protected OneRClassificationSolution(OneRClassificationSolution original, Cloner cloner) : base(original, cloner)
{
}
private OneRClassificationSolution(OneRClassificationSolution original, Cloner cloner) : base(original, cloner)
{
}
protected OneRClassificationSolution(OneRClassificationSolution original, Cloner cloner) : base(original, cloner) { }
public static IClassificationSolution CreateOneRSolution(IClassificationProblemData problemData, int minBucketSize = 6)
{
var bestClassified = 0;
List <Split> bestSplits = null;
string bestVariable = string.Empty;
double bestMissingValuesClass = double.NaN;
var classValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices);
foreach (var variable in problemData.AllowedInputVariables)
{
var inputValues = problemData.Dataset.GetDoubleValues(variable, problemData.TrainingIndices);
var samples = inputValues.Zip(classValues, (i, v) => new Sample(i, v)).OrderBy(s => s.inputValue);
var missingValuesDistribution = samples.Where(s => double.IsNaN(s.inputValue)).GroupBy(s => s.classValue).ToDictionary(s => s.Key, s => s.Count()).MaxItems(s => s.Value).FirstOrDefault();
//calculate class distributions for all distinct inputValues
List <Dictionary <double, int> > classDistributions = new List <Dictionary <double, int> >();
List <double> thresholds = new List <double>();
double lastValue = double.NaN;
foreach (var sample in samples.Where(s => !double.IsNaN(s.inputValue)))
{
if (sample.inputValue > lastValue || double.IsNaN(lastValue))
{
if (!double.IsNaN(lastValue))
{
thresholds.Add((lastValue + sample.inputValue) / 2);
}
lastValue = sample.inputValue;
classDistributions.Add(new Dictionary <double, int>());
foreach (var classValue in problemData.ClassValues)
{
classDistributions[classDistributions.Count - 1][classValue] = 0;
}
}
classDistributions[classDistributions.Count - 1][sample.classValue]++;
}
thresholds.Add(double.PositiveInfinity);
var distribution = classDistributions[0];
var threshold = thresholds[0];
var splits = new List <Split>();
for (int i = 1; i < classDistributions.Count; i++)
{
var samplesInSplit = distribution.Max(d => d.Value);
//join splits if there are too few samples in the split or the distributions has the same maximum class value as the current split
if (samplesInSplit < minBucketSize ||
classDistributions[i].MaxItems(d => d.Value).Select(d => d.Key).Contains(
distribution.MaxItems(d => d.Value).Select(d => d.Key).First()))
{
foreach (var classValue in classDistributions[i])
{
distribution[classValue.Key] += classValue.Value;
}
threshold = thresholds[i];
}
else
{
splits.Add(new Split(threshold, distribution.MaxItems(d => d.Value).Select(d => d.Key).First()));
distribution = classDistributions[i];
threshold = thresholds[i];
}
}
splits.Add(new Split(double.PositiveInfinity, distribution.MaxItems(d => d.Value).Select(d => d.Key).First()));
int correctClassified = 0;
int splitIndex = 0;
foreach (var sample in samples.Where(s => !double.IsNaN(s.inputValue)))
{
while (sample.inputValue >= splits[splitIndex].thresholdValue)
{
splitIndex++;
}
correctClassified += sample.classValue == splits[splitIndex].classValue ? 1 : 0;
}
correctClassified += missingValuesDistribution.Value;
if (correctClassified > bestClassified)
{
bestClassified = correctClassified;
bestSplits = splits;
bestVariable = variable;
bestMissingValuesClass = missingValuesDistribution.Value == 0 ? double.NaN : missingValuesDistribution.Key;
}
}
//remove neighboring splits with the same class value
for (int i = 0; i < bestSplits.Count - 1; i++)
{
if (bestSplits[i].classValue == bestSplits[i + 1].classValue)
{
bestSplits.Remove(bestSplits[i]);
i--;
}
}
var model = new OneRClassificationModel(bestVariable, bestSplits.Select(s => s.thresholdValue).ToArray(), bestSplits.Select(s => s.classValue).ToArray(), bestMissingValuesClass);
var solution = new OneRClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
return(solution);
}
