/// <summary>
/// Get the default Decision tree training parameters
/// </summary>
/// <returns>The default Decision tree training parameters</returns>
public static MCvDTreeParams GetDefaultParameter()
{
IntPtr ptr = MlInvoke.CvDTreeParamsCreate();
MCvDTreeParams p = (MCvDTreeParams)Marshal.PtrToStructure(ptr, typeof(MCvDTreeParams));
MlInvoke.CvDTreeParamsRelease(ptr);
return(p);
}
/// <summary>
/// Train the decision tree using the specific traning data
/// </summary>
/// <param name="trainData">The training data. A 32-bit floating-point, single-channel matrix, one vector per row</param>
/// <param name="tflag">data layout type</param>
/// <param name="responses">A floating-point matrix of the corresponding output vectors, one vector per row. </param>
/// <param name="varIdx">Can be null if not needed. When specified, identifies variables (features) of interest. It is a Matrix>int< of nx1</param>
/// <param name="sampleIdx">Can be null if not needed. When specified, identifies samples of interest. It is a Matrix>int< of nx1</param>
/// <param name="varType">The types of input variables</param>
/// <param name="missingMask">Can be null if not needed. When specified, it is an 8-bit matrix of the same size as <paramref name="trainData"/>, is used to mark the missed values (non-zero elements of the mask)</param>
/// <param name="param">The parameters for training the decision tree</param>
/// <returns></returns>
public bool Train(
Matrix<float> trainData,
MlEnum.DATA_LAYOUT_TYPE tflag,
Matrix<float> responses,
Matrix<Byte> varIdx,
Matrix<Byte> sampleIdx,
Matrix<Byte> varType,
Matrix<Byte> missingMask,
MCvDTreeParams param)
{
return MlInvoke.CvDTreeTrain(
_ptr,
trainData.Ptr,
tflag,
responses.Ptr,
varIdx == null ? IntPtr.Zero : varIdx.Ptr,
sampleIdx == null ? IntPtr.Zero : sampleIdx.Ptr,
varType == null ? IntPtr.Zero : varType.Ptr,
missingMask == null ? IntPtr.Zero : missingMask.Ptr,
param);
}
public void TestDTreesMushroom()
{
Matrix<float> data, response;
ReadMushroomData(out data, out response);
//Use the first 80% of data as training sample
int trainingSampleCount = (int)(data.Rows * 0.8);
Matrix<Byte> varType = new Matrix<byte>(data.Cols + 1, 1);
varType.SetValue((byte)MlEnum.VAR_TYPE.CATEGORICAL); //the data is categorical
Matrix<byte> sampleIdx = new Matrix<byte>(data.Rows, 1);
using (Matrix<byte> sampleRows = sampleIdx.GetRows(0, trainingSampleCount, 1))
sampleRows.SetValue(255);
float[] priors = new float[] {1, 0.5f};
GCHandle priorsHandle = GCHandle.Alloc(priors, GCHandleType.Pinned);
MCvDTreeParams param = new MCvDTreeParams();
param.maxDepth = 8;
param.minSampleCount = 10;
param.regressionAccuracy = 0;
param.useSurrogates = true;
param.maxCategories = 15;
param.cvFolds = 10;
param.use1seRule = true;
param.truncatePrunedTree = true;
param.priors = priorsHandle.AddrOfPinnedObject();
using (DTree dtree = new DTree())
{
bool success = dtree.Train(
data,
Emgu.CV.ML.MlEnum.DATA_LAYOUT_TYPE.ROW_SAMPLE,
response,
null,
sampleIdx,
varType,
null,
param);
if (!success) return;
double trainDataCorrectRatio = 0;
double testDataCorrectRatio = 0;
for (int i = 0; i < data.Rows; i++)
{
using (Matrix<float> sample = data.GetRow(i))
{
double r = dtree.Predict(sample, null, false).value;
r = Math.Abs(r - response[i, 0]);
if (r < 1.0e-5)
{
if (i < trainingSampleCount)
trainDataCorrectRatio++;
else
testDataCorrectRatio++;
}
}
}
trainDataCorrectRatio /= trainingSampleCount;
testDataCorrectRatio /= (data.Rows - trainingSampleCount);
Trace.WriteLine(String.Format("Prediction accuracy for training data :{0}%", trainDataCorrectRatio*100));
Trace.WriteLine(String.Format("Prediction accuracy for test data :{0}%", testDataCorrectRatio*100));
}
priorsHandle.Free();
}
public static extern bool CvDTreeTrain(
IntPtr model,
IntPtr trainData,
MlEnum.DATA_LAYOUT_TYPE tflag,
IntPtr responses,
IntPtr varIdx,
IntPtr sampleIdx,
IntPtr varType,
IntPtr missingMask,
MCvDTreeParams param);
