getWeight(); //increment the corresponding attribute variant by the case's weight (summing number of hits for each)
sumWeight += c.getWeight();
}
for (int i = 0; i < numVars; i++) //divide each by count to get the relative proportion of the label as oppsed to the count.
{
output[i] = output[i] / sumWeight;
}
return(output);
}
