public Data(StreamReader r, StreamReader r2, StreamReader eval, StreamReader train_ID, StreamReader test_ID, StreamReader eval_ID, int depth, Random rand, int ForestSize)
{
Forest = new List <BaggedForest>();
Training_Data_Forest = new List <TrainingData>();
data_1 = new List <Entry>();
Training_Data = new List <TrainingData>();
data_2 = new List <Entry>();
Test_Data = new List <TrainingData>();
SetData(r, r2);
SetTrainingData();
Training_Data_Forest = Training_Data;
for (int i = 0; i < ForestSize; i++)
{
ShuffleForestData(rand);
data_1 = new List <Entry>();
Training_Data = new List <TrainingData>();
data_2 = new List <Entry>();
Test_Data = new List <TrainingData>();
SetData(r, r2);
SetTrainingData();
List <TrainingData> trainingDataHelper = Training_Data_Forest.GetRange(0, 1000);
Tree = new DecisionTree(ref trainingDataHelper, depth, rand);
Tree.CollapseTree();
List <TrainingData> testDataHelper = Test_Data;
Error = (Convert.ToDouble(Tree.DetermineError(ref testDataHelper)) / Convert.ToDouble(Test_Data.Count)) * 100;
Test_Accuracy = 100 - Error;
Depth = Tree.DetermineDepth(0);
List <Prediction> Test_Predictions = SetPredictions(test_ID, Tree.Labels);
Tree.Labels = new List <int>();
trainingDataHelper = Training_Data;
Tree.DetermineError(ref trainingDataHelper);
double train_accuracy = 100 - ((Convert.ToDouble(Tree.DetermineError(ref trainingDataHelper)) / Convert.ToDouble(Training_Data.Count)) * 100);
List <Prediction> Train_Predictions = SetPredictions(train_ID, Tree.Labels);
data_1 = new List <Entry>();
data_2 = new List <Entry>();
Training_Data = new List <TrainingData>();
SetData(eval);
SetTrainingData();
Tree.Labels = new List <int>();
trainingDataHelper = Training_Data;
double eval_accuracy = 100 - ((Convert.ToDouble(Tree.DetermineError(ref trainingDataHelper)) / Convert.ToDouble(Training_Data.Count)) * 100);
List <Prediction> Eval_Predictions = SetPredictions(eval_ID, Tree.Labels);
Forest.Add(new BaggedForest(train_accuracy, Train_Predictions, Test_Accuracy, Test_Predictions, eval_accuracy, Eval_Predictions));
if (i % 5 == 0)
{
Console.WriteLine(i);
}
}
data_3 = data_1;
data_1 = new List <Entry>();
data_2 = new List <Entry>();
SetData(r, r2);
}
public Data(StreamReader train, StreamReader test, StreamReader eval, StreamReader eval_ID, int depth, Random r)
{
double temp_error1;
double temp_error2;
double temp_error3;
double temp_error4;
double temp_error5;
Cross_Validate_Data = new List <Entry>();
Predictions = new List <Prediction>();
Predictions2 = new List <Prediction>();
Predictions3 = new List <Prediction>();
Predictions4 = new List <Prediction>();
Predictions5 = new List <Prediction>();
Predictions_Average = new List <Prediction>();
Cross_1 = new List <Entry>();
Cross_2 = new List <Entry>();
Cross_3 = new List <Entry>();
Cross_4 = new List <Entry>();
Cross_5 = new List <Entry>();
Accuracies = new List <double>();
SetValidateData(train, test, r);
#region First Fold
data_1 = new List <Entry>();
Training_Data = new List <TrainingData>();
data_2 = new List <Entry>();
Test_Data = new List <TrainingData>();
data_1 = Cross_1.Concat(Cross_2.Concat(Cross_3.Concat(Cross_4))).ToList();
data_2 = Cross_5;
SetTrainingData();
List <TrainingData> trainingDataHelper = Training_Data;
Tree = new DecisionTree(ref trainingDataHelper, depth, r);
Tree.CollapseTree();
List <TrainingData> testDataHelper = Test_Data;
temp_error1 = (Convert.ToDouble(Tree.DetermineError(ref testDataHelper)) / Convert.ToDouble(Test_Data.Count)) * 100;
Tree.Accuracy = 100 - temp_error1;
data_1 = new List <Entry>();
data_2 = new List <Entry>();
Training_Data = new List <TrainingData>();
SetData(eval);
SetTrainingData();
Tree.Labels = new List <int>();
trainingDataHelper = Training_Data;
Tree.DetermineError(ref trainingDataHelper);
Predictions = SetPredictions(eval_ID, Tree.Labels);
#endregion
#region Second Fold
Training_Data = new List <TrainingData>();
Test_Data = new List <TrainingData>();
data_1 = Cross_1.Concat(Cross_2.Concat(Cross_3.Concat(Cross_5))).ToList();
data_2 = Cross_4;
SetTrainingData();
trainingDataHelper = Training_Data;
Tree2 = new DecisionTree(ref trainingDataHelper, depth, r);
Tree2.CollapseTree();
testDataHelper = Test_Data;
temp_error2 = (Convert.ToDouble(Tree2.DetermineError(ref testDataHelper)) / Convert.ToDouble(Test_Data.Count)) * 100;
Tree2.Accuracy = 100 - temp_error2;
data_1 = new List <Entry>();
data_2 = new List <Entry>();
Training_Data = new List <TrainingData>();
SetData(eval);
SetTrainingData();
Tree2.Labels = new List <int>();
trainingDataHelper = Training_Data;
Tree2.DetermineError(ref trainingDataHelper);
Predictions2 = SetPredictions(eval_ID, Tree2.Labels);
#endregion
#region Third Fold
Training_Data = new List <TrainingData>();
Test_Data = new List <TrainingData>();
data_1 = Cross_1.Concat(Cross_2.Concat(Cross_4.Concat(Cross_5))).ToList();
data_2 = Cross_3;
SetTrainingData();
trainingDataHelper = Training_Data;
Tree3 = new DecisionTree(ref trainingDataHelper, depth, r);
Tree3.CollapseTree();
testDataHelper = Test_Data;
temp_error3 = (Convert.ToDouble(Tree3.DetermineError(ref testDataHelper)) / Convert.ToDouble(Test_Data.Count)) * 100;
Tree3.Accuracy = 100 - temp_error3;
data_1 = new List <Entry>();
data_2 = new List <Entry>();
Training_Data = new List <TrainingData>();
SetData(eval);
SetTrainingData();
Tree3.Labels = new List <int>();
trainingDataHelper = Training_Data;
Tree3.DetermineError(ref trainingDataHelper);
Predictions3 = SetPredictions(eval_ID, Tree3.Labels);
#endregion
#region Fourth Fold
Training_Data = new List <TrainingData>();
Test_Data = new List <TrainingData>();
data_1 = Cross_1.Concat(Cross_3.Concat(Cross_4.Concat(Cross_5))).ToList();
data_2 = Cross_2;
SetTrainingData();
trainingDataHelper = Training_Data;
Tree4 = new DecisionTree(ref trainingDataHelper, depth, r);
Tree4.CollapseTree();
testDataHelper = Test_Data;
temp_error4 = (Convert.ToDouble(Tree4.DetermineError(ref testDataHelper)) / Convert.ToDouble(Test_Data.Count)) * 100;
Tree4.Accuracy = 100 - temp_error4;
data_1 = new List <Entry>();
data_2 = new List <Entry>();
Training_Data = new List <TrainingData>();
SetData(eval);
SetTrainingData();
Tree4.Labels = new List <int>();
trainingDataHelper = Training_Data;
Tree4.DetermineError(ref trainingDataHelper);
Predictions4 = SetPredictions(eval_ID, Tree4.Labels);
#endregion
#region Fifth Fold
Training_Data = new List <TrainingData>();
Test_Data = new List <TrainingData>();
data_1 = Cross_2.Concat(Cross_3.Concat(Cross_4.Concat(Cross_5))).ToList();
data_2 = Cross_1;
SetTrainingData();
trainingDataHelper = Training_Data;
Tree5 = new DecisionTree(ref trainingDataHelper, depth, r);
Tree5.CollapseTree();
testDataHelper = Test_Data;
temp_error5 = (Convert.ToDouble(Tree5.DetermineError(ref testDataHelper)) / Convert.ToDouble(Test_Data.Count)) * 100;
Tree5.Accuracy = 100 - temp_error5;
data_1 = new List <Entry>();
data_2 = new List <Entry>();
Training_Data = new List <TrainingData>();
SetData(eval);
SetTrainingData();
Tree5.Labels = new List <int>();
trainingDataHelper = Training_Data;
Tree5.DetermineError(ref trainingDataHelper);
Predictions5 = SetPredictions(eval_ID, Tree5.Labels);
#endregion
SetAveragedPredictions();
StandardDeviation = CalculateStandardDeviation(1 - temp_error1, 1 - temp_error2, 1 - temp_error3, 1 - temp_error4, 1 - temp_error5);
//Console.WriteLine(temp_error1);
//Console.WriteLine(temp_error2);
//Console.WriteLine(temp_error3);
//Console.WriteLine(temp_error4);
Error = (temp_error1 + temp_error2 + temp_error3 + temp_error4) / 4;
Accuracies.Add(Tree.Accuracy);
Accuracies.Add(Tree2.Accuracy);
Accuracies.Add(Tree3.Accuracy);
Accuracies.Add(Tree4.Accuracy);
Accuracies.Add(Tree5.Accuracy);
Accuracy = Accuracies.Average();
Depth = Tree.DetermineDepth(0);
}