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 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 override void buildClassifier(Instances insts)
{
if (insts.checkForStringAttributes())
{
throw new Exception("Cannot handle string attributes!");
}
if (insts.numClasses() > 2)
{
throw new System.Exception("Can only handle two-class datasets!");
}
if (insts.classAttribute().Numeric)
{
throw new Exception("Can't handle a numeric class!");
}
// Filter data
m_Train = new Instances(insts);
m_Train.deleteWithMissingClass();
m_ReplaceMissingValues = new ReplaceMissingValues();
m_ReplaceMissingValues.setInputFormat(m_Train);
m_Train = Filter.useFilter(m_Train, m_ReplaceMissingValues);
m_NominalToBinary = new NominalToBinary();
m_NominalToBinary.setInputFormat(m_Train);
m_Train = Filter.useFilter(m_Train, m_NominalToBinary);
/** Randomize training data */
//UPGRADE_TODO: The differences in the expected value of parameters for constructor 'java.util.Random.Random' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
m_Train.randomize(new System.Random((System.Int32) m_Seed));
/** Make space to store perceptrons */
m_Additions = new int[m_MaxK + 1];
m_IsAddition = new bool[m_MaxK + 1];
m_Weights = new int[m_MaxK + 1];
/** Compute perceptrons */
m_K = 0;
for (int it = 0; it < m_NumIterations; it++)
{
for (int i = 0; i < m_Train.numInstances(); i++)
{
Instance inst = m_Train.instance(i);
if (!inst.classIsMissing())
{
int prediction = makePrediction(m_K, inst);
//UPGRADE_WARNING: Data types in Visual C# might be different. Verify the accuracy of narrowing conversions. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1042'"
int classValue = (int) inst.classValue();
if (prediction == classValue)
{
m_Weights[m_K]++;
}
else
{
m_IsAddition[m_K] = (classValue == 1);
m_Additions[m_K] = i;
m_K++;
m_Weights[m_K]++;
}
if (m_K == m_MaxK)
{
//UPGRADE_NOTE: Labeled break statement was changed to a goto statement. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1012'"
goto out_brk;
}
}
}
}
//UPGRADE_NOTE: Label 'out_brk' was added. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1011'"
out_brk: ;
}
/// <summary> Performs a (stratified if class is nominal) cross-validation
/// for a classifier on a set of instances. Now performs
/// a deep copy of the classifier before each call to
/// buildClassifier() (just in case the classifier is not
/// initialized properly).
///
/// </summary>
/// <param name="classifier">the classifier with any options set.
/// </param>
/// <param name="data">the data on which the cross-validation is to be
/// performed
/// </param>
/// <param name="numFolds">the number of folds for the cross-validation
/// </param>
/// <param name="random">random number generator for randomization
/// </param>
/// <throws> Exception if a classifier could not be generated </throws>
/// <summary> successfully or the class is not defined
/// </summary>
public virtual void crossValidateModel(Classifier classifier, Instances data, int numFolds, System.Random random)
{
// Make a copy of the data we can reorder
data = new Instances(data);
data.randomize(random);
if (data.classAttribute().Nominal)
{
data.stratify(numFolds);
}
// Do the folds
for (int i = 0; i < numFolds; i++)
{
Instances train = data.trainCV(numFolds, i, random);
Priors = train;
Classifier copiedClassifier = Classifier.makeCopy(classifier);
copiedClassifier.buildClassifier(train);
Instances test = data.testCV(numFolds, i);
evaluateModel(copiedClassifier, test);
}
m_NumFolds = numFolds;
}
/// <summary> Builds the boosted classifier</summary>
public virtual void buildClassifier(Instances data)
{
m_RandomInstance = new Random(m_Seed);
Instances boostData;
int classIndex = data.classIndex();
if (data.classAttribute().Numeric)
{
throw new Exception("LogitBoost can't handle a numeric class!");
}
if (m_Classifier == null)
{
throw new System.Exception("A base classifier has not been specified!");
}
if (!(m_Classifier is WeightedInstancesHandler) && !m_UseResampling)
{
m_UseResampling = true;
}
if (data.checkForStringAttributes())
{
throw new Exception("Cannot handle string attributes!");
}
if (m_Debug)
{
System.Console.Error.WriteLine("Creating copy of the training data");
}
m_NumClasses = data.numClasses();
m_ClassAttribute = data.classAttribute();
// Create a copy of the data
data = new Instances(data);
data.deleteWithMissingClass();
// Create the base classifiers
if (m_Debug)
{
System.Console.Error.WriteLine("Creating base classifiers");
}
m_Classifiers = new Classifier[m_NumClasses][];
for (int j = 0; j < m_NumClasses; j++)
{
m_Classifiers[j] = Classifier.makeCopies(m_Classifier, this.NumIterations);
}
// Do we want to select the appropriate number of iterations
// using cross-validation?
int bestNumIterations = this.NumIterations;
if (m_NumFolds > 1)
{
if (m_Debug)
{
System.Console.Error.WriteLine("Processing first fold.");
}
// Array for storing the results
double[] results = new double[this.NumIterations];
// Iterate throught the cv-runs
for (int r = 0; r < m_NumRuns; r++)
{
// Stratify the data
data.randomize(m_RandomInstance);
data.stratify(m_NumFolds);
// Perform the cross-validation
for (int i = 0; i < m_NumFolds; i++)
{
// Get train and test folds
Instances train = data.trainCV(m_NumFolds, i, m_RandomInstance);
Instances test = data.testCV(m_NumFolds, i);
// Make class numeric
Instances trainN = new Instances(train);
trainN.ClassIndex = - 1;
trainN.deleteAttributeAt(classIndex);
trainN.insertAttributeAt(new weka.core.Attribute("'pseudo class'"), classIndex);
trainN.ClassIndex = classIndex;
m_NumericClassData = new Instances(trainN, 0);
// Get class values
int numInstances = train.numInstances();
double[][] tmpArray = new double[numInstances][];
for (int i2 = 0; i2 < numInstances; i2++)
{
tmpArray[i2] = new double[m_NumClasses];
}
double[][] trainFs = tmpArray;
double[][] tmpArray2 = new double[numInstances][];
for (int i3 = 0; i3 < numInstances; i3++)
{
tmpArray2[i3] = new double[m_NumClasses];
}
double[][] trainYs = tmpArray2;
for (int j = 0; j < m_NumClasses; j++)
{
for (int k = 0; k < numInstances; k++)
{
trainYs[k][j] = (train.instance(k).classValue() == j)?1.0 - m_Offset:0.0 + (m_Offset / (double) m_NumClasses);
}
}
// Perform iterations
double[][] probs = initialProbs(numInstances);
m_NumGenerated = 0;
double sumOfWeights = train.sumOfWeights();
for (int j = 0; j < this.NumIterations; j++)
{
performIteration(trainYs, trainFs, probs, trainN, sumOfWeights);
Evaluation eval = new Evaluation(train);
eval.evaluateModel(this, test);
results[j] += eval.correct();
}
}
}
// Find the number of iterations with the lowest error
//UPGRADE_TODO: The equivalent in .NET for field 'java.lang.Double.MAX_VALUE' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
double bestResult = - System.Double.MaxValue;
for (int j = 0; j < this.NumIterations; j++)
{
if (results[j] > bestResult)
{
bestResult = results[j];
bestNumIterations = j;
}
}
if (m_Debug)
{
System.Console.Error.WriteLine("Best result for " + bestNumIterations + " iterations: " + bestResult);
}
}
// Build classifier on all the data
int numInstances2 = data.numInstances();
double[][] trainFs2 = new double[numInstances2][];
for (int i4 = 0; i4 < numInstances2; i4++)
{
trainFs2[i4] = new double[m_NumClasses];
}
double[][] trainYs2 = new double[numInstances2][];
for (int i5 = 0; i5 < numInstances2; i5++)
{
trainYs2[i5] = new double[m_NumClasses];
}
for (int j = 0; j < m_NumClasses; j++)
{
for (int i = 0, k = 0; i < numInstances2; i++, k++)
{
trainYs2[i][j] = (data.instance(k).classValue() == j)?1.0 - m_Offset:0.0 + (m_Offset / (double) m_NumClasses);
}
}
// Make class numeric
data.ClassIndex = - 1;
data.deleteAttributeAt(classIndex);
data.insertAttributeAt(new weka.core.Attribute("'pseudo class'"), classIndex);
data.ClassIndex = classIndex;
m_NumericClassData = new Instances(data, 0);
// Perform iterations
double[][] probs2 = initialProbs(numInstances2);
double logLikelihood = CalculateLogLikelihood(trainYs2, probs2);
m_NumGenerated = 0;
if (m_Debug)
{
System.Console.Error.WriteLine("Avg. log-likelihood: " + logLikelihood);
}
double sumOfWeights2 = data.sumOfWeights();
for (int j = 0; j < bestNumIterations; j++)
{
double previousLoglikelihood = logLikelihood;
performIteration(trainYs2, trainFs2, probs2, data, sumOfWeights2);
logLikelihood = CalculateLogLikelihood(trainYs2, probs2);
if (m_Debug)
{
System.Console.Error.WriteLine("Avg. log-likelihood: " + logLikelihood);
}
if (System.Math.Abs(previousLoglikelihood - logLikelihood) < m_Precision)
{
return ;
}
}
}
