/// <summary>
/// Grid search with crossvalidation
/// </summary>
/// <param name="problemData">The classification problem data</param>
/// <param name="numberOfFolds">The number of folds for crossvalidation</param>
/// <param name="shuffleFolds">Specifies whether the folds should be shuffled</param>
/// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
/// <param name="seed">The random seed (for shuffling)</param>
/// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
public static RFParameter GridSearch(IClassificationProblemData problemData, int numberOfFolds, bool shuffleFolds, Dictionary <string, IEnumerable <double> > parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1)
{
DoubleValue accuracy = new DoubleValue(0);
RFParameter bestParameter = new RFParameter();
var setters = parameterRanges.Keys.Select(GenerateSetter).ToList();
var crossProduct = parameterRanges.Values.CartesianProduct();
var partitions = GenerateRandomForestPartitions(problemData, numberOfFolds, shuffleFolds);
var locker = new object();
Parallel.ForEach(crossProduct, new ParallelOptions {
MaxDegreeOfParallelism = maxDegreeOfParallelism
}, parameterCombination => {
var parameterValues = parameterCombination.ToList();
double testAccuracy;
var parameters = new RFParameter();
for (int i = 0; i < setters.Count; ++i)
{
setters[i](parameters, parameterValues[i]);
}
CrossValidate(problemData, partitions, parameters.N, parameters.R, parameters.M, seed, out testAccuracy);
lock (locker) {
if (testAccuracy > accuracy.Value)
{
accuracy.Value = testAccuracy;
bestParameter = (RFParameter)parameters.Clone();
}
}
});
return(bestParameter);
}
protected RFParameter(RFParameter original, Cloner cloner)
: base(original, cloner)
{
this.N = original.N;
this.R = original.R;
this.M = original.M;
}
/// <summary>
/// Grid search without crossvalidation (since for random forests the out-of-bag estimate is unbiased)
/// </summary>
/// <param name="problemData">The classification problem data</param>
/// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
/// <param name="seed">The random seed (required by the random forest model)</param>
/// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
public static RFParameter GridSearch(IClassificationProblemData problemData, Dictionary <string, IEnumerable <double> > parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1)
{
var setters = parameterRanges.Keys.Select(GenerateSetter).ToList();
var crossProduct = parameterRanges.Values.CartesianProduct();
double bestOutOfBagRmsError = double.MaxValue;
RFParameter bestParameters = new RFParameter();
var locker = new object();
Parallel.ForEach(crossProduct, new ParallelOptions {
MaxDegreeOfParallelism = maxDegreeOfParallelism
}, parameterCombination => {
var parameterValues = parameterCombination.ToList();
var parameters = new RFParameter();
for (int i = 0; i < setters.Count; ++i)
{
setters[i](parameters, parameterValues[i]);
}
double rmsError, outOfBagRmsError, avgRelError, outOfBagAvgRelError;
RandomForestModel.CreateClassificationModel(problemData, problemData.TrainingIndices, parameters.N, parameters.R, parameters.M, seed,
out rmsError, out outOfBagRmsError, out avgRelError, out outOfBagAvgRelError);
lock (locker) {
if (bestOutOfBagRmsError > outOfBagRmsError)
{
bestOutOfBagRmsError = outOfBagRmsError;
bestParameters = (RFParameter)parameters.Clone();
}
}
});
return(bestParameters);
}
