public override void Main()
{
var variables = (Variables)vars;
var item = variables.SingleOrDefault(x => x.Value is IRegressionProblem || x.Value is IRegressionProblemData);
if (item.Equals(default(KeyValuePair <string, object>)))
{
throw new ArgumentException("Could not find a suitable problem or problem data.");
}
string name = item.Key;
IRegressionProblemData problemData;
if (item.Value is IRegressionProblem)
{
problemData = ((IRegressionProblem)item.Value).ProblemData;
}
else
{
problemData = (IRegressionProblemData)item.Value;
}
var bestParameters = new RFParameter();
var bestSolution = GridSearch(problemData, out bestParameters);
vars["bestSolution"] = bestSolution;
vars["bestParameters"] = bestParameters;
Console.WriteLine("R2 (training): " + bestSolution.TrainingRSquared + ", R2 (test): " + bestSolution.TestRSquared);
Console.WriteLine("Model parameters: n = {0}, r = {1}, m = {2}", bestParameters.N, bestParameters.R, bestParameters.M);
}
private static RandomForestClassificationSolution GridSearch(IClassificationProblemData problemData, out RFParameter bestParameters, int seed = 3141519) {
double rmsError, outOfBagRmsError, relClassificationError, outOfBagRelClassificationError;
bestParameters = RandomForestUtil.GridSearch(problemData, randomForestParameterRanges, seed, maximumDegreeOfParallelism);
var model = RandomForestModel.CreateClassificationModel(problemData, problemData.TrainingIndices, bestParameters.N, bestParameters.R, bestParameters.M, seed,
out rmsError, out outOfBagRmsError, out relClassificationError, out outOfBagRelClassificationError);
return (RandomForestClassificationSolution)model.CreateClassificationSolution(problemData);
}
private static RandomForestRegressionSolution GridSearch(IRegressionProblemData problemData, out RFParameter bestParameters, int seed = 3141519) {
double rmsError, outOfBagRmsError, avgRelError, outOfBagAvgRelError;
var random = new MersenneTwister();
bestParameters = RandomForestUtil.GridSearch(problemData, randomForestParameterRanges, seed, maximumDegreeOfParallelism);
var model = RandomForestModel.CreateRegressionModel(problemData, problemData.TrainingIndices, bestParameters.N, bestParameters.R, bestParameters.M, seed,
out rmsError, out outOfBagRmsError, out avgRelError, out outOfBagAvgRelError);
return (RandomForestRegressionSolution)model.CreateRegressionSolution(problemData);
}
public override void Main() {
var variables = (Variables)vars;
var item = variables.SingleOrDefault(x => x.Value is IClassificationProblem || x.Value is IClassificationProblemData);
if (item.Equals(default(KeyValuePair<string, object>)))
throw new ArgumentException("Could not find a suitable problem or problem data.");
string name = item.Key;
IClassificationProblemData problemData;
if (item.Value is IClassificationProblem)
problemData = ((IClassificationProblem)item.Value).ProblemData;
else
problemData = (IClassificationProblemData)item.Value;
var bestParameters = new RFParameter();
var bestSolution = GridSearch(problemData, out bestParameters);
vars["bestSolution"] = bestSolution;
vars["bestParameters"] = bestParameters;
Console.WriteLine("Accuracy (training): " + bestSolution.TrainingAccuracy + ", Accuracy (test): " + bestSolution.TestAccuracy);
Console.WriteLine("Model parameters: n = {0}, r = {1}, m = {2}", bestParameters.N, bestParameters.R, bestParameters.M);
}
private static RandomForestRegressionSolution GridSearch(IRegressionProblemData problemData, out RFParameter bestParameters, int seed = 3141519)
{
double rmsError, outOfBagRmsError, avgRelError, outOfBagAvgRelError;
var random = new MersenneTwister();
bestParameters = RandomForestUtil.GridSearch(problemData, randomForestParameterRanges, seed, maximumDegreeOfParallelism);
var model = RandomForestModel.CreateRegressionModel(problemData, problemData.TrainingIndices, bestParameters.N, bestParameters.R, bestParameters.M, seed,
out rmsError, out outOfBagRmsError, out avgRelError, out outOfBagAvgRelError);
return((RandomForestRegressionSolution)model.CreateRegressionSolution(problemData));
}
private static RandomForestClassificationSolution GridSearch(IClassificationProblemData problemData, out RFParameter bestParameters, int seed = 3141519)
{
double rmsError, outOfBagRmsError, relClassificationError, outOfBagRelClassificationError;
bestParameters = RandomForestUtil.GridSearch(problemData, randomForestParameterRanges, seed, maximumDegreeOfParallelism);
var model = RandomForestModel.CreateClassificationModel(problemData, problemData.TrainingIndices, bestParameters.N, bestParameters.R, bestParameters.M, seed,
out rmsError, out outOfBagRmsError, out relClassificationError, out outOfBagRelClassificationError);
return((RandomForestClassificationSolution)model.CreateClassificationSolution(problemData));
}
