public override IEnumerable <double> GetEstimatedClassValues(IDataset dataset, IEnumerable <int> rows)
{
double[,] inputData = dataset.ToArray(AllowedInputVariables, rows);
RandomForestUtil.AssertInputMatrix(inputData);
int n = inputData.GetLength(0);
int columns = inputData.GetLength(1);
double[] x = new double[columns];
double[] y = new double[RandomForest.innerobj.nclasses];
for (int row = 0; row < n; row++)
{
for (int column = 0; column < columns; column++)
{
x[column] = inputData[row, column];
}
alglib.dfprocess(randomForest, x, ref y);
// find class for with the largest probability value
int maxProbClassIndex = 0;
double maxProb = y[0];
for (int i = 1; i < y.Length; i++)
{
if (maxProb < y[i])
{
maxProb = y[i];
maxProbClassIndex = i;
}
}
yield return(classValues[maxProbClassIndex]);
}
}
public static RandomForestModel CreateRegressionModel(IRegressionProblemData problemData, IEnumerable <int> trainingIndices, int nTrees, double r, double m, int seed,
out double rmsError, out double outOfBagRmsError, out double avgRelError, out double outOfBagAvgRelError)
{
var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
double[,] inputMatrix = problemData.Dataset.ToArray(variables, trainingIndices);
alglib.dfreport rep;
var dForest = RandomForestUtil.CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, 1, out rep);
rmsError = rep.rmserror;
outOfBagRmsError = rep.oobrmserror;
avgRelError = rep.avgrelerror;
outOfBagAvgRelError = rep.oobavgrelerror;
return(new RandomForestModel(problemData.TargetVariable, dForest, seed, problemData, nTrees, r, m));
}
public IEnumerable <double> GetEstimatedVariances(IDataset dataset, IEnumerable <int> rows)
{
double[,] inputData = dataset.ToArray(AllowedInputVariables, rows);
RandomForestUtil.AssertInputMatrix(inputData);
int n = inputData.GetLength(0);
int columns = inputData.GetLength(1);
double[] x = new double[columns];
double[] ys = new double[this.RandomForest.innerobj.ntrees];
for (int row = 0; row < n; row++)
{
for (int column = 0; column < columns; column++)
{
x[column] = inputData[row, column];
}
alglib.dforest.dfprocessraw(RandomForest.innerobj, x, ref ys);
yield return(ys.VariancePop());
}
}
public IEnumerable <double> GetEstimatedValues(IDataset dataset, IEnumerable <int> rows)
{
double[,] inputData = dataset.ToArray(AllowedInputVariables, rows);
RandomForestUtil.AssertInputMatrix(inputData);
int n = inputData.GetLength(0);
int columns = inputData.GetLength(1);
double[] x = new double[columns];
double[] y = new double[1];
for (int row = 0; row < n; row++)
{
for (int column = 0; column < columns; column++)
{
x[column] = inputData[row, column];
}
alglib.dfprocess(RandomForest, x, ref y);
yield return(y[0]);
}
}
internal static alglib.decisionforest CreateRandomForestModel(int seed, double[,] inputMatrix, int nTrees, double r, double m, int nClasses, out alglib.dfreport rep)
{
RandomForestUtil.AssertParameters(r, m);
RandomForestUtil.AssertInputMatrix(inputMatrix);
int info = 0;
alglib.math.rndobject = new System.Random(seed);
var dForest = new alglib.decisionforest();
rep = new alglib.dfreport();
int nRows = inputMatrix.GetLength(0);
int nColumns = inputMatrix.GetLength(1);
int sampleSize = Math.Max((int)Math.Round(r * nRows), 1);
int nFeatures = Math.Max((int)Math.Round(m * (nColumns - 1)), 1);
alglib.dforest.dfbuildinternal(inputMatrix, nRows, nColumns - 1, nClasses, nTrees, sampleSize, nFeatures, alglib.dforest.dfusestrongsplits + alglib.dforest.dfuseevs, ref info, dForest.innerobj, rep.innerobj);
if (info != 1)
{
throw new ArgumentException("Error in calculation of random forest model");
}
return(dForest);
}
public static RandomForestModel CreateClassificationModel(IClassificationProblemData problemData, IEnumerable <int> trainingIndices, int nTrees, double r, double m, int seed,
out double rmsError, out double outOfBagRmsError, out double relClassificationError, out double outOfBagRelClassificationError)
{
var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
double[,] inputMatrix = problemData.Dataset.ToArray(variables, trainingIndices);
var classValues = problemData.ClassValues.ToArray();
int nClasses = classValues.Length;
// map original class values to values [0..nClasses-1]
var classIndices = new Dictionary <double, double>();
for (int i = 0; i < nClasses; i++)
{
classIndices[classValues[i]] = i;
}
int nRows = inputMatrix.GetLength(0);
int nColumns = inputMatrix.GetLength(1);
for (int row = 0; row < nRows; row++)
{
inputMatrix[row, nColumns - 1] = classIndices[inputMatrix[row, nColumns - 1]];
}
alglib.dfreport rep;
var dForest = RandomForestUtil.CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, nClasses, out rep);
rmsError = rep.rmserror;
outOfBagRmsError = rep.oobrmserror;
relClassificationError = rep.relclserror;
outOfBagRelClassificationError = rep.oobrelclserror;
return(new RandomForestModel(problemData.TargetVariable, dForest, seed, problemData, nTrees, r, m, classValues));
}