public static string Classify(bool useRubine, float duration, bool righthandedness, List<float> SpeakerAngles, PointCollection pointHist, StylusPointCollection S, List<List<int>> hist, List<List<int>> ihist)
{
// Convert all parameters to format used in GestureTests
List<Vector2> InterpretedPoints = new List<Vector2>();
List<Vector2> StylusPoints = new List<Vector2>();
List<Vector2> VelocityHistory = new List<Vector2>();
List<Vector2> InverseVelocityHistory = new List<Vector2>();
foreach(Point P in pointHist)
InterpretedPoints.Add(new Vector2((float)P.X,(float)P.Y));
foreach(StylusPoint P in S)
StylusPoints.Add(new Vector2((float)P.X,(float)P.Y));
for (int i = 0; i < hist[0].Count; i++)
{
VelocityHistory.Add(new Vector2(hist[0][i], hist[1][i]));
InverseVelocityHistory.Add(new Vector2(ihist[0][i], ihist[1][i]));
}
// Create a new Sample, compute the features, and classify
GS = new GestureSample(GestureTests.Types.GestureType.unknown, righthandedness,duration,SpeakerAngles,InterpretedPoints,StylusPoints,VelocityHistory,InverseVelocityHistory);
GS.ComputeFeatures(GestureFeatures.PointsStroke);
if (useRubine)
return EC.Recognizer.Classify(GS).ToString();
WriteARFF();
Instances test = new Instances(new java.io.FileReader("outfile.arff"));
test.setClassIndex(0);
double clsLabel = cls.classifyInstance(test.instance(0));
test.instance(0).setClassValue(clsLabel);
// Return the appropriate label
return ((GestureType2D)((int)clsLabel+1)).ToString();
}
public List <double> testMLPUsingWeka(string[] attributeArray, string[] classNames, double[] dataValues, string classHeader, string defaultclass, string modelName, int hiddelLayers = 7, double learningRate = 0.03, double momentum = 0.4, int decimalPlaces = 2, int trainingTime = 1000)
{
java.util.ArrayList classLabel = new java.util.ArrayList();
foreach (string className in classNames)
{
classLabel.Add(className);
}
weka.core.Attribute classHeaderName = new weka.core.Attribute(classHeader, classLabel);
java.util.ArrayList attributeList = new java.util.ArrayList();
foreach (string attribute in attributeArray)
{
weka.core.Attribute newAttribute = new weka.core.Attribute(attribute);
attributeList.Add(newAttribute);
}
attributeList.add(classHeaderName);
weka.core.Instances data = new weka.core.Instances("TestInstances", attributeList, 0);
data.setClassIndex(data.numAttributes() - 1);
// Set instance's values for the attributes
weka.core.Instance inst_co = new DenseInstance(data.numAttributes());
for (int i = 0; i < data.numAttributes() - 1; i++)
{
inst_co.setValue(i, dataValues.ElementAt(i));
}
inst_co.setValue(classHeaderName, defaultclass);
data.add(inst_co);
java.io.File path = new java.io.File("/models/");
weka.classifiers.functions.MultilayerPerceptron clRead = loadModel(modelName, path);
clRead.setHiddenLayers(hiddelLayers.ToString());
clRead.setLearningRate(learningRate);
clRead.setMomentum(momentum);
clRead.setNumDecimalPlaces(decimalPlaces);
clRead.setTrainingTime(trainingTime);
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(data);
data = weka.filters.Filter.useFilter(data, myRandom);
double classValue = clRead.classifyInstance(data.get(0));
double[] predictionDistribution = clRead.distributionForInstance(data.get(0));
List <double> predictionDistributions = new List <double>();
for (int predictionDistributionIndex = 0;
predictionDistributionIndex < predictionDistribution.Count();
predictionDistributionIndex++)
{
string classValueString1 = classLabel.get(predictionDistributionIndex).ToString();
double prob = predictionDistribution[predictionDistributionIndex] * 100;
predictionDistributions.Add(prob);
}
List <double> prediction = new List <double>();
prediction.Add(classValue);
prediction.AddRange(predictionDistributions);
return(prediction);
}
// Test the classification result of each map that a user played,
// with the data available as if they were playing through it
public static void classifyTest(String dataString, String playerID)
{
String results = "";
try {
java.io.StringReader stringReader = new java.io.StringReader(dataString);
java.io.BufferedReader buffReader = new java.io.BufferedReader(stringReader);
/* NOTE THAT FOR NAIVE BAYES ALL WEIGHTS CAN BE = 1*/
//weka.core.converters.ConverterUtils.DataSource source = new weka.core.converters.ConverterUtils.DataSource("iris.arff");
weka.core.Instances data = new weka.core.Instances(buffReader); //source.getDataSet();
// setting class attribute if the data format does not provide this information
// For example, the XRFF format saves the class attribute information as well
if (data.classIndex() == -1)
data.setClassIndex(data.numAttributes() - 1);
weka.classifiers.Classifier cl;
for (int i = 3; i < data.numInstances(); i++) {
cl = new weka.classifiers.bayes.NaiveBayes();
//cl = new weka.classifiers.trees.J48();
//cl = new weka.classifiers.lazy.IB1();
//cl = new weka.classifiers.functions.MultilayerPerceptron();
((weka.classifiers.functions.MultilayerPerceptron)cl).setHiddenLayers("12");
weka.core.Instances subset = new weka.core.Instances(data,0,i);
cl.buildClassifier(subset);
weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(subset);
eval.crossValidateModel(cl, subset, 3, new java.util.Random(1));
results = results + eval.pctCorrect(); // For accuracy measurement
/* For Mathews Correlation Coefficient */
//double TP = eval.numTruePositives(1);
//double FP = eval.numFalsePositives(1);
//double TN = eval.numTrueNegatives(1);
//double FN = eval.numFalseNegatives(1);
//double correlationCoeff = ((TP*TN)-(FP*FN))/Math.Sqrt((TP+FP)*(TP+FN)*(TN+FP)*(TN+FN));
//results = results + correlationCoeff;
if (i != data.numInstances()-1)
results = results + ", ";
if(i == data.numInstances()-1)
Debug.Log("Player: " + playerID + ", Num Maps: " + data.numInstances() + ", AUC: " + eval.areaUnderROC(1));
}
} catch (java.lang.Exception ex)
{
Debug.LogError(ex.getMessage());
}
// Write values to file for a matlab read
// For accuracy
StreamWriter writer = new StreamWriter("DataForMatlab/"+playerID+"_CrossFoldValidations_NeuralNet.txt");
//StreamWriter writer = new StreamWriter("DataForMatlab/"+playerID+"_CrossFoldCorrCoeff.txt"); // For mathews cc
writer.WriteLine(results);
writer.Close();
Debug.Log(playerID + " has been written to file");
}
public static double classifyTrain_Test(string classifierFileName, Classifier _classifier)
{
double performance = 0.0;
try
{
FileReader javaFileReader = new FileReader(classifierFileName);
weka.core.Instances insts = new weka.core.Instances(javaFileReader);
javaFileReader.close();
insts.setClassIndex(insts.numAttributes() - 1);
System.Console.WriteLine("Performing " + percentSplit + "% split evaluation.");
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
_classifier.buildClassifier(train);
int numCorrect = 0;
var numnerOfInst = insts.numInstances();
int dataIndex = 0;
for (int i = trainSize; i < numnerOfInst; i++)
{
dataIndex++;
weka.core.Instance currentInst = insts.instance(i);
double predictClass = _classifier.classifyInstance(currentInst);
double[] dist = _classifier.distributionForInstance(currentInst);
string actualClass = insts.classAttribute().value((int)insts.instance(i).classValue());
string predictedClass = insts.classAttribute().value((int)predictClass);
var abcd = _classifier.getClass();
if (predictedClass == actualClass)
{
numCorrect++;
}
}
performance = (double)((double)numCorrect / (double)testSize) * 100;
System.Console.WriteLine(numCorrect + " out of " + testSize + " correct (" + performance.toString() + "%)");
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
}
return(performance);
}
public static void classifierTwo(string classifierFileName, string predictionModel)
{
FileReader javaFileReader = new FileReader(classifierFileName);
weka.core.Instances wekaInsts = new weka.core.Instances(javaFileReader);
javaFileReader.close();
wekaInsts.setClassIndex(wekaInsts.numAttributes() - 1);
//Classifier nbTree = (Classifier)SerializationHelper.read(Model) as J48;
Instances testDataSet = new Instances(new BufferedReader(new FileReader(classifierFileName)));
testDataSet.setClassIndex(wekaInsts.numAttributes() - 1);
//testDataSet.setClassIndex(10);
Evaluation evaluation = new Evaluation(testDataSet);
J48 model = new J48();
//Classifier myClassifier = (Classifier)SerializationHelper.read(Model) as NaiveBayes;
//Classifier myClassifier = new NaiveBayes();
for (int i = 0; i < testDataSet.numInstances(); i++)
{
Instance instance = testDataSet.instance(i);
//evaluation.evaluateModelOnceAndRecordPrediction(myClassifier, instance);
//evaluation.evaluateModelOnce(myClassifier, instance);
}
foreach (object o in evaluation.predictions().toArray())
{
NominalPrediction prediction = o as NominalPrediction;
if (prediction != null)
{
double[] distribution = prediction.distribution();
double predicted = prediction.predicted();
for (int i = 0; i < distribution.Length; i++)
{
System.Console.WriteLine(distribution[i]);
}
System.Console.WriteLine(predicted);
}
}
System.Console.WriteLine(evaluation);
System.Console.ReadKey();
}
public static double SupportVectorMachineTest(weka.core.Instances insts)
{
try
{
//weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader("iris.arff"));
insts.setClassIndex(insts.numAttributes() - 1);
SupportVectorMachine = new weka.classifiers.functions.SMO();
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myNormalize);
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
SupportVectorMachine.buildClassifier(train);
int numCorrect = 0;
for (int i = trainSize; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
double predictedClass = SupportVectorMachine.classifyInstance(currentInst);
if (predictedClass == insts.instance(i).classValue())
{
numCorrect++;
}
}
return((double)numCorrect / (double)testSize * 100.0);
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
return(0);
}
}
public static void classifierOne(string classifierFileName, string predictionModel)
{
FileReader javaFileReader = new FileReader(classifierFileName);
weka.core.Instances wekaInsts = new weka.core.Instances(javaFileReader);
javaFileReader.close();
wekaInsts.setClassIndex(wekaInsts.numAttributes() - 1);
Classifier cl = new SMO();
//Classifier cl = new NaiveBayes();
java.util.Random random = new java.util.Random(1);
Evaluation evaluation = new Evaluation(wekaInsts);
evaluation.crossValidateModel(cl, wekaInsts, 10, random);
foreach (object o in evaluation.getMetricsToDisplay().toArray())
{
}
int count = 0;
StringBuilder sb = new StringBuilder();
foreach (object o in evaluation.predictions().toArray())
{
NominalPrediction prediction = o as NominalPrediction;
if (prediction != null)
{
double[] distribution = prediction.distribution();
double predicted = prediction.predicted();
double actual = prediction.actual();
string revision = prediction.getRevision();
double weight = prediction.weight();
double margine = prediction.margin();
//bool equals = prediction.@equals();
string distributions = String.Empty;
for (int i = 0; i < distribution.Length; i++)
{
//System.Console.WriteLine(distribution[i]);
distributions += distribution[i];
}
var predictionLine = String.Format("{0} - {1} - {2} - {3} - {4} - {5}\n", actual, predicted, revision, weight, margine, distributions);
sb.Append(predictionLine);
//System.Console.WriteLine(predicted);
}
count++;
}
File_Helper.WriteToFile(sb, predictionModel + "NbCl.txt");
System.Console.WriteLine(count);
System.Console.ReadKey();
}
private async Task loadFileAndMakeElements(string location)
{
if (location.EndsWith(".csv"))
{
weka.core.converters.CSVLoader csvLoader = new weka.core.converters.CSVLoader();
csvLoader.setSource(new java.io.File(location));
insts = csvLoader.getDataSet();
insts.setClassIndex(insts.numAttributes() - 1);
}
else
{
insts = new weka.core.Instances(new java.io.FileReader(location));
insts.setClassIndex(insts.numAttributes() - 1);
}
flowLayoutPanel1.Controls.Clear();
for (int i = 0; i < insts.numAttributes() - 1; i++)
{
if (insts.attribute(i).isNominal() == true)
{
if (insts.attribute(i).numValues() > 0)
{
Label lbl = new Label();
lbl.Text = insts.attribute(i).name().Trim();
lbl.Enabled = true;
ComboBox cmbBox = new ComboBox();
cmbBox.Name = insts.attribute(i).name();
for (int m = 0; m < insts.attribute(i).numValues(); m++)
{
cmbBox.Items.Add(insts.attribute(i).value(m));
}
cmbBox.DropDownStyle = ComboBoxStyle.DropDownList;
cmbBox.Enabled = true;
flowLayoutPanel1.Controls.Add(lbl);
flowLayoutPanel1.Controls.Add(cmbBox);
}
else
{
}
}
else if (insts.attribute(i).isNumeric() == true)
{
Label lbl = new Label();
lbl.Text = insts.attribute(i).name().Trim();
TextBox txtBox = new TextBox();
txtBox.Name = insts.attribute(i).name();
txtBox.KeyPress += new KeyPressEventHandler(txtBox_Keypress);
flowLayoutPanel1.Controls.Add(lbl);
flowLayoutPanel1.Controls.Add(txtBox);
}
}
}
private void button1_Click(object sender, EventArgs e)
{
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(file));
double[] Data = new double[insts.numAttributes()];
for (int i = 0; i < list.Count; i++)
{
if (list[i].GetType() == typeof(TextBox))
{
TextBox txt = (TextBox)list[i];
string value = txt.Text.Replace('.', ',');
Data[i] = Convert.ToDouble(value);
}
else
{
ComboBox combobox = (ComboBox)list[i];
Data[i] = Convert.ToDouble(combobox.SelectedIndex);
}
}
// Data[(insts.numAttributes() - 1] = 0;
insts.setClassIndex(insts.numAttributes() - 1);
Instance newInsts = new Instance(1.0, Data);
insts.add(newInsts);
string type = model.GetType().ToString();
if (type == "weka.classifiers.bayes.NaiveBayes")
{
weka.filters.Filter myDiscretize = new weka.filters.unsupervised.attribute.Discretize();
myDiscretize.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myDiscretize);
}
else if (type == "weka.classifiers.lazy.IBk")
{
weka.filters.Filter myDummy = new weka.filters.unsupervised.attribute.NominalToBinary();
myDummy.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myDummy);
weka.filters.Filter myNormalize = new weka.filters.unsupervised.instance.Normalize();
myNormalize.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myNormalize);
}
double index = model.classifyInstance(insts.lastInstance());
string result = insts.attribute(insts.numAttributes() - 1).value(Convert.ToInt16(index));
MessageBox.Show(result);
}
public void trainMachineForEmotionUsingWeka(string wekaFile, string modelName, int hiddelLayers = 7, double learningRate = 0.03, double momentum = 0.4, int decimalPlaces = 2, int trainingTime = 1000)
{
//"C:\\Users\\Gulraiz\\Desktop\\Genereted2.arff" "MLP"
try
{
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(wekaFile));
insts.setClassIndex(insts.numAttributes() - 1);
weka.classifiers.functions.MultilayerPerceptron cl;
cl = new weka.classifiers.functions.MultilayerPerceptron();
cl.setHiddenLayers(hiddelLayers.ToString());
cl.setLearningRate(learningRate);
cl.setMomentum(momentum);
cl.setNumDecimalPlaces(decimalPlaces);
cl.setTrainingTime(trainingTime);
System.Console.WriteLine("Performing " + percentSplit + "% split evaluation.");
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
java.io.File path = new java.io.File("/models/");
cl.buildClassifier(train);
saveModel(cl, modelName, path);
#region test whole set
//int numCorrect = 0;
//for (int i = trainSize; i < insts.numInstances(); i++)
//{
// weka.core.Instance currentInst = insts.instance(i);
// double predictedClass = cl.classifyInstance(currentInst);
// if (predictedClass == insts.instance(i).classValue())
// numCorrect++;
//}
//System.Console.WriteLine(numCorrect + " out of " + testSize + " correct (" +
// (double)((double)numCorrect / (double)testSize * 100.0) + "%)");
#endregion
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
}
}
public static void JackKnife_Test_prepare(string classifierFileName, int baseClasses, Classifier _classifie)
{
for (int singleClass = 1; singleClass <= baseClasses; singleClass++)
{
string eachFileName = String.Format("{0}_{1}.arff", classifierFileName, singleClass);
FileReader javaFileReader = new FileReader(eachFileName);
weka.core.Instances insts = new weka.core.Instances(javaFileReader);
javaFileReader.close();
insts.setClassIndex(insts.numAttributes() - 1);
var totalnstances = insts.numInstances();
//insts.re
}
}
public static double NaiveBayesTest(weka.core.Instances insts)
{
try
{
//weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader("iris.arff"));
insts.setClassIndex(insts.numAttributes() - 1);
NaiveBayescl = new weka.classifiers.bayes.NaiveBayes();
//discretize
weka.filters.Filter myDiscretize = new weka.filters.unsupervised.attribute.Discretize();
myDiscretize.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myDiscretize);
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
NaiveBayescl.buildClassifier(train);
int numCorrect = 0;
for (int i = trainSize; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
double predictedClass = NaiveBayescl.classifyInstance(currentInst);
if (predictedClass == insts.instance(i).classValue())
{
numCorrect++;
}
}
return((double)numCorrect / (double)testSize * 100.0);
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
return(0);
}
}
public void trainMachineForHybridUsingWeka(string wekaFile, string modelName)
{
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(wekaFile));
insts.setClassIndex(insts.numAttributes() - 1);
weka.classifiers.Classifier bagging = new weka.classifiers.meta.Bagging();
System.Console.WriteLine("Performing " + percentSplit + "% split evaluation.");
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
java.io.File path = new java.io.File("/models/");
bagging.buildClassifier(train);
saveModel(bagging, modelName, path);
}
public List <DrugBrandInfo> AssociateDrugs(int?drugId, string dataPath)
{
List <DrugBrandInfo> drugList = new List <DrugBrandInfo>();
weka.core.Instances data = new weka.core.Instances(new java.io.FileReader(dataPath));
data.setClassIndex(data.numAttributes() - 1);
Apriori apriori = new Apriori();
apriori.setClassIndex(data.classIndex());
apriori.buildAssociations(data);
FastVector[] vector = apriori.getAllTheRules();
for (int i = 0; i < vector[0].size(); i++)
{
string value1 = ((AprioriItemSet)vector[0].elementAt(i)).toString(data);
string value2 = ((AprioriItemSet)vector[1].elementAt(i)).toString(data);
string[] set1 = value1.Split(' ', '=');
string[] set2 = value2.Split(' ', '=');
if (set1[0].Equals(drugId.ToString()))
{
if (set1[1] == "1" && set2[1] == "1")
{
int brandId = Convert.ToInt32(set2[0]);
var drug = db.DrugBrandInfos.SingleOrDefault(c => c.Id == brandId);
drugList.Add(drug);
}
break;
}
}
return(drugList);
}
public string testHybridEmotionUsingWeka(string[] attributeArray, string[] classNames, double[] dataValues, string classHeader, string defaultclass, string modelName)
{
java.util.ArrayList classLabel = new java.util.ArrayList();
foreach (string className in classNames)
{
classLabel.Add(className);
}
weka.core.Attribute classHeaderName = new weka.core.Attribute(classHeader, classLabel);
java.util.ArrayList attributeList = new java.util.ArrayList();
foreach (string attribute in attributeArray)
{
weka.core.Attribute newAttribute = new weka.core.Attribute(attribute);
attributeList.Add(newAttribute);
}
attributeList.add(classHeaderName);
weka.core.Instances data = new weka.core.Instances("TestInstances", attributeList, 0);
data.setClassIndex(data.numAttributes() - 1);
// Set instance's values for the attributes
weka.core.Instance inst_co = new DenseInstance(data.numAttributes());
for (int i = 0; i < data.numAttributes() - 1; i++)
{
inst_co.setValue(i, dataValues.ElementAt(i));
}
inst_co.setValue(classHeaderName, defaultclass);
data.add(inst_co);
java.io.File path = new java.io.File("/models/");
weka.classifiers.meta.Bagging clRead = loadBaggingModel(modelName, path);
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(data);
data = weka.filters.Filter.useFilter(data, myRandom);
double classValue = clRead.classifyInstance(data.get(0));
string classValueString = classLabel.get(Int32.Parse(classValue.ToString())).ToString();
return(classValueString);
}
/* Use when the player logs in to initially create the classifier with data from server */
public void InitializeClassifier(String dataString)
{
try {
java.io.StringReader stringReader = new java.io.StringReader(dataString);
java.io.BufferedReader buffReader = new java.io.BufferedReader(stringReader);
playerData = new weka.core.Instances(buffReader);
/* State where in each Instance the class attribute is, if its not already specified by the file */
if (playerData.classIndex() == -1)
playerData.setClassIndex(playerData.numAttributes() - 1);
/* NAIVE BAYES */
//classifier = new weka.classifiers.bayes.NaiveBayes();
/* NEURAL NET */
//classifier = new weka.classifiers.functions.MultilayerPerceptron();
//((weka.classifiers.functions.MultilayerPerceptron)classifier).setHiddenLayers("12");
/* J48 TREE */
//classifier = new weka.classifiers.trees.J48();
/* IB1 NEAREST NEIGHBOUR */
//classifier = new weka.classifiers.lazy.IB1();
/* RANDOM FOREST */
classifier = new weka.classifiers.trees.RandomForest();
classifier.buildClassifier(playerData);
Debug.Log("Initialized Classifier");
}
catch (java.lang.Exception ex)
{
Debug.LogError(ex.getMessage());
}
}
/// <summary>
/// Create an instances structure with classes for supervised methods
/// </summary>
/// <param name="NumClass"></param>
/// <returns></returns>
public Instances CreateInstancesWithClassesWithPlateBasedDescriptor(int NumberOfClass)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < ParentScreening.ListPlateBaseddescriptorNames.Count; i++)
{
atts.addElement(new weka.core.Attribute(ParentScreening.ListPlateBaseddescriptorNames[i]));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
for (int i = 0; i < NumberOfClass; i++)
attVals.addElement("Class" + (i).ToString());
atts.addElement(new weka.core.Attribute("Class", attVals));
Instances data1 = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (CurrentWell.GetCurrentClassIdx() == -1) continue;
double[] vals = new double[data1.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < ParentScreening.ListPlateBaseddescriptorNames.Count; Col++)
{
vals[IdxCol++] = CurrentWell.ListPlateBasedDescriptors[Col].GetValue();
}
vals[columnNo] = CurrentWell.GetCurrentClassIdx();
data1.add(new DenseInstance(1.0, vals));
IdxWell++;
}
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
public static void Test()
{
weka.core.Instances data = new weka.core.Instances(new java.io.FileReader("./data/Classification/Communication.arff"));
data.setClassIndex(data.numAttributes() - 1);
weka.classifiers.Classifier cls = new weka.classifiers.bayes.BayesNet();
//Save BayesNet results in .txt file
using (System.IO.StreamWriter file = new System.IO.StreamWriter("./data/Classification/Communication_Report.txt"))
{
file.WriteLine("Performing " + percentSplit + "% split evaluation.");
int runs = 1;
// perform cross-validation
for (int i = 0; i < runs; i++)
{
// randomize data
int seed = i + 1;
java.util.Random rand = new java.util.Random(seed);
weka.core.Instances randData = new weka.core.Instances(data);
randData.randomize(rand);
//weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(randData);
int trainSize = (int)Math.Round((double)data.numInstances() * percentSplit / 100);
int testSize = data.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(data, 0, 0);
weka.core.Instances test = new weka.core.Instances(data, 0, 0);
train.setClassIndex(train.numAttributes() - 1);
test.setClassIndex(test.numAttributes() - 1);
//Print classifier analytics for all the dataset
file.WriteLine("EVALUATION OF TEST DATASET.");
//int numCorrect = 0;
for (int j = 0; j < data.numInstances(); j++)
{
weka.core.Instance currentInst = randData.instance(j);
if (j < trainSize)
{
train.add(currentInst);
}
else
{
test.add(currentInst);
/*
* double predictedClass = cls.classifyInstance(currentInst);
*
* double[] prediction = cls.distributionForInstance(currentInst);
*
* for (int p = 0; p < prediction.Length; p++)
* {
* file.WriteLine("Probability of class [{0}] for [{1}] is: {2}", currentInst.classAttribute().value(p), currentInst, Math.Round(prediction[p], 4));
* }
* file.WriteLine();
*
* file.WriteLine();
* if (predictedClass == data.instance(j).classValue())
* numCorrect++;*/
}
}
// build and evaluate classifier
cls.buildClassifier(train);
// Test the model
weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(randData);
eval.evaluateModel(cls, test);
// Print the results as in Weka explorer:
//Print statistics
String strSummaryTest = eval.toSummaryString();
file.WriteLine(strSummaryTest);
file.WriteLine();
//Print detailed class statistics
file.WriteLine(eval.toClassDetailsString());
file.WriteLine();
//Print confusion matrix
file.WriteLine(eval.toMatrixString());
file.WriteLine();
// Get the confusion matrix
double[][] cmMatrixTest = eval.confusionMatrix();
System.Console.WriteLine("Bayesian Network results saved in Communication_Report.txt file successfully.");
}
}
}
public static void BayesTest()
{
try
{
weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader("iris.arff"));
insts.setClassIndex(insts.numAttributes() - 1);
weka.classifiers.Classifier cl = new weka.classifiers.bayes.BayesNet();
System.Console.WriteLine("Performing " + percentSplit + "% split evaluation.");
//randomize the order of the instances in the dataset.
weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
myRandom.setInputFormat(insts);
insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
weka.core.Instances test = new weka.core.Instances(insts, 0, 0);
cl.buildClassifier(train);
//print model
System.Console.WriteLine(cl);
int numCorrect = 0;
for (int i = trainSize; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
double predictedClass = cl.classifyInstance(currentInst);
test.add(currentInst);
double[] prediction = cl.distributionForInstance(currentInst);
for (int x = 0; x < prediction.Length; x++)
{
System.Console.WriteLine("Probability of class [{0}] for [{1}] is: {2}", currentInst.classAttribute().value(x), currentInst, Math.Round(prediction[x], 4));
}
System.Console.WriteLine();
if (predictedClass == insts.instance(i).classValue())
{
numCorrect++;
}
}
System.Console.WriteLine(numCorrect + " out of " + testSize + " correct (" +
(double)((double)numCorrect / (double)testSize * 100.0) + "%)");
// Train the model
weka.classifiers.Evaluation eTrain = new weka.classifiers.Evaluation(train);
eTrain.evaluateModel(cl, train);
// Print the results as in Weka explorer:
//Print statistics
String strSummaryTrain = eTrain.toSummaryString();
System.Console.WriteLine(strSummaryTrain);
//Print detailed class statistics
System.Console.WriteLine(eTrain.toClassDetailsString());
//Print confusion matrix
System.Console.WriteLine(eTrain.toMatrixString());
// Get the confusion matrix
double[][] cmMatrixTrain = eTrain.confusionMatrix();
// Test the model
weka.classifiers.Evaluation eTest = new weka.classifiers.Evaluation(test);
eTest.evaluateModel(cl, test);
// Print the results as in Weka explorer:
//Print statistics
String strSummaryTest = eTest.toSummaryString();
System.Console.WriteLine(strSummaryTest);
//Print detailed class statistics
System.Console.WriteLine(eTest.toClassDetailsString());
//Print confusion matrix
System.Console.WriteLine(eTest.toMatrixString());
// Get the confusion matrix
double[][] cmMatrixTest = eTest.confusionMatrix();
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
}
}
public static void cvdTest()
{
weka.core.Instances data = new weka.core.Instances(new java.io.FileReader("./data/Classification/Communication.arff"));
data.setClassIndex(data.numAttributes() - 1);
weka.classifiers.Classifier cls = new weka.classifiers.bayes.NaiveBayes();
//Save BayesNet results in .txt file
using (System.IO.StreamWriter file = new System.IO.StreamWriter("./data/Classification/Communication_Report.txt"))
{
int runs = 1;
int folds = 10;
// perform cross-validation
for (int i = 0; i < runs; i++)
{
// randomize data
int seed = i + 1;
java.util.Random rand = new java.util.Random(seed);
weka.core.Instances randData = new weka.core.Instances(data);
randData.randomize(rand);
if (randData.classAttribute().isNominal())
{
randData.stratify(folds);
}
weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(randData);
for (int n = 0; n < folds; n++)
{
weka.core.Instances train = randData.trainCV(folds, n);
weka.core.Instances test = randData.testCV(folds, n);
// build and evaluate classifier
//weka.classifiers.Classifier clsCopy = weka.classifiers.Classifier.makeCopy(cls);
cls.buildClassifier(train);
//eval.evaluateModel(cls, test);
//Print classifier analytics for all the dataset
file.WriteLine("EVALUATION OF TEST DATASET.");
// Test the model
weka.classifiers.Evaluation eTest = new weka.classifiers.Evaluation(test);
eTest.evaluateModel(cls, test);
// Print the results as in Weka explorer:
//Print statistics
String strSummaryTest = eTest.toSummaryString();
file.WriteLine(strSummaryTest);
file.WriteLine();
//Print detailed class statistics
file.WriteLine(eTest.toClassDetailsString());
file.WriteLine();
//Print confusion matrix
file.WriteLine(eTest.toMatrixString());
file.WriteLine();
// Get the confusion matrix
double[][] cmMatrixTest = eTest.confusionMatrix();
System.Console.WriteLine("Bayesian Network results saved in Communication_Report.txt file successfully.");
}
//Print classifier analytics for all the dataset
file.WriteLine("EVALUATION OF ALL DATASET.");
cls.buildClassifier(data);
// Train the model
weka.classifiers.Evaluation eAlldata = new weka.classifiers.Evaluation(data);
eAlldata.evaluateModel(cls, data);
// Print the results as in Weka explorer:
//Print statistics
String strSummaryAlldata = eAlldata.toSummaryString();
file.WriteLine(strSummaryAlldata);
file.WriteLine();
//Print detailed class statistics
file.WriteLine(eAlldata.toClassDetailsString());
file.WriteLine();
//Print confusion matrix
file.WriteLine(eAlldata.toMatrixString());
file.WriteLine("----------------");
//print model
file.WriteLine(cls);
file.WriteLine();
}
}
}
public List <double> testSMOUsingWeka(string[] attributeArray, string[] classNames, double[] dataValues, string classHeader, string defaultclass, string modelName, int hiddelLayers = 7, double learningRate = 0.03, double momentum = 0.4, int decimalPlaces = 2, int trainingTime = 1000)
{
java.util.ArrayList classLabel = new java.util.ArrayList();
foreach (string className in classNames)
{
classLabel.Add(className);
}
weka.core.Attribute classHeaderName = new weka.core.Attribute(classHeader, classLabel);
java.util.ArrayList attributeList = new java.util.ArrayList();
foreach (string attribute in attributeArray)
{
weka.core.Attribute newAttribute = new weka.core.Attribute(attribute);
attributeList.Add(newAttribute);
}
attributeList.add(classHeaderName);
weka.core.Instances data = new weka.core.Instances("TestInstances", attributeList, 0);
data.setClassIndex(data.numAttributes() - 1);
// Set instance's values for the attributes
weka.core.Instance inst_co = new DenseInstance(data.numAttributes());
for (int i = 0; i < data.numAttributes() - 1; i++)
{
inst_co.setValue(i, Math.Round(dataValues.ElementAt(i), 5));
}
inst_co.setValue(classHeaderName, defaultclass);
data.add(inst_co);
weka.core.Instance currentInst = data.get(0);
int j = 0;
//foreach (float value in dataValues)
//{
// // double roundedValue = Math.Round(value);
// //var rounded = Math.Floor(value * 100) / 100;
// if (array.ElementAt(j) != value)
// {
// System.Console.WriteLine("Masla occur");
// }
// j++;
//}
//double predictedClass = cl.classifyInstance(data.get(0));
weka.classifiers.functions.SMO clRead = new weka.classifiers.functions.SMO();
try
{
java.io.File path = new java.io.File("/models/");
clRead = loadSMOModel(modelName, path);
}
catch (Exception e)
{
//string p1 = Assembly.GetExecutingAssembly().Location;
string ClassifierName = Path.GetFileName(Path.GetFileName(modelName));
string Path1 = HostingEnvironment.MapPath(@"~//libs//models//" + ClassifierName);
//string Path1 = HostingEnvironment.MapPath(@"~//libs//models//FusionCustomized.model");
clRead = (weka.classifiers.functions.SMO)weka.core.SerializationHelper.read(modelName);
}
// weka.classifiers.functions.SMO clRead = loadSMOModel(modelName, path);
clRead.setBatchSize("100");
clRead.setCalibrator(new weka.classifiers.functions.Logistic());
clRead.setKernel(new weka.classifiers.functions.supportVector.PolyKernel());
clRead.setEpsilon(1.02E-12);
clRead.setC(1.0);
clRead.setDebug(false);
clRead.setChecksTurnedOff(false);
clRead.setFilterType(new SelectedTag(weka.classifiers.functions.SMO.FILTER_NORMALIZE, weka.classifiers.functions.SMO.TAGS_FILTER));
double classValue = clRead.classifyInstance(data.get(0));
double[] predictionDistribution = clRead.distributionForInstance(data.get(0));
//for (int predictionDistributionIndex = 0;
// predictionDistributionIndex < predictionDistribution.Count();
// predictionDistributionIndex++)
//{
// string classValueString1 = classLabel.get(predictionDistributionIndex).ToString();
// double prob= predictionDistribution[predictionDistributionIndex]*100;
// System.Console.WriteLine(classValueString1 + ":" + prob);
//}
List <double> prediction = new List <double>();
prediction.Add(classValue);
//prediction.AddRange(predictionDistribution);
return(prediction);
}
public void trainSMOUsingWeka(string wekaFile, string modelName)
{
try
{
weka.core.converters.CSVLoader csvLoader = new weka.core.converters.CSVLoader();
csvLoader.setSource(new java.io.File(wekaFile));
weka.core.Instances insts = csvLoader.getDataSet();
//weka.core.Instances insts = new weka.core.Instances(new java.io.FileReader(wekaFile));
insts.setClassIndex(insts.numAttributes() - 1);
cl = new weka.classifiers.functions.SMO();
cl.setBatchSize("100");
cl.setCalibrator(new weka.classifiers.functions.Logistic());
cl.setKernel(new weka.classifiers.functions.supportVector.PolyKernel());
cl.setEpsilon(1.02E-12);
cl.setC(1.0);
cl.setDebug(false);
cl.setChecksTurnedOff(false);
cl.setFilterType(new SelectedTag(weka.classifiers.functions.SMO.FILTER_NORMALIZE, weka.classifiers.functions.SMO.TAGS_FILTER));
System.Console.WriteLine("Performing " + percentSplit + "% split evaluation.");
//randomize the order of the instances in the dataset.
// weka.filters.Filter myRandom = new weka.filters.unsupervised.instance.Randomize();
//myRandom.setInputFormat(insts);
// insts = weka.filters.Filter.useFilter(insts, myRandom);
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
java.io.File path = new java.io.File("/models/");
cl.buildClassifier(train);
saveModel(cl, modelName, path);
#region test whole set
int numCorrect = 0;
for (int i = 0; i < insts.numInstances(); i++)
{
weka.core.Instance currentInst = insts.instance(i);
if (i == 12)
{
array = new List <float>();
foreach (float value in currentInst.toDoubleArray())
{
array.Add(value);
}
}
double predictedClass = cl.classifyInstance(currentInst);
if (predictedClass == insts.instance(i).classValue())
{
numCorrect++;
}
}
System.Console.WriteLine(numCorrect + " out of " + testSize + " correct (" +
(double)((double)numCorrect / (double)testSize * 100.0) + "%)");
#endregion
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
}
}
// Test the classification result of each map that a user played,
// with the data available as if they were playing through it
public static void classifyTest(String dataString, String playerID)
{
try {
java.io.StringReader stringReader = new java.io.StringReader(dataString);
java.io.BufferedReader buffReader = new java.io.BufferedReader(stringReader);
/* NOTE THAT FOR NAIVE BAYES ALL WEIGHTS CAN BE = 1*/
//weka.core.converters.ConverterUtils.DataSource source = new weka.core.converters.ConverterUtils.DataSource("iris.arff");
weka.core.Instances thisData = new weka.core.Instances(buffReader); //source.getDataSet();
if (thisData.classIndex() == -1)
thisData.setClassIndex(thisData.numAttributes() - 1);
weka.core.Instances thisUniqueData = new weka.core.Instances(thisData);
if (thisUniqueData.classIndex() == -1)
thisUniqueData.setClassIndex(thisUniqueData.numAttributes() - 1);
thisUniqueData.delete();
if (allUniqueData == null) {
allUniqueData = new weka.core.Instances(thisData);
if (allUniqueData.classIndex() == -1)
allUniqueData.setClassIndex(allUniqueData.numAttributes() - 1);
allUniqueData.delete();
}
weka.core.InstanceComparator com = new weka.core.InstanceComparator(false);
for (int i = 0; i < thisData.numInstances(); i++)
{
bool dup = false;
for (int j = 0; j < allUniqueData.numInstances(); j++)
{
if (com.compare(thisData.instance(i),allUniqueData.instance(j)) == 0)
{
Debug.Log("Duplicate found!");
dup = true;
break;
}
}
if (!dup)
allUniqueData.add(thisData.instance(i));
else
dupInstances++;
}
for (int i = 0; i < thisData.numInstances(); i++)
{
bool dup = false;
for (int j = 0; j < thisUniqueData.numInstances(); j++)
{
if (com.compare(thisData.instance(i),thisUniqueData.instance(j)) == 0)
{
Debug.Log("Duplicate found!");
dup = true;
break;
}
}
if (!dup)
thisUniqueData.add(thisData.instance(i));
else
dupInstancesSamePlayer++;
}
//Debug.Log("All Data Instance Count = " + thisData.numInstances());
//Debug.Log("Unique Data Instance Count = " + thisUniqueData.numInstances());
//Debug.Log("Done!");
} catch (java.lang.Exception ex)
{
Debug.LogError(ex.getMessage());
}
}
public static double classifyCrossFold_Train_Test_onlySelectedClass(string classifierFileName, int baseClasses, Classifier _classifier)
{
double performance = 0.0;
try
{
List <BrResult> results = new List <BrResult>();
for (int singleClass = 1; singleClass <= baseClasses; singleClass++)
{
string eachFileName = String.Format("{0}_{1}.arff", classifierFileName, singleClass);
BrResult result = new BrResult();
result.classNumber = singleClass;
FileReader javaFileReader = new FileReader(eachFileName);
weka.core.Instances insts = new weka.core.Instances(javaFileReader);
javaFileReader.close();
insts.setClassIndex(insts.numAttributes() - 1);
List <Result> eachResults = new List <Result>();
var totalnstances = insts.numInstances();
var foldsInstances = totalnstances / 10;
Instances foldsData = new Instances(insts);
var folds = 10;
int numCorrect = 0;
int dataIndex = 0;
for (int n = 0; n < folds; n++)
{
System.Console.WriteLine("Performing " + n + " folds");
Instances trainFold = foldsData.trainCV(folds, n);
var numnerOfTrainInst = trainFold.numInstances();
Instances testFold = foldsData.testCV(folds, n);
var numnerOfTestInst = testFold.numInstances();
_classifier.buildClassifier(trainFold);
//List<Result> eachResults = new List<Result>();
for (int test = 0; test < numnerOfTestInst; test++)
{
dataIndex++;
Result eachRow = new Result();
eachRow.lineIndex = 0;
weka.core.Instance currentInst = testFold.instance(test);
double predictClass = _classifier.classifyInstance(currentInst);
//double[] dist = _classifier.distributionForInstance(currentInst);
string actualClass = testFold.classAttribute().value((int)testFold.instance(test).classValue());
string predictedClass = testFold.classAttribute().value((int)predictClass);
//var abcd = _classifier.getClass();
if (predictedClass == actualClass)
{
eachRow.correct = "1";
numCorrect++;
}
else
{
eachRow.correct = "0";
}
eachRow.lineIndex = dataIndex;
eachRow.classActual = actualClass;
eachRow.classPredicted = predictedClass;
eachResults.Add(eachRow);
}
}
result.classResult = eachResults;
results.Add(result);
//System.Console.WriteLine(numCorrect + " out of " + testSize + " correct (" + (double)((double)numCorrect / (double)testSize * 100.0) + "%)");
}
#region Evaludation Matrix
var evaluationMatrix = new Dictionary <int, string>();
foreach (var res in results)
{
foreach (var classRes in res.classResult)
{
if (!evaluationMatrix.Keys.Contains(classRes.lineIndex))
{
evaluationMatrix[classRes.lineIndex] = classRes.correct.toString();
}
else
{
evaluationMatrix[classRes.lineIndex] = evaluationMatrix[classRes.lineIndex].toString() + "," + classRes.correct.toString();
}
}
}
#endregion
#region
int correnctlyClassified = 0;
int incorrenctlyClassified = 0;
int totalData = evaluationMatrix.Count;
foreach (var key in evaluationMatrix.Keys)
{
string multiLevelClass = evaluationMatrix[key].ToString();
string[] a = multiLevelClass.Split(',');
int classPredect = 0;
for (int i = 0; i < a.Length; i++)
{
if (a[i] == "0")
{
classPredect++;
}
}
if (classPredect == 0)
{
correnctlyClassified++;
}
else if (classPredect > 0)
{
incorrenctlyClassified++;
}
}
performance = (double)((double)correnctlyClassified / (double)totalData) * 100;
System.Console.WriteLine(performance);
#endregion
}
catch (java.lang.Exception ex)
{
ex.printStackTrace();
}
return(performance);
}
/// <summary>
/// Create an instances structure with classes for supervised methods
/// </summary>
/// <param name="NumClass"></param>
/// <returns></returns>
public Instances CreateInstancesWithClasses(cInfoClass InfoClass, int NeutralClass)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < ParentScreening.ListDescriptors.Count; i++)
{
if (ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(ParentScreening.ListDescriptors[i].GetName()));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
for (int i = 0; i < InfoClass.NumberOfClass; i++)
attVals.addElement("Class__" + (i).ToString());
atts.addElement(new weka.core.Attribute("Class__", attVals));
Instances data1 = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (CurrentWell.GetCurrentClassIdx() == NeutralClass) continue;
double[] vals = new double[data1.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < ParentScreening.ListDescriptors.Count; Col++)
{
if (ParentScreening.ListDescriptors[Col].IsActive() == false) continue;
vals[IdxCol++] = CurrentWell.ListSignatures[Col].GetValue();
}
vals[columnNo] = InfoClass.CorrespondanceTable[CurrentWell.GetCurrentClassIdx()];
data1.add(new DenseInstance(1.0, vals));
IdxWell++;
}
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
/// <summary>
/// Create an instances structure with classes for supervised methods
/// </summary>
/// <param name="NumClass"></param>
/// <returns></returns>
public Instances CreateInstancesWithClasses(List<bool> ListClassSelected)
{
weka.core.FastVector atts = new FastVector();
int columnNo = 0;
for (int i = 0; i < ParentScreening.ListDescriptors.Count; i++)
{
if (ParentScreening.ListDescriptors[i].IsActive() == false) continue;
atts.addElement(new weka.core.Attribute(ParentScreening.ListDescriptors[i].GetName()));
columnNo++;
}
weka.core.FastVector attVals = new FastVector();
foreach (var item in cGlobalInfo.ListWellClasses)
{
attVals.addElement(item.Name);
}
atts.addElement(new weka.core.Attribute("ClassAttribute", attVals));
Instances data1 = new Instances("MyRelation", atts, 0);
int IdxWell = 0;
foreach (cWell CurrentWell in this.ListActiveWells)
{
if (!ListClassSelected[CurrentWell.GetCurrentClassIdx()]) continue;
double[] vals = new double[data1.numAttributes()];
int IdxCol = 0;
for (int Col = 0; Col < ParentScreening.ListDescriptors.Count; Col++)
{
if (ParentScreening.ListDescriptors[Col].IsActive() == false) continue;
vals[IdxCol++] = CurrentWell.ListSignatures[Col].GetValue();
}
vals[columnNo] = CurrentWell.GetCurrentClassIdx();
data1.add(new DenseInstance(1.0, vals));
IdxWell++;
}
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
private Instances createWhyInstances()
{
FastVector fvWhy = createWhyFastVector();
Instances whyInstances = new Instances("WhyInstances", fvWhy, listSecondaryWhyCandidates.Count);
foreach (Token candidate in listSecondaryWhyCandidates)
{
if (candidate.Value == null) continue;
Instance whyInstance = createSingleWhyInstance(fvWhy, candidate);
whyInstance.setDataset(whyInstances);
whyInstances.add(whyInstance);
}
whyInstances.setClassIndex(fvWhy.size() - 1);
return whyInstances;
}
// ---- OPERATIONS ----
///
/// <summary> * Analyze the time series data. The similarity matrices are created
/// * and filled with euclidean distances based on the tolerance values
/// * for similarity.
/// * </summary>
/// * <param name="data"> data to be analyzed </param>
public override void analyze(Instances data)
{
data.setClassIndex(data.numAttributes() - 1);
m_data = data;
m_rangeTemplates.setUpper(data.numAttributes());
//Date startFT = new Date();
// compute fourier transform
FourierTransform dftFilter = new FourierTransform();
dftFilter.setInputFormat(data);
dftFilter.setNumCoeffs(getNumCoeffs());
dftFilter.setUseFFT(getUseFFT());
Instances fourierdata = Filter.useFilter(data, dftFilter);
Date endFT = new Date();
// time taken for FT
//m_DFTTime = new Date(endFT.getTime() - startFT.getTime());
int numdim = data.numAttributes();
//ORIGINAL LINE: m_distancesFreq = new double[numdim][numdim];
//JAVA TO VB & C# CONVERTER NOTE: The following call to the 'RectangularArrays' helper class reproduces the rectangular array initialization that is automatic in Java:
m_distancesFreq = RectangularArrays.ReturnRectangularDoubleArray(numdim, numdim);
//ORIGINAL LINE: m_distancesTime = new double[numdim][numdim];
//JAVA TO VB & C# CONVERTER NOTE: The following call to the 'RectangularArrays' helper class reproduces the rectangular array initialization that is automatic in Java:
m_distancesTime = RectangularArrays.ReturnRectangularDoubleArray(numdim, numdim);
//long ftDistTime = 0;
//long tDistTime = 0;
// compute similarity matrices
for (int i = 0; i < data.numAttributes(); ++i)
{
for (int j = 0; j < i; j++)
{
// not for template sequences
if (m_rangeTemplates.isInRange(i) && m_rangeTemplates.isInRange(j))
{
continue;
}
//Date startFTDist = new Date();
// Compute the Euclidean distance between 2 dims using FT
double[] reCT = fourierdata.attributeToDoubleArray(2 * i);
double[] imCT = fourierdata.attributeToDoubleArray(2 * i + 1);
double[] reCS = fourierdata.attributeToDoubleArray(2 * j);
double[] imCS = fourierdata.attributeToDoubleArray(2 * j + 1);
m_distancesFreq[i][j] = computeEuclidean(reCT, imCT, reCS, imCS);
// if found similar using FT
if (m_distancesFreq[i][j] <= m_epsilon)
{
// then compute normal Euclidean distances between the 2 dims
double[] x = data.attributeToDoubleArray(i);
double[] y = data.attributeToDoubleArray(j);
m_distancesTime[i][j] = computeEuclidean(x, y);
}
//Date endFTDist = new Date();
// time taken for computing similarity based on FT
//ftDistTime += (endFTDist.getTime() - startFTDist.getTime());
// Date startDist = new Date();
//// compute similarity matrices (brute force)
// double[] x1 = data.attributeToDoubleArray(i);
// double[] y1 = data.attributeToDoubleArray(j);
// computeEuclidean(x1, y1);
// Date endDist = new Date();
//// time taken for computing similarity based brute force method
// tDistTime += (endDist.getTime() - startDist.getTime());
}
}
//m_FTEuclideanTime = new Date(ftDistTime);
//m_EuclideanTime = new Date(tDistTime);
}
/// <summary>
/// Create a single instance for WEKA
/// </summary>
/// <param name="NClasses">Number of classes</param>
/// <returns>the weka instances</returns>
public Instances CreateInstanceForNClasses(cInfoClass InfoClass)
{
List<double> AverageList = new List<double>();
for (int i = 0; i < Parent.ListDescriptors.Count; i++)
if (Parent.ListDescriptors[i].IsActive()) AverageList.Add(GetAverageValuesList()[i]);
weka.core.FastVector atts = new FastVector();
List<string> NameList = Parent.ListDescriptors.GetListNameActives();
for (int i = 0; i < NameList.Count; i++)
atts.addElement(new weka.core.Attribute(NameList[i]));
weka.core.FastVector attVals = new FastVector();
for (int i = 0; i < InfoClass.NumberOfClass; i++)
attVals.addElement("Class" + i);
atts.addElement(new weka.core.Attribute("Class__", attVals));
Instances data1 = new Instances("SingleInstance", atts, 0);
double[] newTable = new double[AverageList.Count + 1];
Array.Copy(AverageList.ToArray(), 0, newTable, 0, AverageList.Count);
//newTable[AverageList.Count] = 1;
data1.add(new DenseInstance(1.0, newTable));
data1.setClassIndex((data1.numAttributes() - 1));
return data1;
}
/// <summary>
/// Build the learning model for classification
/// </summary>
/// <param name="InstancesList">list of instances </param>
/// <param name="NumberofClusters">Number of Clusters</param>
/// <param name="TextBoxForFeedback">Text box for the results (can be NULL)</param>
/// <param name="PanelForVisualFeedback">Panel to display visual results if avalaible (can be NULL)</param>
public Classifier PerformTraining(FormForClassificationInfo WindowForClassificationParam, Instances InstancesList, /*int NumberofClusters,*/ RichTextBox TextBoxForFeedback,
Panel PanelForVisualFeedback, out weka.classifiers.Evaluation ModelEvaluation, bool IsCellular)
{
// weka.classifiers.Evaluation ModelEvaluation = null;
// FormForClassificationInfo WindowForClassificationParam = new FormForClassificationInfo(GlobalInfo);
ModelEvaluation = null;
// if (WindowForClassificationParam.ShowDialog() != System.Windows.Forms.DialogResult.OK) return null;
// weka.classifiers.Evaluation ModelEvaluation = new Evaluation(
cParamAlgo ClassifAlgoParams = WindowForClassificationParam.GetSelectedAlgoAndParameters();
if (ClassifAlgoParams == null) return null;
//this.Cursor = Cursors.WaitCursor;
// cParamAlgo ClassificationAlgo = WindowForClassificationParam.GetSelectedAlgoAndParameters();
cListValuesParam Parameters = ClassifAlgoParams.GetListValuesParam();
//Classifier this.CurrentClassifier = null;
// -------------------------- Classification -------------------------------
// create the instances
// InstancesList = this.ListInstances;
this.attValsWithoutClasses = new FastVector();
if (IsCellular)
for (int i = 0; i < cGlobalInfo.ListCellularPhenotypes.Count; i++)
this.attValsWithoutClasses.addElement(cGlobalInfo.ListCellularPhenotypes[i].Name);
else
for (int i = 0; i < cGlobalInfo.ListWellClasses.Count; i++)
this.attValsWithoutClasses.addElement(cGlobalInfo.ListWellClasses[i].Name);
InstancesList.insertAttributeAt(new weka.core.Attribute("Class", this.attValsWithoutClasses), InstancesList.numAttributes());
//int A = Classes.Count;
for (int i = 0; i < Classes.Count; i++)
InstancesList.get(i).setValue(InstancesList.numAttributes() - 1, Classes[i]);
InstancesList.setClassIndex(InstancesList.numAttributes() - 1);
weka.core.Instances train = new weka.core.Instances(InstancesList, 0, InstancesList.numInstances());
if (PanelForVisualFeedback != null)
PanelForVisualFeedback.Controls.Clear();
#region List classifiers
#region J48
if (ClassifAlgoParams.Name == "J48")
{
this.CurrentClassifier = new weka.classifiers.trees.J48();
((J48)this.CurrentClassifier).setMinNumObj((int)Parameters.ListDoubleValues.Get("numericUpDownMinInstLeaf").Value);
((J48)this.CurrentClassifier).setConfidenceFactor((float)Parameters.ListDoubleValues.Get("numericUpDownConfFactor").Value);
((J48)this.CurrentClassifier).setNumFolds((int)Parameters.ListDoubleValues.Get("numericUpDownNumFolds").Value);
((J48)this.CurrentClassifier).setUnpruned((bool)Parameters.ListCheckValues.Get("checkBoxUnPruned").Value);
((J48)this.CurrentClassifier).setUseLaplace((bool)Parameters.ListCheckValues.Get("checkBoxLaplacianSmoothing").Value);
((J48)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeedNumber").Value);
((J48)this.CurrentClassifier).setSubtreeRaising((bool)Parameters.ListCheckValues.Get("checkBoxSubTreeRaising").Value);
// CurrentClassif.SetJ48Tree((J48)this.CurrentClassifier, Classes.Length);
this.CurrentClassifier.buildClassifier(train);
// display results training
// display tree
if (PanelForVisualFeedback != null)
{
GViewer GraphView = DisplayTree(GlobalInfo, ((J48)this.CurrentClassifier), IsCellular).gViewerForTreeClassif;
GraphView.Size = new System.Drawing.Size(PanelForVisualFeedback.Width, PanelForVisualFeedback.Height);
GraphView.Anchor = (AnchorStyles.Bottom | AnchorStyles.Top | AnchorStyles.Left | AnchorStyles.Right);
PanelForVisualFeedback.Controls.Clear();
PanelForVisualFeedback.Controls.Add(GraphView);
}
}
#endregion
#region Random Tree
else if (ClassifAlgoParams.Name == "RandomTree")
{
this.CurrentClassifier = new weka.classifiers.trees.RandomTree();
if ((bool)Parameters.ListCheckValues.Get("checkBoxMaxDepthUnlimited").Value)
((RandomTree)this.CurrentClassifier).setMaxDepth(0);
else
((RandomTree)this.CurrentClassifier).setMaxDepth((int)Parameters.ListDoubleValues.Get("numericUpDownMaxDepth").Value);
((RandomTree)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
((RandomTree)this.CurrentClassifier).setMinNum((double)Parameters.ListDoubleValues.Get("numericUpDownMinWeight").Value);
if ((bool)Parameters.ListCheckValues.Get("checkBoxIsBackfitting").Value)
{
((RandomTree)this.CurrentClassifier).setNumFolds((int)Parameters.ListDoubleValues.Get("numericUpDownBackFittingFolds").Value);
}
else
{
((RandomTree)this.CurrentClassifier).setNumFolds(0);
}
this.CurrentClassifier.buildClassifier(train);
//string StringForTree = ((RandomTree)this.CurrentClassifier).graph().Remove(0, ((RandomTree)this.CurrentClassifier).graph().IndexOf("{") + 2);
//Microsoft.Msagl.GraphViewerGdi.GViewer GraphView = new GViewer();
//GraphView.Graph = GlobalInfo.WindowHCSAnalyzer.ComputeAndDisplayGraph(StringForTree);//.Remove(StringForTree.Length - 3, 3));
//GraphView.Size = new System.Drawing.Size(panelForGraphicalResults.Width, panelForGraphicalResults.Height);
//GraphView.Anchor = (AnchorStyles.Bottom | AnchorStyles.Top | AnchorStyles.Left | AnchorStyles.Right);
//this.panelForGraphicalResults.Controls.Clear();
//this.panelForGraphicalResults.Controls.Add(GraphView);
}
#endregion
#region Random Forest
else if (ClassifAlgoParams.Name == "RandomForest")
{
this.CurrentClassifier = new weka.classifiers.trees.RandomForest();
if ((bool)Parameters.ListCheckValues.Get("checkBoxMaxDepthUnlimited").Value)
((RandomForest)this.CurrentClassifier).setMaxDepth(0);
else
((RandomForest)this.CurrentClassifier).setMaxDepth((int)Parameters.ListDoubleValues.Get("numericUpDownMaxDepth").Value);
((RandomForest)this.CurrentClassifier).setNumTrees((int)Parameters.ListDoubleValues.Get("numericUpDownNumTrees").Value);
((RandomForest)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region KStar
else if (ClassifAlgoParams.Name == "KStar")
{
this.CurrentClassifier = new weka.classifiers.lazy.KStar();
((KStar)this.CurrentClassifier).setGlobalBlend((int)Parameters.ListDoubleValues.Get("numericUpDownGlobalBlend").Value);
((KStar)this.CurrentClassifier).setEntropicAutoBlend((bool)Parameters.ListCheckValues.Get("checkBoxBlendAuto").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region SVM
else if (ClassifAlgoParams.Name == "SVM")
{
this.CurrentClassifier = new weka.classifiers.functions.SMO();
((SMO)this.CurrentClassifier).setC((double)Parameters.ListDoubleValues.Get("numericUpDownC").Value);
((SMO)this.CurrentClassifier).setKernel(WindowForClassificationParam.GeneratedKernel);
((SMO)this.CurrentClassifier).setRandomSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region KNN
else if (ClassifAlgoParams.Name == "KNN")
{
this.CurrentClassifier = new weka.classifiers.lazy.IBk();
string OptionDistance = " -K " + (int)Parameters.ListDoubleValues.Get("numericUpDownKNN").Value + " -W 0 ";
string WeightType = (string)Parameters.ListTextValues.Get("comboBoxDistanceWeight").Value;
switch (WeightType)
{
case "No Weighting":
OptionDistance += "";
break;
case "1/Distance":
OptionDistance += "-I";
break;
case "1-Distance":
OptionDistance += "-F";
break;
default:
break;
}
OptionDistance += " -A \"weka.core.neighboursearch.LinearNNSearch -A \\\"weka.core.";
string DistanceType = (string)Parameters.ListTextValues.Get("comboBoxDistance").Value;
// OptionDistance += " -A \"weka.core.";
switch (DistanceType)
{
case "Euclidean":
OptionDistance += "EuclideanDistance";
break;
case "Manhattan":
OptionDistance += "ManhattanDistance";
break;
case "Chebyshev":
OptionDistance += "ChebyshevDistance";
break;
default:
break;
}
if (!(bool)Parameters.ListCheckValues.Get("checkBoxNormalize").Value)
OptionDistance += " -D";
OptionDistance += " -R ";
OptionDistance += "first-last\\\"\"";
((IBk)this.CurrentClassifier).setOptions(weka.core.Utils.splitOptions(OptionDistance));
//((IBk)this.CurrentClassifier).setKNN((int)Parameters.ListDoubleValues.Get("numericUpDownKNN").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region Multilayer Perceptron
else if (ClassifAlgoParams.Name == "Perceptron")
{
this.CurrentClassifier = new weka.classifiers.functions.MultilayerPerceptron();
((MultilayerPerceptron)this.CurrentClassifier).setMomentum((double)Parameters.ListDoubleValues.Get("numericUpDownMomentum").Value);
((MultilayerPerceptron)this.CurrentClassifier).setLearningRate((double)Parameters.ListDoubleValues.Get("numericUpDownLearningRate").Value);
((MultilayerPerceptron)this.CurrentClassifier).setSeed((int)Parameters.ListDoubleValues.Get("numericUpDownSeed").Value);
((MultilayerPerceptron)this.CurrentClassifier).setTrainingTime((int)Parameters.ListDoubleValues.Get("numericUpDownTrainingTime").Value);
((MultilayerPerceptron)this.CurrentClassifier).setNormalizeAttributes((bool)Parameters.ListCheckValues.Get("checkBoxNormAttribute").Value);
((MultilayerPerceptron)this.CurrentClassifier).setNormalizeNumericClass((bool)Parameters.ListCheckValues.Get("checkBoxNormNumericClasses").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region ZeroR
else if (ClassifAlgoParams.Name == "ZeroR")
{
this.CurrentClassifier = new weka.classifiers.rules.OneR();
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region OneR
else if (ClassifAlgoParams.Name == "OneR")
{
this.CurrentClassifier = new weka.classifiers.rules.OneR();
((OneR)this.CurrentClassifier).setMinBucketSize((int)Parameters.ListDoubleValues.Get("numericUpDownMinBucketSize").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region Naive Bayes
else if (ClassifAlgoParams.Name == "NaiveBayes")
{
this.CurrentClassifier = new weka.classifiers.bayes.NaiveBayes();
((NaiveBayes)this.CurrentClassifier).setUseKernelEstimator((bool)Parameters.ListCheckValues.Get("checkBoxKernelEstimator").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
#region Logistic
else if (ClassifAlgoParams.Name == "Logistic")
{
this.CurrentClassifier = new weka.classifiers.functions.Logistic();
((Logistic)this.CurrentClassifier).setUseConjugateGradientDescent((bool)Parameters.ListCheckValues.Get("checkBoxUseConjugateGradientDescent").Value);
((Logistic)this.CurrentClassifier).setRidge((double)Parameters.ListDoubleValues.Get("numericUpDownRidge").Value);
this.CurrentClassifier.buildClassifier(train);
}
#endregion
//weka.classifiers.functions.SMO
//BayesNet
#endregion
if (TextBoxForFeedback != null)
{
TextBoxForFeedback.Clear();
TextBoxForFeedback.AppendText(this.CurrentClassifier.ToString());
}
TextBoxForFeedback.AppendText("\n" + (InstancesList.numAttributes() - 1) + " attributes:\n\n");
for (int IdxAttributes = 0; IdxAttributes < InstancesList.numAttributes() - 1; IdxAttributes++)
{
TextBoxForFeedback.AppendText(IdxAttributes + "\t: " + InstancesList.attribute(IdxAttributes).name() + "\n");
}
#region evaluation of the model and results display
if ((WindowForClassificationParam.numericUpDownFoldNumber.Enabled) && (TextBoxForFeedback != null))
{
TextBoxForFeedback.AppendText("\n-----------------------------\nModel validation\n-----------------------------\n");
ModelEvaluation = new weka.classifiers.Evaluation(InstancesList);
ModelEvaluation.crossValidateModel(this.CurrentClassifier, InstancesList, (int)WindowForClassificationParam.numericUpDownFoldNumber.Value, new java.util.Random(1));
TextBoxForFeedback.AppendText(ModelEvaluation.toSummaryString());
TextBoxForFeedback.AppendText("\n-----------------------------\nConfusion Matrix:\n-----------------------------\n");
double[][] ConfusionMatrix = ModelEvaluation.confusionMatrix();
string NewLine = "";
for (int i = 0; i < ConfusionMatrix[0].Length; i++)
{
NewLine += "c" + i + "\t";
}
TextBoxForFeedback.AppendText(NewLine + "\n\n");
for (int j = 0; j < ConfusionMatrix.Length; j++)
{
NewLine = "";
for (int i = 0; i < ConfusionMatrix[0].Length; i++)
{
NewLine += ConfusionMatrix[j][i] + "\t";
}
// if
TextBoxForFeedback.AppendText(NewLine + "| c" + j + " <=> " + cGlobalInfo.ListCellularPhenotypes[j].Name + "\n");
}
}
#endregion
return this.CurrentClassifier;
}
public static void Test_predictClass(string classifierFileName)
{
FileReader javaFileReader = new FileReader(classifierFileName);
weka.core.Instances insts = new weka.core.Instances(javaFileReader);
javaFileReader.close();
insts.setClassIndex(insts.numAttributes() - 1);
weka.classifiers.Classifier cl = new weka.classifiers.trees.J48();
System.Console.WriteLine("Performing " + percentSplit + "% split evaluation.");
#region Manual Cross Fold
Instances foldsData = new Instances(insts);
int folds = 10;
for (int n = 0; n < folds; n++)
{
Instances trainFold = foldsData.trainCV(folds, n);
Instances testFold = foldsData.testCV(folds, n);
}
#endregion
#region
int trainSize = insts.numInstances() * percentSplit / 100;
int testSize = insts.numInstances() - trainSize;
weka.core.Instances train = new weka.core.Instances(insts, 0, trainSize);
cl.buildClassifier(train);
#endregion
//Classifier cls = new J48();
Evaluation eval = new Evaluation(insts);
java.util.Random rand = new java.util.Random(1); // using seed = 1
int fold = 10;
eval.crossValidateModel(cl, insts, fold, rand);
System.Console.WriteLine("toClassDetailsString" + eval.toClassDetailsString());
System.Console.WriteLine("toMatrixString\n" + eval.toMatrixString());
System.Console.WriteLine("toCumulativeMarginDistributionString\n" + eval.toCumulativeMarginDistributionString());
//System.Console.WriteLine("predictions\n" + eval.predictions());
System.Console.ReadKey();
//var numnerOfInst = insts.numInstances();
//for (int i = trainSize; i < numnerOfInst; i++)
//{
// weka.core.Instance currentInst = insts.instance(i);
// double pred = cl.classifyInstance(currentInst);
// System.Console.WriteLine("class Index: " + insts.instance(i).classIndex());
// System.Console.WriteLine(", class value: " + insts.instance(i).classValue());
// System.Console.WriteLine(", ID: " + insts.instance(i).value(0));
// System.Console.WriteLine(", actual: " + insts.classAttribute().value((int)insts.instance(i).classValue()));
// System.Console.WriteLine(", predicted: " + insts.classAttribute().value((int)pred));
//}
}
