/// <summary> Method for building a classifier tree.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
public virtual void buildClassifier(Instances data)
{
if (data.checkForStringAttributes())
{
throw new Exception("Cannot handle string attributes!");
}
data = new Instances(data);
data.deleteWithMissingClass();
buildTree(data, false);
}
/// <summary> Method for building a pruneable classifier tree.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
public override void buildClassifier(Instances data)
{
if (data.classAttribute().Numeric)
throw new Exception("Class is numeric!");
if (data.checkForStringAttributes())
{
throw new Exception("Cannot handle string attributes!");
}
data = new Instances(data);
data.deleteWithMissingClass();
buildTree(data, m_subtreeRaising);
collapse();
if (m_pruneTheTree)
{
prune();
}
if (m_cleanup)
{
cleanup(new Instances(data, 0));
}
}
/// <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 ;
}
}
}
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> Generates the classifier.
///
/// </summary>
/// <param name="instances">set of instances serving as training data
/// </param>
/// <exception cref="Exception">if the classifier has not been generated successfully
/// </exception>
public override void buildClassifier(Instances instances)
{
//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 bestVal = System.Double.MaxValue, currVal;
//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 bestPoint = - System.Double.MaxValue, sum;
int bestAtt = - 1, numClasses;
if (instances.checkForStringAttributes())
{
throw new Exception("Can't handle string attributes!");
}
double[][] bestDist = new double[3][];
for (int i = 0; i < 3; i++)
{
bestDist[i] = new double[instances.numClasses()];
}
m_Instances = new Instances(instances);
m_Instances.deleteWithMissingClass();
if (m_Instances.numInstances() == 0)
{
throw new System.ArgumentException("No instances without missing " + "class values in training file!");
}
if (instances.numAttributes() == 1)
{
throw new System.ArgumentException("Attribute missing. Need at least one " + "attribute other than class attribute!");
}
if (m_Instances.classAttribute().Nominal)
{
numClasses = m_Instances.numClasses();
}
else
{
numClasses = 1;
}
// For each attribute
bool first = true;
for (int i = 0; i < m_Instances.numAttributes(); i++)
{
if (i != m_Instances.classIndex())
{
// Reserve space for distribution.
double[][] tmpArray = new double[3][];
for (int i2 = 0; i2 < 3; i2++)
{
tmpArray[i2] = new double[numClasses];
}
m_Distribution = tmpArray;
// Compute value of criterion for best split on attribute
if (m_Instances.attribute(i).Nominal)
{
currVal = findSplitNominal(i);
}
else
{
currVal = findSplitNumeric(i);
}
if ((first) || (currVal < bestVal))
{
bestVal = currVal;
bestAtt = i;
bestPoint = m_SplitPoint;
for (int j = 0; j < 3; j++)
{
Array.Copy(m_Distribution[j], 0, bestDist[j], 0, numClasses);
}
}
// First attribute has been investigated
first = false;
}
}
// Set attribute, split point and distribution.
m_AttIndex = bestAtt;
m_SplitPoint = bestPoint;
m_Distribution = bestDist;
if (m_Instances.classAttribute().Nominal)
{
for (int i = 0; i < m_Distribution.Length; i++)
{
double sumCounts = Utils.sum(m_Distribution[i]);
if (sumCounts == 0)
{
// This means there were only missing attribute values
Array.Copy(m_Distribution[2], 0, m_Distribution[i], 0, m_Distribution[2].Length);
Utils.normalize(m_Distribution[i]);
}
else
{
Utils.normalize(m_Distribution[i], sumCounts);
}
}
}
// Save memory
m_Instances = new Instances(m_Instances, 0);
}
