static List <Record> DiscretizeDataset(List <Record> dataset, ReferenceTable table)
{
int[] row = { 0 };
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
Discretize(table.HasUnknowns(0), rec => double.Parse(rec[row[0]]), (rec, val) => rec[row[0]] = val, table.GetRanges(row[0]), table.GetValues(row[0]), dataset); row[0]++;
return(dataset);
}
static void RunDiabetesTest(string trainingFile, string testFile)
{
Console.WriteLine($"[{GetTimeStamp()}] Diabetes test:");
ReferenceTable table = new ReferenceTable();
Console.WriteLine($"[{GetTimeStamp()}] Loading training file: {trainingFile}.");
List <Record> trainingRecords = DiscretizeDataset(ParseRecords(File.ReadAllLines(trainingFile)), table);
Console.WriteLine($"[{GetTimeStamp()}] Loading test file: {trainingFile}.");
List <Record> testRecords = DiscretizeDataset(ParseRecords(File.ReadAllLines(testFile)), table);
var attributes = table.GetIndex().Select(idx => new DiscreteAttribute(idx, table.GetName(idx), table.GetValues(idx))).ToList();
//DecisionTree.AssignProbabilitiesByClass(attributes, trainingRecords, false);
attributes.ForEach(attribute => DecisionTree.AssignProbabilities(attribute, trainingRecords));
attributes.ForEach(attribute => DecisionTree.AssignProbabilities(attribute, testRecords.Union(trainingRecords).ToList()));
Console.WriteLine($"[{GetTimeStamp()}] Building Ensemble of ID3 decision trees...");
Random sampler = new Random();
var ensemble = new Ensemble();
for (int i = 0; i <= 1000; i++)
{
DecisionTree tree = new DecisionTree(attributes, SampledData(trainingRecords, sampler)).Build();
ensemble.AddVoter(tree.Test);
if (i != 0 && i != 20 && i != 100 && i != 500 && i != 1000 && i != 2000)
{
continue;
}
ConfusionMatrix trainingMatrix = RunPredictions(trainingRecords, rec => rec.IsPositive, ensemble.Test);
ConfusionMatrix testMatrix = RunPredictions(testRecords, rec => rec.IsPositive, ensemble.Test);
Console.WriteLine("----------------------------------------------------------------");
Console.WriteLine($"[{GetTimeStamp()}][Ensemble: {i}] Printing sanity results: ");
PrintResults(trainingMatrix);
Console.WriteLine($"[{GetTimeStamp()}][Ensemble: {i}] Printing prediction results: ");
PrintResults(testMatrix);
}
}
