public Id3Classifier(List <int[]> instances, int classIndex, double confidence)
{
Instances = instances;
Confidence = confidence;
Tree = Id3Node.BuildTree(instances, classIndex, confidence);
}
public Id3Classifier(List <int[]> instances, int classIndex, double confidence, int maxDepth)
{
Confidence = confidence;
Tree = Id3Node.BuildTree(instances, classIndex, confidence, maxDepth);
}
static void Main(string[] args)
{
// Training
ArffHeader header = null;
List <object[]> instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(_arffFile))
{
header = arffReader.ReadHeader();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
instances.Add(instance);
}
}
List <int[]> trainingData = new List <int[]>(instances.Select(objectArray => objectArray.Select(o => o == null ? -1 : (int)o).ToArray()));
// Test
instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(_testArffFile))
{
header = arffReader.ReadHeader();
object[] instance;
while ((instance = arffReader.ReadInstance()) != null)
{
instances.Add(instance);
}
}
List <int[]> testData = new List <int[]>(instances.Select(objectArray => objectArray.Select(o => o == null ? -1 : (int)o).ToArray()));
double[] confidences = new double[]
{
0.0,
0.1,
0.2,
0.4,
0.6,
0.8,
0.9,
0.95,
0.99,
0.9999
};
PrintAsCsv(header, trainingData, @"c:\users\andresz\desktop\data.csv");
Parallel.ForEach(confidences, confidence =>
{
Id3Node tree = Id3Node.BuildTree(trainingData, trainingData[0].Length - 1, confidence);
Console.WriteLine($"Confidence {confidence}: Num of nodes {GetCount(tree)}");
// Test accuracy on training
Console.WriteLine($"Confidence {confidence}: Accuracy on train = { trainingData.Where(instance => GetClass(instance, tree) == instance[trainingData[0].Length - 1]).Count() / (double)trainingData.Count}");
// Test accuracy on test
Console.WriteLine($"Confidence {confidence}: Accuracy on test = { testData.Where(instance => GetClass(instance, tree) == instance[testData[0].Length - 1]).Count() / (double)testData.Count}");
StringBuilder sb = new StringBuilder();
StringBuilder sbMaxPositive = new StringBuilder();
StringBuilder sbMaxNegative = new StringBuilder();
int maxPositive = int.MinValue;
int maxNegative = int.MinValue;
// Only print small trees.
if (confidence > 0.5)
{
PrintTreeAsRules(sb, ref sbMaxPositive, ref sbMaxNegative, ref maxPositive, ref maxNegative, tree, header);
sb.AppendLine("The most max positive rule is:");
sb.AppendLine(sbMaxPositive.ToString());
sb.AppendLine();
sb.AppendLine("The most max negative rule is:");
sb.AppendLine(sbMaxNegative.ToString());
Directory.CreateDirectory(_outputFolder);
File.WriteAllText(Path.Combine(_outputFolder, $"Tree{confidence}.txt"), sb.ToString());
}
});
}
