public static void RandomMonteCarlo(string Filename, Dataset Train, int NumberOfTrainingSamplesMin, int NumberOfTrainingSamplesMax, int NumberOfDecisionTreesMin, int NumberOfDecisionTreesMax, int MaxTreeDepthMin, int MaxTreeDepthMax, int SamplesPerTreeMin, int SamplesPerTreeMax)
{
StringBuilder sb = new StringBuilder();
sb.AppendLine("numberOfTrainingSamples,numberofDecisionTrees,maxTreeDepth,samplesPerTree,fitness");
while (true)
{
int numberOfTrainingSamples = RNG.Next(NumberOfTrainingSamplesMin, NumberOfTrainingSamplesMax);
int numberOfDecisionTrees = RNG.Next(NumberOfDecisionTreesMin, NumberOfDecisionTreesMax);
int maxTreeDepth = RNG.Next(MaxTreeDepthMin, MaxTreeDepthMax);
int samplesPerTree = RNG.Next(SamplesPerTreeMin, SamplesPerTreeMax);
if (samplesPerTree > numberOfTrainingSamples)
{
samplesPerTree = numberOfTrainingSamples;
}
Dataset currentTrain = new Dataset();
currentTrain.Inputs.AddRange(Train.Inputs.GetRange(0, numberOfTrainingSamples));
currentTrain.Outputs.AddRange(Train.Outputs.GetRange(0, numberOfTrainingSamples));
Dataset currentValidation = new Dataset();
currentValidation.Inputs.AddRange(Train.Inputs.GetRange(numberOfTrainingSamples, Train.Inputs.Count - numberOfTrainingSamples));
currentValidation.Outputs.AddRange(Train.Outputs.GetRange(numberOfTrainingSamples, Train.Inputs.Count - numberOfTrainingSamples));
DecisionForest df = new DecisionForest(currentTrain, numberOfDecisionTrees, maxTreeDepth, samplesPerTree);
float fitness = Fitness(df, currentValidation);
string line = numberOfTrainingSamples + "," + numberOfDecisionTrees + "," + maxTreeDepth + "," + samplesPerTree + "," + fitness;
sb.AppendLine(line);
Console.WriteLine(line);
using (StreamWriter sw = new StreamWriter(Filename))
{
sw.Write(sb.ToString());
}
}
}
public static float Fitness (DecisionForest DecisionForest, Dataset Validation)
{
int correct = 0;
for (int row = 0; row < Validation.Inputs.Count; row++)
{
if (Validation.Outputs[row][0] == DecisionForest.Classify(Validation.Inputs[row]))
{
correct++;
}
}
return ((float)correct) / ((float)Validation.Inputs.Count);
}
static void spiral ()
{
Dataset train = Dataset.GenerateSpiral(0, 0, 1, 1, 0.1f, 1000, 10, 100);
train.WriteCSV("./data/spiral_train.csv", true);
Dataset test = Dataset.CloneInputSet(train);
DecisionForest df = new DecisionForest(train, 10, 30, 20);
for (int row = 0; row < test.Inputs.Count; row++)
{
List<float> outputs = new List<float>();
outputs.Add(df.Classify(test.Inputs[row]));
test.Outputs.Add(outputs);
}
test.WriteCSV("./data/spiral_test.csv", true);
}
static void ocr ()
{
OCRDataset train = new OCRDataset();
train.ReadTrainCSV("./data/ocr_train.csv");
OCRDataset test = new OCRDataset();
test.ReadTestCSV("./data/ocr_test.csv");
DecisionForest df = new DecisionForest(train, 20000, 1000, 10000);
for (int row = 0; row < test.Inputs.Count; row++)
{
Console.WriteLine("i: " + row + "/" + test.Inputs.Count);
List<float> outputs = new List<float>();
outputs.Add(df.Classify(test.Inputs[row]));
test.Outputs.Add(outputs);
}
test.WriteTestCSV("./data/ocr_est.csv");
}
static void fin()
{
Dataset train = new Dataset();
train.ReadCSV("./data/validate.win", 2000, false);
Dataset test = new Dataset();
test.Inputs.Add(train.Inputs[train.Inputs.Count - 1]);
DecisionForest df = new DecisionForest(train, 10, 500, 500);
for (int row = 0; row < test.Inputs.Count; row++)
{
Console.WriteLine("i: " + row + "/" + test.Inputs.Count);
List<float> outputs = new List<float>();
outputs.Add(df.Classify(test.Inputs[row]));
test.Outputs.Add(outputs);
}
test.WriteCSV("./data/est.win", false);
}
public static void IterativeMonteCarlo (string Filename, Dataset Train, int NumberOfTrainingSamplesMin, int NumberOfTrainingSamplesMax, int NumberOfDecisionTreesMin, int NumberOfDecisionTreesMax, int MaxTreeDepthMin, int MaxTreeDepthMax, int SamplesPerTreeMin, int SamplesPerTreeMax)
{
StringBuilder sb = new StringBuilder();
sb.AppendLine("numberOfTrainingSamples,numberofDecisionTrees,maxTreeDepth,samplesPerTree,fitness");
for (int numberOfTrainingSamples = NumberOfDecisionTreesMin; numberOfTrainingSamples <= NumberOfDecisionTreesMax; numberOfTrainingSamples += 1)
{
for (int numberOfDecisionTrees = NumberOfDecisionTreesMin; numberOfDecisionTrees <= NumberOfDecisionTreesMax; numberOfDecisionTrees += 1)
{
for (int maxTreeDepth = MaxTreeDepthMin; maxTreeDepth <= MaxTreeDepthMax; maxTreeDepth += 1)
{
for (int samplesPerTree = SamplesPerTreeMin; samplesPerTree <= SamplesPerTreeMax && samplesPerTree <= numberOfTrainingSamples; samplesPerTree += 1)
{
Dataset currentTrain = new Dataset();
currentTrain.Inputs.AddRange(Train.Inputs.GetRange(0, numberOfTrainingSamples));
currentTrain.Outputs.AddRange(Train.Outputs.GetRange(0, numberOfTrainingSamples));
Dataset currentValidation = new Dataset();
currentValidation.Inputs.AddRange(Train.Inputs.GetRange(numberOfTrainingSamples, Train.Inputs.Count - numberOfTrainingSamples));
currentValidation.Outputs.AddRange(Train.Outputs.GetRange(numberOfTrainingSamples, Train.Inputs.Count - numberOfTrainingSamples));
DecisionForest df = new DecisionForest(currentTrain, numberOfDecisionTrees, maxTreeDepth, samplesPerTree);
float fitness = Fitness(df, currentValidation);
string line = numberOfTrainingSamples + "," + numberOfDecisionTrees + "," + maxTreeDepth + "," + samplesPerTree + "," + fitness;
sb.AppendLine(line);
Console.WriteLine(line);
using (StreamWriter sw = new StreamWriter(Filename))
{
sw.Write(sb.ToString());
}
}
}
}
}
using (StreamWriter sw = new StreamWriter(Filename))
{
sw.Write(sb.ToString());
}
}
