public void Train(List <int[]> trainingData, int classIndex, double confidence, int maxDepth)
{
Classifiers = new List <Id3Classifier>();
List <List <int[]> > samples = Sampler.SampleData(trainingData, NumberOfSamples);
for (int i = 0; i < NumberOfSamples; i++)
{
Id3Classifier classifier = new Id3Classifier(samples[i], classIndex, confidence, maxDepth);
Classifiers.Add(classifier);
}
}
static void Main(string[] args)
{
List <double[]> continuousTrainData = DataWrangler.LoadContinuousDataAsync(TrainingCsv, _indexToIgnore).Result;
List <double[]> continuousTestData = DataWrangler.LoadContinuousDataAsync(TestingCsv, _indexToIgnore).Result;
// Print continuous columns for calculating elbows in external tool(https://bl.ocks.org/rpgove/0060ff3b656618e9136b)
//foreach (int i in _continuesIndexes)
//{
// using (StreamWriter sw = new StreamWriter($"{i}.txt"))
// {
// sw.WriteLine(string.Join(",", continuousTrainData.Select(array => array[i])));
// }
//}
// Convert continuous to discrete
Dictionary <int, GaussianClusterCollection> indexClusterMapping = DataWrangler.GetIndexClustersMap(continuousTrainData, _indexElbowMap);
List <int[]> discreteTrainData = DataWrangler.ConvertContinuesToDiscrete(continuousTrainData, indexClusterMapping);
List <int[]> discreteTestData = DataWrangler.ConvertContinuesToDiscrete(continuousTestData, indexClusterMapping);
// Verify clustering
//foreach (int continuousIndex in _continuousIndexes)
//{
// HashSet<int> clustersTrain = new HashSet<int>();
// HashSet<int> clustersTest = new HashSet<int>();
// foreach (int[] instance in discreteTrainData)
// {
// clustersTrain.Add(instance[continuousIndex]);
// }
// foreach (int[] instance in discreteTestData)
// {
// clustersTest.Add(instance[continuousIndex]);
// }
// Console.WriteLine($"Clustering in index {continuousIndex} generated {clustersTrain.Count} unique clusters in train and {clustersTest.Count} unique clusters in test");
// Console.WriteLine($"Train: {string.Join(",", clustersTrain.OrderBy(i => i))}");
// Console.WriteLine($"Test: {string.Join(",", clustersTest.OrderBy(i => i))}");
// Console.WriteLine();
//}
List <List <int[]> > samples = Sampler.SampleData(discreteTrainData, BiasVarianceNumOfSamples);
ConcurrentDictionary <int, ConcurrentDictionary <int, ConcurrentDictionary <int, int> > > id3ClassifierDepthInstanceClassifierPredictionMappings = new ConcurrentDictionary <int, ConcurrentDictionary <int, ConcurrentDictionary <int, int> > >();
ConcurrentDictionary <int, ConcurrentDictionary <int, ConcurrentDictionary <int, int> > > id3BaggerDepthInstanceClassifierPredictionMappings = new ConcurrentDictionary <int, ConcurrentDictionary <int, ConcurrentDictionary <int, int> > >();
ConcurrentDictionary <int, Tuple <double, double, double> > id3ClassifierResult = new ConcurrentDictionary <int, Tuple <double, double, double> >();
ConcurrentDictionary <int, Tuple <double, double, double> > id3BaggerClassifierResult = new ConcurrentDictionary <int, Tuple <double, double, double> >();
// From 0 to 10 maxDepth, calculate the bias and variance of the classifiers in parallel.
Parallel.For(0, 11, (maxDepth) =>
//for (int maxDepth = 0; maxDepth < 2; maxDepth++)
{
ConcurrentDictionary <int, ConcurrentDictionary <int, int> > id3BaggerInstanceClassifierPredictionMappings = id3BaggerDepthInstanceClassifierPredictionMappings.GetOrAdd(maxDepth, new ConcurrentDictionary <int, ConcurrentDictionary <int, int> >());
ConcurrentDictionary <int, ConcurrentDictionary <int, int> > id3ClassifierInstanceClassifierPredictionMappings = id3ClassifierDepthInstanceClassifierPredictionMappings.GetOrAdd(maxDepth, new ConcurrentDictionary <int, ConcurrentDictionary <int, int> >());
for (int i = 0; i < BiasVarianceNumOfSamples; i++)
//Parallel.For(0, BiasVarianceNumOfSamples, i =>
{
// Initialize and train the classifiers in parallel
Id3Bagger bagger = new Id3Bagger(BaggerSamples);
bagger.Train(samples[i], ClassIndex, 0, maxDepth);
// Store predictions on test data
//Parallel.For(0, discreteTestData.Count, (j) =>
for (int j = 0; j < discreteTestData.Count; j++)
{
ConcurrentDictionary <int, int> classifierPredictionMapping = id3BaggerInstanceClassifierPredictionMappings.GetOrAdd(j, new ConcurrentDictionary <int, int>());
classifierPredictionMapping.GetOrAdd(i, bagger.GetClass(discreteTestData[j]));
}
;
// Free the memory
bagger = null;
// Initialize and train the classifiers in parallel
Id3Classifier tree = new Id3Classifier(samples[i], ClassIndex, 0, maxDepth);
// Store predictions on test data
//Parallel.For(0, discreteTestData.Count, (j) =>
for (int j = 0; j < discreteTestData.Count; j++)
{
ConcurrentDictionary <int, int> classifierPredictionMapping = id3ClassifierInstanceClassifierPredictionMappings.GetOrAdd(j, new ConcurrentDictionary <int, int>());
classifierPredictionMapping.GetOrAdd(i, tree.GetClass(discreteTestData[j]));
}
;
// Free the memory
tree = null;
}
;
// Calculate bias and variance for each classifier and store it.
id3BaggerClassifierResult.GetOrAdd(maxDepth, BiasVarianceHelper.GetBiasVarianceAccuracy(discreteTestData, ClassIndex, id3BaggerInstanceClassifierPredictionMappings));
id3ClassifierResult.GetOrAdd(maxDepth, BiasVarianceHelper.GetBiasVarianceAccuracy(discreteTestData, ClassIndex, id3ClassifierInstanceClassifierPredictionMappings));
});
Console.WriteLine("Id3 Classifier");
Console.WriteLine("Max Depth, Bias, Variance, Accuracy");
foreach (int maxDepth in id3ClassifierResult.Keys)
{
Console.WriteLine($"{maxDepth}, {id3ClassifierResult[maxDepth].Item1}, {id3ClassifierResult[maxDepth].Item2}, {id3ClassifierResult[maxDepth].Item3}");
}
Console.WriteLine();
Console.WriteLine("Bagger");
Console.WriteLine("Max Depth, Bias, Variance, Accuracy");
foreach (int maxDepth in id3BaggerClassifierResult.Keys)
{
Console.WriteLine($"{maxDepth}, {id3BaggerClassifierResult[maxDepth].Item1}, {id3BaggerClassifierResult[maxDepth].Item2}, {id3ClassifierResult[maxDepth].Item3}");
}
Console.WriteLine();
Console.WriteLine("Press ENTER to exit...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Training
ArffHeader header = null;
List <object[]> instances = new List <object[]>();
using (ArffReader arffReader = new ArffReader(TrainingArffFile))
{
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()));
Console.WriteLine("Number of Samples, training accuracy, test accuracy");
// Do this excercise multiple times as sampling is random.
Parallel.For(0, 100, (k) =>
{
// Dictionaries to store results for different accuracies. KEEP IN SYNC :)
ConcurrentDictionary <int, double> sampleTrainingAccuraciesMap = new ConcurrentDictionary <int, double>(new Dictionary <int, double>
{
{ 1, 0 },
{ 3, 0 },
{ 5, 0 },
{ 10, 0 },
{ 20, 0 },
{ 25, 0 },
{ 50, 0 },
{ 75, 0 },
{ 100, 0 }
});
ConcurrentDictionary <int, double> sampleTestAccuraciesMap = new ConcurrentDictionary <int, double>(new Dictionary <int, double>
{
{ 1, 0 },
{ 3, 0 },
{ 5, 0 },
{ 10, 0 },
{ 20, 0 },
{ 25, 0 },
{ 50, 0 },
{ 75, 0 },
{ 100, 0 }
});
// Calculate different sample accuracies in parallel.
Parallel.ForEach(sampleTrainingAccuraciesMap.Keys, numOfSamples =>
{
List <Id3Classifier> classifiers = new List <Id3Classifier>();
Sampler sampler = new Sampler(trainingData, numOfSamples);
for (int i = 0; i < numOfSamples; i++)
{
Id3Classifier classifier = new Id3Classifier(sampler.Samples[i], ClassIndex, Confidence);
classifiers.Add(classifier);
}
// Evaluate training and test to look out for overfitting.
sampleTrainingAccuraciesMap[numOfSamples] = Evaluate(trainingData, classifiers);
sampleTestAccuraciesMap[numOfSamples] = Evaluate(testData, classifiers);
});
lock (_lockConsole)
{
foreach (int numOfSamples in sampleTestAccuraciesMap.Keys.OrderBy(n => n))
{
Console.WriteLine($"{numOfSamples},{sampleTrainingAccuraciesMap[numOfSamples]},{sampleTestAccuraciesMap[numOfSamples]}");
}
}
});
Console.WriteLine("Press ENTER to exit...");
Console.ReadLine();
}