public static extern bool CvRTreesTrain(
IntPtr model,
IntPtr trainData,
MlEnum.DataLayoutType tFlag,
IntPtr responses,
IntPtr varIdx,
IntPtr sampleIdx,
IntPtr varType,
IntPtr missingMask,
ref MCvRTParams param);
public static extern bool CvRTreesTrain(
IntPtr model,
IntPtr trainData,
MlEnum.DATA_LAYOUT_TYPE tFlag,
IntPtr responses,
IntPtr varIdx,
IntPtr sampleIdx,
IntPtr varType,
IntPtr missingMask,
MCvRTParams param);
/// <summary>
/// Train the random 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 random 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,
MCvRTParams param)
{
return(MlInvoke.CvRTreesTrain(
_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 TestERTreesLetterRecognition()
{
Matrix <float> data, response;
ReadLetterRecognitionData(out data, out response);
int trainingSampleCount = (int)(data.Rows * 0.8);
Matrix <Byte> varType = new Matrix <byte>(data.Cols + 1, 1);
varType.SetValue((byte)MlEnum.VarType.Numerical); //the data is numerical
varType[data.Cols, 0] = (byte)MlEnum.VarType.Categorical; //the response is catagorical
MCvRTParams param = new MCvRTParams();
param.maxDepth = 10;
param.minSampleCount = 10;
param.regressionAccuracy = 0.0f;
param.useSurrogates = false;
param.maxCategories = 15;
param.priors = IntPtr.Zero;
param.calcVarImportance = true;
param.nactiveVars = 4;
param.termCrit = new MCvTermCriteria(100, 0.01f);
param.termCrit.Type = Emgu.CV.CvEnum.TermCritType.Iter;
using (ERTrees forest = new ERTrees())
{
bool success = forest.Train(
data.GetRows(0, trainingSampleCount, 1),
Emgu.CV.ML.MlEnum.DataLayoutType.RowSample,
response.GetRows(0, trainingSampleCount, 1),
null,
null,
varType,
null,
param);
if (!success)
{
return;
}
#if !NETFX_CORE
String fileName = Path.Combine(Path.GetTempPath(), "ERTree.xml");
forest.Save(fileName);
if (File.Exists(fileName))
{
File.Delete(fileName);
}
#endif
double trainDataCorrectRatio = 0;
double testDataCorrectRatio = 0;
for (int i = 0; i < data.Rows; i++)
{
using (Matrix <float> sample = data.GetRow(i))
{
double r = forest.Predict(sample, null);
r = Math.Abs(r - response[i, 0]);
if (r < 1.0e-5)
{
if (i < trainingSampleCount)
{
trainDataCorrectRatio++;
}
else
{
testDataCorrectRatio++;
}
}
}
}
trainDataCorrectRatio /= trainingSampleCount;
testDataCorrectRatio /= (data.Rows - trainingSampleCount);
EmguAssert.WriteLine(String.Format("Prediction accuracy for training data :{0}%", trainDataCorrectRatio * 100));
EmguAssert.WriteLine(String.Format("Prediction accuracy for test data :{0}%", testDataCorrectRatio * 100));
}
}
public void TestRTreesLetterRecognition()
{
Matrix <float> data, response;
ReadLetterRecognitionData(out data, out response);
int trainingSampleCount = (int)(data.Rows * 0.8);
Matrix <Byte> varType = new Matrix <byte>(data.Cols + 1, 1);
varType.SetValue((byte)MlEnum.VarType.Numerical); //the data is numerical
varType[data.Cols, 0] = (byte)MlEnum.VarType.Categorical; //the response is catagorical
Matrix <byte> sampleIdx = new Matrix <byte>(data.Rows, 1);
using (Matrix <byte> sampleRows = sampleIdx.GetRows(0, trainingSampleCount, 1))
sampleRows.SetValue(255);
MCvRTParams param = new MCvRTParams();
param.maxDepth = 10;
param.minSampleCount = 10;
param.regressionAccuracy = 0.0f;
param.useSurrogates = false;
param.maxCategories = 15;
param.priors = IntPtr.Zero;
param.calcVarImportance = true;
param.nactiveVars = 4;
param.termCrit = new MCvTermCriteria(100, 0.01f);
param.termCrit.Type = Emgu.CV.CvEnum.TermCritType.Iter;
using (RTrees forest = new RTrees())
{
bool success = forest.Train(
data,
Emgu.CV.ML.MlEnum.DataLayoutType.RowSample,
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 = forest.Predict(sample, null);
r = Math.Abs(r - response[i, 0]);
if (r < 1.0e-5)
{
if (i < trainingSampleCount)
{
trainDataCorrectRatio++;
}
else
{
testDataCorrectRatio++;
}
}
}
}
trainDataCorrectRatio /= trainingSampleCount;
testDataCorrectRatio /= (data.Rows - trainingSampleCount);
StringBuilder builder = new StringBuilder("Variable Importance: ");
using (Matrix <float> varImportance = forest.VarImportance)
{
for (int i = 0; i < varImportance.Cols; i++)
{
builder.AppendFormat("{0} ", varImportance[0, i]);
}
}
EmguAssert.WriteLine(String.Format("Prediction accuracy for training data :{0}%", trainDataCorrectRatio * 100));
EmguAssert.WriteLine(String.Format("Prediction accuracy for test data :{0}%", testDataCorrectRatio * 100));
EmguAssert.WriteLine(builder.ToString());
}
}
public void TestERTreesLetterRecognition()
{
Matrix <float> data, response;
ReadLetterRecognitionData(out data, out response);
int trainingSampleCount = (int)(data.Rows * 0.8);
Matrix <Byte> varType = new Matrix <byte>(data.Cols + 1, 1);
varType.SetValue((byte)MlEnum.VAR_TYPE.NUMERICAL); //the data is numerical
varType[data.Cols, 0] = (byte)MlEnum.VAR_TYPE.CATEGORICAL; //the response is catagorical
MCvRTParams param = new MCvRTParams();
param.maxDepth = 10;
param.minSampleCount = 10;
param.regressionAccuracy = 0.0f;
param.useSurrogates = false;
param.maxCategories = 15;
param.priors = IntPtr.Zero;
param.calcVarImportance = true;
param.nactiveVars = 4;
param.termCrit = new MCvTermCriteria(100, 0.01f);
param.termCrit.type = Emgu.CV.CvEnum.TERMCRIT.CV_TERMCRIT_ITER;
using (ERTrees forest = new ERTrees())
{
bool success = forest.Train(
data.GetRows(0, trainingSampleCount, 1),
Emgu.CV.ML.MlEnum.DATA_LAYOUT_TYPE.ROW_SAMPLE,
response.GetRows(0, trainingSampleCount, 1),
null,
null,
varType,
null,
param);
forest.Save("ERTree.xml");
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 = forest.Predict(sample, null);
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));
}
}
