/// <summary>
///
/// </summary>
/// <param name="data"></param>
/// <param name="missing"></param>
/// <param name="responses"></param>
/// <param name="pWeight"></param>
/// <returns></returns>
private CvDTree MushroomCreateDTree(CvMat data, CvMat missing, CvMat responses, float pWeight)
{
float[] priors = { 1, pWeight };
CvMat varType = new CvMat(data.Cols + 1, 1, MatrixType.U8C1);
Cv.Set(varType, CvScalar.ScalarAll(CvStatModel.CV_VAR_CATEGORICAL)); // all the variables are categorical
CvDTree dtree = new CvDTree();
CvDTreeParams p = new CvDTreeParams(8, // max depth
10, // min sample count
0, // regression accuracy: N/A here
true, // compute surrogate split, as we have missing data
15, // max number of categories (use sub-optimal algorithm for larger numbers)
10, // the number of cross-validation folds
true, // use 1SE rule => smaller tree
true, // throw away the pruned tree branches
priors // the array of priors, the bigger p_weight, the more attention
// to the poisonous mushrooms
// (a mushroom will be judjed to be poisonous with bigger chance)
);
dtree.Train(data, DTreeDataLayout.RowSample, responses, null, null, varType, missing, p);
// compute hit-rate on the training database, demonstrates predict usage.
int hr1 = 0, hr2 = 0, pTotal = 0;
for (int i = 0; i < data.Rows; i++)
{
CvMat sample, mask;
Cv.GetRow(data, out sample, i);
Cv.GetRow(missing, out mask, i);
double r = dtree.Predict(sample, mask).Value;
bool d = Math.Abs(r - responses.DataArraySingle[i]) >= float.Epsilon;
if (d)
{
if (r != 'p')
hr1++;
else
hr2++;
}
//Console.WriteLine(responses.DataArraySingle[i]);
pTotal += (responses.DataArraySingle[i] == (float)'p') ? 1 : 0;
}
Console.WriteLine("Results on the training database");
Console.WriteLine("\tPoisonous mushrooms mis-predicted: {0} ({1}%)", hr1, (double)hr1 * 100 / pTotal);
Console.WriteLine("\tFalse-alarms: {0} ({1}%)", hr2, (double)hr2 * 100 / (data.Rows - pTotal));
varType.Dispose();
return dtree;
}
