private void btnUpdate_Click(object sender, EventArgs e)
{
double penalty;
if (Double.TryParse(tbPenalty.Text, out penalty))
{
Penalty = penalty;
if (Tree != null)
{
Tree = new RegressionTree(TestDataSet, "Single Tree", Penalty);
RegressionTreeVisualizator.ClearChart(RegressionChart);
fillRegressionChart();
}
if (Forest != null)
{
Forest = new RandomForest(dataSet, AmountOfTreesInForest, Penalty);
RegressionTreeVisualizator.ClearChart(RandomForestChart);
fillRandomForestChart();
}
}
else
{
MessageBox.Show("Input double value in /Penalty on leaves amount/ field!", "Error");
}
}
public void Train(List <Person> people, int numberOfTrees, int skillSetSize)
{
double[][] inputs = _dataPointService.GenerateDataPointsFromPeople(people, skillSetSize);
int[] expectedResults = _dataPointService.GenerateExpectedResultFromPeople(people);
// Create the forest learning algorithm
var teacher = new RandomForestLearning()
{
NumberOfTrees = numberOfTrees, // use 10 trees in the forest
};
// Finally, learn a random forest from data
_randomForest = teacher.Learn(inputs, expectedResults);
// We can estimate class labels using
trainingPredictions = _randomForest.Decide(inputs);
// And the classification error (0.0006) can be computed as
double error = new ZeroOneLoss(expectedResults).Loss(_randomForest.Decide(inputs));
File.WriteAllLines(
@"C:\Users\Niall\Documents\Visual Studio 2015\Projects\LinkedInSearchUi\LinkedIn Dataset\XML\random_forest_predictions.txt" // <<== Put the file name here
, trainingPredictions.Select(d => d.ToString()).ToArray());
}
public ResultExperimentClassification ExperimentClassification(object a)
{
InfaForExperimentClassification infa = (InfaForExperimentClassification)a;
ResultExperimentClassification result = new ResultExperimentClassification();
result.timeTrain = new Stopwatch();
result.timeTest = new Stopwatch();
result.timeСlassification = new Stopwatch();
RandomForest RF = new RandomForest();
RF.setNumIterations(100); //Количество деревьев
result.timeTrain.Start();
RF.buildClassifier(infa.trainDataSet); //Обучние
result.timeTrain.Stop();
result.timeTest.Start();
result.evaluation = evaluateModel(RF, infa.trainDataSet, infa.testDataSet); //Тестирование
result.timeTest.Stop();
result.timeСlassification.Start();
RF.classifyInstance(infa.testDataSet.instance(0)); //Замер времени классификации 1 экземпляра
result.timeСlassification.Stop();
return(result);
}
public static double resultPrepareWithCrossFold(string classifierFileName, int baseClasses, string clasifier)
{
double performance = 0.0;
if (clasifier == "svm")
{
weka.classifiers.Classifier svm = new SMO();
performance = Weka.classifyCrossFold_Train_Test(classifierFileName, baseClasses, svm);
}
else if (clasifier == "nb")
{
weka.classifiers.Classifier nb = new NaiveBayes();
performance = Weka.classifyCrossFold_Train_Test(classifierFileName, baseClasses, nb);
}
else if (clasifier == "rf")
{
weka.classifiers.Classifier rf = new RandomForest();
performance = Weka.classifyCrossFold_Train_Test(classifierFileName, baseClasses, rf);
}
else if (clasifier == "j48")
{
weka.classifiers.Classifier j48 = new J48();
performance = Weka.classifyCrossFold_Train_Test(classifierFileName, baseClasses, j48);
}
return(performance);
}
static void BestClassificator(RandomForest forest, DecisionTree tree, KNearestNeighbors knn, double[] precision)
{
if (precision[0] > precision[1])
{
Console.WriteLine("Geriausias parinktas klasifikavimo metodas: {0}", "Random Forest");
Console.Write("Iveskite penkiu kortu rinkini, skaicius atskirdamo tarpu: ");
string[] val = Console.ReadLine().Split(' ');
double[] hand = new double[10];
for (int i = 0; i < 10; i++)
{
hand[i] = Convert.ToDouble(val[i]);
}
Console.WriteLine(forest.Decide(hand));
}
else
{
Console.WriteLine("Geriausias parinktas klasifikavimo metodas: %s", "Decision Tree");
Console.Write("Iveskite penkiu kortu rinkini, skaicius atskirdamo tarpu: ");
string[] val = Console.ReadLine().Split(' ');
double[] hand = new double[10];
for (int i = 0; i < 10; i++)
{
hand[i] = Convert.ToDouble(val[i]);
}
Console.WriteLine(tree.Decide(hand));
}
}
public ResultExperimentClassification TestClassification(object a)
{
InfaForExperimentClassification infa = (InfaForExperimentClassification)a;
ResultExperimentClassification result = new ResultExperimentClassification();
result.timeTrain = new Stopwatch();
result.timeTest = new Stopwatch();
result.timeСlassification = new Stopwatch();
RandomForest RF = (RandomForest)SerializationHelper.read(infa.fileNameModel); //Загрузка модели
//RandomForest RF = new RandomForest();
result.timeTest.Start();
result.evaluation = evaluateModel(RF, infa.trainDataSet, infa.testDataSet); //Тестирование
result.timeTest.Stop();
result.timeСlassification.Start();
RF.classifyInstance(infa.testDataSet.instance(0)); //Замер времени классификации 1 экземпляра
result.timeСlassification.Stop();
return(result);
}
private void ClassifierList_MouseUp(object sender, MouseEventArgs e)
{
if (e.Button == System.Windows.Forms.MouseButtons.Right && SelectedItem != null)
{
Classifier classifier = SelectedItem as Classifier;
if (classifier == null)
{
throw new NullReferenceException("Failed to cast classifier item from list");
}
string updateWindowTitle = "Updating " + classifier.GetType().Name + "...";
if (classifier is LibLinear)
{
LibLinear liblinear = classifier as LibLinear;
DynamicForm f = new DynamicForm("Set LibLinear parameters", DynamicForm.CloseButtons.OkCancel);
f.AddCheckBox("Run feature selection:", ContentAlignment.MiddleRight, liblinear.RunFeatureSelection, "run_feature_selection");
f.AddDropDown("Positive weighting:", Enum.GetValues(typeof(LibLinear.PositiveClassWeighting)), liblinear.Weighting, "positive_weighting", true);
if (f.ShowDialog() == DialogResult.OK)
{
liblinear.RunFeatureSelection = f.GetValue <bool>("run_feature_selection");
liblinear.Weighting = f.GetValue <LibLinear.PositiveClassWeighting>("positive_weighting");
}
}
else if (classifier is SvmRank)
{
SvmRank svmRank = classifier as SvmRank;
DynamicForm f = new DynamicForm("Set SvmRank parameters", DynamicForm.CloseButtons.OkCancel);
f.AddNumericUpdown("c:", (decimal)svmRank.C, 3, decimal.MinValue, decimal.MaxValue, (decimal)0.01, "c");
if (f.ShowDialog() == DialogResult.OK)
{
try { svmRank.C = Convert.ToSingle(f.GetValue <decimal>("c")); }
catch (Exception ex) { MessageBox.Show("Invalid value for C: " + ex.Message); }
}
}
else if (classifier is RandomForest)
{
RandomForest randomForest = classifier as RandomForest;
DynamicForm f = new DynamicForm("Set RandomForest parameters", DynamicForm.CloseButtons.OkCancel);
f.AddNumericUpdown("Number of trees:", randomForest.NumTrees, 0, 1, decimal.MaxValue, 1, "ntree");
if (f.ShowDialog() == DialogResult.OK)
{
randomForest.NumTrees = Convert.ToInt32(f.GetValue <decimal>("ntree"));
}
}
else if (classifier is AdaBoost)
{
AdaBoost adaBoost = classifier as AdaBoost;
DynamicForm f = new DynamicForm("Set AdaBoost parameters", DynamicForm.CloseButtons.OkCancel);
f.AddNumericUpdown("Number of iterations:", adaBoost.Iterations, 0, 1, decimal.MaxValue, 1, "iterations");
if (f.ShowDialog() == DialogResult.OK)
{
adaBoost.Iterations = Convert.ToInt32(f.GetValue <decimal>("iterations"));
}
}
}
}
private static void Predict()
{
var lgrPred = -1;
var lgrProb = -1.0;
if (MultinomialLogisticRegression != null)
{
lgrPred = MultinomialLogisticRegression.Decide(CurrPredictionPoints);
lgrProb = MultinomialLogisticRegression.Probability(CurrPredictionPoints);
PredictedFrequencyClassifiers = lgrPred;
if (Classification.IsValidation)
{
Console.WriteLine($"Real Frequency: {BrainStorm0.ClassificationShape.Hertz} Logistic Regression Predicted Frequency: {lgrPred} Probability: {lgrProb}");
}
}
var mmdPred = -1;
var mmdScore = -1.0;
if (MinimumMeanDistance != null)
{
mmdPred = MinimumMeanDistance.Decide(CurrPredictionPoints);
mmdScore = MinimumMeanDistance.Score(CurrPredictionPoints);
if (Classification.IsValidation)
{
Console.WriteLine(
$"Real Frequency: {BrainStorm0.ClassificationShape.Hertz} Minimun Distance Predicted Frequency: {PredictedFrequencyClassifiers}");
}
else
{
Console.WriteLine(
$"MMD Predicted Frequency: {mmdPred} {mmdScore}");
}
}
var rfPred = -1;
if (RandomForest != null)
{
rfPred = RandomForest.Decide(CurrPredictionPoints);
if (Classification.IsValidation)
{
Console.WriteLine(
$"Real Frequency: {BrainStorm0.ClassificationShape.Hertz} Random Forest Predicted Frequency: {rfPred}");
}
else
{
Console.WriteLine(
$"Random Forest Predicted Frequency: {rfPred}");
}
}
if (IsTyping)
{
UpdateTypingPredictions();
}
}
public RandomForest TrainClassification(object a)
{
InfaForExperimentClassification infa = (InfaForExperimentClassification)a;
RandomForest RF = new RandomForest();
RF.setNumIterations(100); //Количество деревьев
RF.buildClassifier(infa.trainDataSet); //Обучние
SerializationHelper.write(infa.fileNameModel, RF); //Сохранение модели
return(RF);
}
public void buildModel()
{
var attributes = DecisionVariable.FromData(inputs);
// Now, let's create the forest learning algorithm
var teacher = new RandomForestLearning(attributes)
{
NumberOfTrees = 1,
SampleRatio = 1.0
};
// Finally, learn a random forest from data
this.forest = teacher.Learn(inputs, outputs);
}
public void test_building_predictions_lines()
{
Runtime rt = Runtime.LoadFromFile <TitanicDataRow>(0, TestingHelpers.GetResourceFileName("titanic_train.csv"));
RandomForest cls = rt.Classifiers.Trees.RandomForest.
NumExecutionSlots(4).
NumFeatures(5).
NumTrees(50);
Runtime testset = Runtime.LoadFromFile <TitanicDataRow>(0, TestingHelpers.GetResourceFileName("titanic_test.csv"), preprocessor: TestLinePreproc);
int count = testset.NumInstances;
System.Collections.Generic.List <string> lines = testset.GeneratePredictions(GeneratePredictionLine, cls);
Assert.AreEqual(count, lines.Count);
}
public RandomForestClassifier(FeatureValueTypes featureDefaultsValueTypes, FeatureGranularities featureGranularities, string serializedClassifierPath = null)
{
var featureKinds = new List <DecisionVariable>();
foreach (var entry in featureDefaultsValueTypes)
{
var featureName = entry.Key.ToString();
var featureType = entry.Value;
var featureGranularity = featureGranularities[entry.Key];
if (featureGranularity == FeatureGranularity.Continuous)
{
featureKinds.Add(new DecisionVariable(featureName, DecisionVariableKind.Continuous));
}
else if (featureGranularity == FeatureGranularity.Discrete)
{
var decisionVar = new DecisionVariable(featureName, DecisionVariableKind.Discrete);
// TODO: Fix uint, there is no Accord.UIntRange
if (featureType == (typeof(int)) || featureType == (typeof(int?)) || featureType == (typeof(uint)) || featureType == (typeof(uint?)))
{
decisionVar.Range = new Accord.IntRange(min: int.MinValue, max: int.MaxValue);
}
else if (featureType == (typeof(byte)) || featureType == (typeof(byte?)))
{
decisionVar.Range = new Accord.IntRange(min: byte.MinValue, max: byte.MaxValue);
}
featureKinds.Add(decisionVar);
}
else
{
throw new ArgumentException("Unknown feature granularity");
}
}
var featureKindsArr = featureKinds.ToArray <DecisionVariable>();
this.RandomForestLearner = new RandomForestLearning(featureKindsArr)
{
NumberOfTrees = 10
};
if (serializedClassifierPath != null)
{
this.RandomForest = Serializer.Load <RandomForest>(serializedClassifierPath);
}
}
static void Dirbam()
{
DownloadTrainingAndTestingData();
List <int[]> trainingData = ReadData("poker-hand-training-true.data");
List <int[]> testingData = ReadData("poker-hand-testing.data");
double[] precision = new double[3];
RandomForest ranForest = RandomForestClassification(trainingData, testingData, out precision[0]);
DecisionTree decisionTree = DecisionTreeClassification(trainingData, testingData, out precision[1]);
KNearestNeighbors knn = kNearestNeighbours(trainingData, testingData, out precision[2]);
BestClassificator(ranForest, decisionTree, knn, precision);
Console.ReadKey();
}
public ICU()
{
InitializeComponent();
current_frame_num1 = 0;
current_frame_num2 = 0;
F_E = new FeaturesExtraction();
knn = Serializer.Load <KNearestNeighbors>(Path.Combine(path, "knn7.bin"));
RF = Serializer.Load <RandomForest>(Path.Combine(path, "RF7.bin"));
LR = Serializer.Load <LogisticRegression>(Path.Combine(path, "LR7.bin"));
SVM = Serializer.Load <SupportVectorMachine <Gaussian> >(Path.Combine(path, "SVM7.bin"));
NB = Serializer.Load <NaiveBayes>(Path.Combine(path, "NB7.bin"));
HMM = Serializer.Load <HiddenMarkovModel>(Path.Combine(path, "HMM_seq7.bin"));
dataGridView1.RowTemplate.Height = 120;
((DataGridViewImageColumn)dataGridView1.Columns[0]).ImageLayout = DataGridViewImageCellLayout.Stretch;
dataGridView1.Columns[1].Visible = false;
}
private void PreprocessToWorkTreeRandomForest(TrainData trainedData, TrainData checkData,
Dictionary <int, string> analysParameter)
{
int numberOfForest = Convert.ToInt32(numberOfForests.Value);
RandForests = new List <DM.DecisionTree.TreeNode>();
//double accuracy = 0.0;
//do
//{
//Random rand = new Random((int) (DateTime.Now.Ticks));
//DivideSet(rand, trainData, trainedData, checkData);
List <DM.DecisionTree.TreeNode> rndForests = new List <DM.DecisionTree.TreeNode>();
int parameterID = XMLWork.FindIDWithName(parameterCondition.SelectedItem.ToString(), Properties.Settings.Default.Languages);
int restrictCountOfParameters = Convert.ToInt32(Math.Sqrt(analysParameter.Count)) + 1;
Dictionary <int, string> newParameters = new Dictionary <int, string>();
for (int forestsCount = 0; forestsCount < numberOfForest;)
{
DM.DecisionTree.RandomForest random = new RandomForest();
List <int> parametersName = new List <int>();
foreach (KeyValuePair <int, string> keyValuePair in analysParameter)
{
if (!keyValuePair.Value.StartsWith("Def"))
{
parametersName.Add(keyValuePair.Key);
}
}
for (int i = 0; i < restrictCountOfParameters; i++)
{
int j = rand.Next(0, analysParameter.Count);
if (!newParameters.ContainsKey(parametersName[j]))
{
newParameters.Add(parametersName[j], analysParameter[parametersName[j]]);
}
}
List <OneRow> trainData = new List <OneRow>();
trainData = GetRandomData(TrainData.Train, newParameters, parameterID);
_root = random.MountTree(trainData, newParameters, parameterID, Convert.ToInt32(textEdit1.Value) + 1);
if (_root.attributeName != "False")
{
RandForests.Add(_root);
forestsCount++;
}
newParameters.Clear();
}
}
/// <summary>
/// Invoke weka jar to create an arff from a csv file
/// </summary>
protected override RandomForestFromWekaOutput Perform(RandomForestFromWekaInput input)
{
s_logger.Debug($"RandomForestFromWeka starts");
try
{
var outputTreeFile = $"{input.TrainingSetCsv}.wtree";
var outputArffFile = $"{input.TrainingSetCsv}.arff";
RandomForest forest = null;
if (!File.Exists(outputTreeFile))
{
// lets analyze this in here
try
{
var arffExitCode = WriteArff(input, outputArffFile);
s_logger.Debug($"ArffWrite returns exitCode={arffExitCode}");
if (File.Exists(outputArffFile))
{
var exitCode = RunWeka(input, outputArffFile, outputTreeFile);
s_logger.Debug($"RandomForestFromWeka returns exitCode={exitCode}");
}
else
{
s_logger.Error($"Could not write arff file for [{input.TrainingSetCsv}]");
}
}
catch (Exception e)
{
s_logger.Error(e, "An exception ocurred when writting forest from weka");
}
finally
{
if (!File.Exists(outputTreeFile))
{
throw new Exception($"RandomForestFromWeka task failed to write output to [{outputTreeFile}]");
}
}
}
// and now load the forest
forest = RandomForest.FromWekaFile(outputTreeFile);
// done
return(new RandomForestFromWekaOutput(forest, input.TrainingSetCsv, outputTreeFile));
}
finally
{
s_logger.Debug($"RandomForestFromWeka ends in {Stopwatch.ElapsedMilliseconds}ms");
}
}
public void Uczenie(string[] naglowki, string[][] dane)
{
Codification kody = new Codification(naglowki, dane);
int[][] symbole = kody.Transform(dane);
int[][] daneWejsciowe = symbole.Get(null, 0, -1);
KolumnaWynikow = symbole.GetColumn(-1);
RandomForestLearning nauczyciel = new RandomForestLearning()
{
SampleRatio = IloscDanychModelu
};
RandomForest las = nauczyciel.Learn(daneWejsciowe, KolumnaWynikow);
Rezultaty = las.Decide(daneWejsciowe);
}
public void TestTrain()
{
var randomForest = new RandomForest();
var randomForestParameter = new RandomForestParameter(1, 100, 35);
randomForest.Train(iris.GetInstanceList(), randomForestParameter);
Assert.AreEqual(2.00, 100 * randomForest.Test(iris.GetInstanceList()).GetErrorRate(), 0.01);
randomForest.Train(bupa.GetInstanceList(), randomForestParameter);
Assert.AreEqual(42.03, 100 * randomForest.Test(bupa.GetInstanceList()).GetErrorRate(), 0.01);
randomForest.Train(dermatology.GetInstanceList(), randomForestParameter);
Assert.AreEqual(2.46, 100 * randomForest.Test(dermatology.GetInstanceList()).GetErrorRate(), 0.01);
randomForest.Train(car.GetInstanceList(), randomForestParameter);
Assert.AreEqual(0.0, 100 * randomForest.Test(car.GetInstanceList()).GetErrorRate(), 0.01);
randomForest.Train(tictactoe.GetInstanceList(), randomForestParameter);
Assert.AreEqual(0.0, 100 * randomForest.Test(tictactoe.GetInstanceList()).GetErrorRate(), 0.01);
randomForest.Train(nursery.GetInstanceList(), randomForestParameter);
Assert.AreEqual(0.0, 100 * randomForest.Test(nursery.GetInstanceList()).GetErrorRate(), 0.01);
}
static RandomForest RandomForestClassification(List <int[]> trainingData, List <int[]> testingData, out double precision)
{
int testingCount = testingData.Count / 10;
int trainingCount = testingData.Count - testingCount;
double errorAverage = 0;
int indexTestingStart = testingData.Count - testingCount;
int indexTestingEnd = testingData.Count;
double prec = 0;
Console.WriteLine("Random Forest Classification");
RandomForest bestforest = null;
for (int i = 0; i < iterations; i++)
{
var watch = System.Diagnostics.Stopwatch.StartNew();
Console.WriteLine("Testing from: {0} to {1}", indexTestingStart, indexTestingEnd);
int[][] inputData, testinputData;
int[] outputData, testoutputData;
PrepareInputOutput(out inputData, out outputData, out testinputData, out testoutputData, trainingData, testingData, indexTestingStart, indexTestingEnd);
var RanForest = new RandomForestLearning()
{
NumberOfTrees = 100,
};
var forest = RanForest.Learn(inputData, outputData);
Console.WriteLine("Medis sukurtas - ismokta");
double er = new ZeroOneLoss(testoutputData).Loss(forest.Decide(testinputData));
Console.WriteLine("Apmokymo tikslumas: {0}", 1 - er);
if (1 - er > prec)
{
prec = 1 - er;
bestforest = forest;
}
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("Iteracija baigta per: {0}ms", elapsedMs);
indexTestingEnd = indexTestingStart;
indexTestingStart -= testingCount;
errorAverage += er;
Console.WriteLine("------------------------------------------------------------------------------");
}
precision = 1 - (errorAverage / iterations);
return(bestforest);
}
private static void randomForest(double[][] inputs, int[] outputs)
{
var teacher = new RandomForestLearning()
{
NumberOfTrees = 100, // Use 100 decision trees to cover this problem
};
// Use the learning algorithm to induce the tree
RandomForest rf = teacher.Learn(inputs, outputs);
// Classify the samples using the RF
int[] predicted = rf.Decide(inputs);
// Create a confusion matrix to check the quality of the predictions:
var cm = new ConfusionMatrix(predicted: predicted, expected: outputs);
// Check the accuracy measure:
double accuracy = cm.Accuracy; // (should be 1.0 or 100%)
}
private void btnCreate_Click(object sender, EventArgs e)
{
int amountOfT;
if (Int32.TryParse(tbAmountOfTrees.Text, out amountOfT))
{
AmountOfTreesInForest = Math.Abs(amountOfT);
Forest = new RandomForest(dataSet, AmountOfTreesInForest, Penalty);
addForestPermission();
fillRandomForestChart();
addItemsInDrawComboBox();
MessageBox.Show("Forest was build.");
FillDataGridLearn();
}
else
{
MessageBox.Show("Input integer value in /Amount of trees/ field!", "Error");
}
}
/// <summary>
/// Trains the classifier and computes the training error if option provided.
/// </summary>
/// <param name="trainingData">The training data that will be used to train classifier.</param>
/// <param name="trainingLabels">The training labels related to provided training data.</param>
/// <param name="calculateError">The boolean check to tell if the training error should be calculated.</param>
public override void Train(List <double[]> trainingData, List <int> trainingLabels, bool calculateError = true)
{
LearningAlgorithm = new RandomForestLearning();
if (NumTrees > 0)
{
LearningAlgorithm.NumberOfTrees = NumTrees;
}
if (SamplePropotion > 0)
{
LearningAlgorithm.SampleRatio = SamplePropotion;
}
Model = LearningAlgorithm.Learn(trainingData.ToArray(), trainingLabels.ToArray());
if (calculateError == true)
{
TrainingError = new ZeroOneLoss(trainingLabels.ToArray()).Loss(Model.Decide(trainingData.ToArray()));
}
}
private async void button7_Click(object sender, EventArgs e)
{
saveFileDialog1.Filter = "model файлы (*.model)|*.model|Все файлы (*.*)|*.*";
if (saveFileDialog1.ShowDialog() == DialogResult.OK)
{
InfaForExperimentClassification infa = new InfaForExperimentClassification(); //Инфа для второго потока
trainDataSet.setClassIndex(trainDataSet.numAttributes() - 1); //Установка указателя на атрибут с классами
infa.trainDataSet = trainDataSet;
infa.fileNameModel = saveFileDialog1.FileName;
labelStatus.Text = "Проводится обучение...";
RandomForest RF = await Task.Factory.StartNew(() => TrainClassification(infa));
labelStatus.Text = "Обучение прошло успешно.";
}
}
public void test_making_single_predictions_from_trained_model()
{
Runtime rt = Runtime.LoadFromFile <TitanicDataRow>(0, TestingHelpers.GetResourceFileName("titanic_train.csv"));
RandomForest classifier = rt.Classifiers.Trees.RandomForest.
NumExecutionSlots(4).
NumFeatures(5).
NumTrees(50);
TitanicDataRow row = new TitanicDataRow
{
age = 10,
pclass = "1",
sex = "male",
embarked = "C"
};
double prediction = classifier.ClassifyRow(row);
double proba = classifier.ClassifyRowProba(row);
Assert.AreEqual(0, prediction);
Assert.IsTrue(proba < 0.5);
}
public override void Train(List <double[]> trainingData, List <double> trainingLabels, bool calculateError = true)
{
LearningAlgorithm = new RandomForestLearning();
if (NumTrees > 0)
{
LearningAlgorithm.NumberOfTrees = NumTrees;
}
if (SamplePropotion > 0)
{
LearningAlgorithm.SampleRatio = SamplePropotion;
}
int[][] TrainingData = TypeCasters.DoubleMultiArrayToInt(trainingData).ToArray();
int[] TrainingLabels = TypeCasters.DoubleArrayToInt(trainingLabels).ToArray();
Model = LearningAlgorithm.Learn(TrainingData, TrainingLabels);
if (calculateError == true)
{
TrainingError = new ZeroOneLoss(TrainingLabels).Loss(Model.Decide(TrainingData));
}
}
private static void EvaluateForests(Args arguments)
{
Contract.Requires(arguments.InputDirectory != null, "You must specify an input directory");
Contract.Requires(Directory.Exists(arguments.InputDirectory), "The input directory must exist");
// we have a bunch of forests and we will compare them by classifying against
// unknown samples. The forests are in weka format (wtree)
s_logger.Info("Evaluating random forests...");
// create the tree from the sample csvs...
var treeEvaluationBlock = new ActionBlock <string>(i =>
{
var classifier = RandomForest.FromWekaFile(i);
s_logger.Info($"Evaluating forest from [{i}] against universe");
// and now evaluate
foreach (var evaluationFile in Directory.EnumerateFiles(arguments.InputDirectory, "*.csv"))
{
if (!evaluationFile.Contains("-sample"))
{
classifier.EvaluateOnTrainingSet(evaluationFile, true, false, 0);
}
}
},
new ExecutionDataflowBlockOptions()
{
MaxDegreeOfParallelism = 1
}
);
// post each action
foreach (var treeFile in Directory.EnumerateFiles(arguments.InputDirectory, "*.wtree"))
{
treeEvaluationBlock.Post(treeFile);
}
// complete
treeEvaluationBlock.Complete();
// wait
treeEvaluationBlock.Completion.Wait();
// done...
}
public void Train(double[][] trainingInputs, int[] trainingOutputs)
{
this.RandomForest = this.RandomForestLearner.Learn(trainingInputs, trainingOutputs);
}
private void bwLoadData_DoWork(object sender, DoWorkEventArgs e)
{
try
{
Classifier classif = null;
Datas.Useable train = null;
Datas.Useable test = null;
ConfusionMatrix conf_train, conf_test;
if (e.Argument is ToBackgroundWorkerArgsTree)
{
var args = e.Argument as ToBackgroundWorkerArgsTree;
train = args._Train;
test = args._Test;
classif = new DecisionTree(args._MaxDepth);
classif.Train(train);
conf_train = new ConfusionMatrix(classif.Compile, train);
conf_test = new ConfusionMatrix(classif.Compile, test);
}
else if (e.Argument is ToBackgroundWorkerArgsForest)
{
var args = e.Argument as ToBackgroundWorkerArgsForest;
train = args._Train;
test = args._Test;
classif = new RandomForest(args._MaxDepth, args._TreeCount);
classif.Train(train);
conf_train = new ConfusionMatrix(classif.Compile, train);
conf_test = new ConfusionMatrix(classif.Compile, test);
}
else if (e.Argument is ToBackgroundWorkerArgsAdaBoost)
{
var args = e.Argument as ToBackgroundWorkerArgsAdaBoost;
train = args._Train;
test = args._Test;
classif = new AdaBoost(args._Factory, args._Boosts);
classif.Train(train);
conf_train = new ConfusionMatrix(classif.Compile, train);
conf_test = new ConfusionMatrix(classif.Compile, test);
}
else if (e.Argument is ToBackgroundWorkerkNN)
{
var args = e.Argument as ToBackgroundWorkerkNN;
train = args._Train;
test = args._Test;
classif = new kNN(args._kNN);
classif.Train(train);
conf_train = null;
conf_test = new ConfusionMatrix(classif.Compile, test);
}
else
{
throw new Exception("Not recognized stuff");
}
if (this.bwLoadData.CancellationPending)
{
e.Result = null;
}
else
{
e.Result = new TrainerReturn(
conf_train,
conf_test,
classif);
}
}
catch (Exception exc)
{
e.Result = exc.ToString();
}
}
/// <summary>
/// Loads the trained model.
/// </summary>
/// <param name="path">The location from where to load the trained model.</param>
public override void Load(string path)
{
Model = Accord.IO.Serializer.Load <RandomForest>(path);
}
/// <summary>
/// Constructor
/// </summary>
public RandomForestFromWekaOutput(RandomForest p, string ifn, string pfn)
{
Predictor = p;
PredictorInputFileName = ifn;
PredictorFileName = pfn;
}