/// <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)
{
double sumOfWeights = 0;
m_Class = instances.classAttribute();
m_ClassValue = 0;
switch (instances.classAttribute().type())
{
case weka.core.Attribute.NUMERIC:
m_Counts = null;
break;
case weka.core.Attribute.NOMINAL:
m_Counts = new double[instances.numClasses()];
for (int i = 0; i < m_Counts.Length; i++)
{
m_Counts[i] = 1;
}
sumOfWeights = instances.numClasses();
break;
default:
throw new System.Exception("ZeroR can only handle nominal and numeric class" + " attributes.");
}
System.Collections.IEnumerator enu = instances.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
Instance instance = (Instance) enu.Current;
if (!instance.classIsMissing())
{
if (instances.classAttribute().Nominal)
{
//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'"
m_Counts[(int) instance.classValue()] += instance.weight();
}
else
{
m_ClassValue += instance.weight() * instance.classValue();
}
sumOfWeights += instance.weight();
}
}
if (instances.classAttribute().Numeric)
{
if (Utils.gr(sumOfWeights, 0))
{
m_ClassValue /= sumOfWeights;
}
}
else
{
m_ClassValue = Utils.maxIndex(m_Counts);
Utils.normalize(m_Counts, sumOfWeights);
}
}
/// <summary> Creates split on numeric attribute.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
private void handleNumericAttribute(Instances trainInstances)
{
int firstMiss;
int next = 1;
int last = 0;
int splitIndex = - 1;
double currentInfoGain;
double defaultEnt;
double minSplit;
Instance instance;
int i;
// Current attribute is a numeric attribute.
m_distribution = new Distribution(2, trainInstances.numClasses());
// Only Instances with known values are relevant.
System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
i = 0;
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
instance = (Instance) enu.Current;
if (instance.isMissing(m_attIndex))
break;
m_distribution.add(1, instance);
i++;
}
firstMiss = i;
// Compute minimum number of Instances required in each
// subset.
minSplit = 0.1 * (m_distribution.total()) / ((double) trainInstances.numClasses());
if (Utils.smOrEq(minSplit, m_minNoObj))
minSplit = m_minNoObj;
else if (Utils.gr(minSplit, 25))
minSplit = 25;
// Enough Instances with known values?
if (Utils.sm((double) firstMiss, 2 * minSplit))
return ;
// Compute values of criteria for all possible split
// indices.
defaultEnt = infoGainCrit.oldEnt(m_distribution);
while (next < firstMiss)
{
if (trainInstances.instance(next - 1).value_Renamed(m_attIndex) + 1e-5 < trainInstances.instance(next).value_Renamed(m_attIndex))
{
// Move class values for all Instances up to next
// possible split point.
m_distribution.shiftRange(1, 0, trainInstances, last, next);
// Check if enough Instances in each subset and compute
// values for criteria.
if (Utils.grOrEq(m_distribution.perBag(0), minSplit) && Utils.grOrEq(m_distribution.perBag(1), minSplit))
{
currentInfoGain = infoGainCrit.splitCritValue(m_distribution, m_sumOfWeights, defaultEnt);
if (Utils.gr(currentInfoGain, m_infoGain))
{
m_infoGain = currentInfoGain;
splitIndex = next - 1;
}
m_index++;
}
last = next;
}
next++;
}
// Was there any useful split?
if (m_index == 0)
return ;
// Compute modified information gain for best split.
m_infoGain = m_infoGain - (Utils.log2(m_index) / m_sumOfWeights);
if (Utils.smOrEq(m_infoGain, 0))
return ;
// Set instance variables' values to values for
// best split.
m_numSubsets = 2;
m_splitPoint = (trainInstances.instance(splitIndex + 1).value_Renamed(m_attIndex) + trainInstances.instance(splitIndex).value_Renamed(m_attIndex)) / 2;
// In case we have a numerical precision problem we need to choose the
// smaller value
if (m_splitPoint == trainInstances.instance(splitIndex + 1).value_Renamed(m_attIndex))
{
m_splitPoint = trainInstances.instance(splitIndex).value_Renamed(m_attIndex);
}
// Restore distributioN for best split.
m_distribution = new Distribution(2, trainInstances.numClasses());
m_distribution.addRange(0, trainInstances, 0, splitIndex + 1);
m_distribution.addRange(1, trainInstances, splitIndex + 1, firstMiss);
// Compute modified gain ratio for best split.
m_gainRatio = gainRatioCrit.splitCritValue(m_distribution, m_sumOfWeights, m_infoGain);
}
/// <summary> Creates split on enumerated attribute.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
private void handleEnumeratedAttribute(Instances trainInstances)
{
Instance instance;
m_distribution = new Distribution(m_complexityIndex, trainInstances.numClasses());
// Only Instances with known values are relevant.
System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
instance = (Instance) enu.Current;
if (!instance.isMissing(m_attIndex))
{
//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'"
m_distribution.add((int) instance.value_Renamed(m_attIndex), instance);
}
}
// Check if minimum number of Instances in at least two
// subsets.
if (m_distribution.check(m_minNoObj))
{
m_numSubsets = m_complexityIndex;
m_infoGain = infoGainCrit.splitCritValue(m_distribution, m_sumOfWeights);
m_gainRatio = gainRatioCrit.splitCritValue(m_distribution, m_sumOfWeights, m_infoGain);
}
}
/// <summary> Creates split on enumerated attribute.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
private void handleEnumeratedAttribute(Instances trainInstances)
{
Distribution newDistribution, secondDistribution;
int numAttValues;
double currIG, currGR;
Instance instance;
int i;
numAttValues = trainInstances.attribute(m_attIndex).numValues();
newDistribution = new Distribution(numAttValues, trainInstances.numClasses());
// Only Instances with known values are relevant.
System.Collections.IEnumerator enu = trainInstances.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
instance = (Instance) enu.Current;
if (!instance.isMissing(m_attIndex))
{
//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'"
newDistribution.add((int) instance.value_Renamed(m_attIndex), instance);
}
}
m_distribution = newDistribution;
// For all values
for (i = 0; i < numAttValues; i++)
{
if (Utils.grOrEq(newDistribution.perBag(i), m_minNoObj))
{
secondDistribution = new Distribution(newDistribution, i);
// Check if minimum number of Instances in the two
// subsets.
if (secondDistribution.check(m_minNoObj))
{
m_numSubsets = 2;
currIG = m_infoGainCrit.splitCritValue(secondDistribution, m_sumOfWeights);
currGR = m_gainRatioCrit.splitCritValue(secondDistribution, m_sumOfWeights, currIG);
if ((i == 0) || Utils.gr(currGR, m_gainRatio))
{
m_gainRatio = currGR;
m_infoGain = currIG;
m_splitPoint = (double) i;
m_distribution = secondDistribution;
}
}
}
}
}
/// <summary> Adds all instances with unknown values for given attribute, weighted
/// according to frequency of instances in each bag.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
public void addInstWithUnknown(Instances source, int attIndex)
{
double[] probs;
double weight, newWeight;
int classIndex;
Instance instance;
int j;
probs = new double[m_perBag.Length];
for (j = 0; j < m_perBag.Length; j++)
{
if (Utils.eq(totaL, 0))
{
probs[j] = 1.0 / probs.Length;
}
else
{
probs[j] = m_perBag[j] / totaL;
}
}
System.Collections.IEnumerator enu = source.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
instance = (Instance) enu.Current;
if (instance.isMissing(attIndex))
{
//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'"
classIndex = (int) instance.classValue();
weight = instance.weight();
m_perClass[classIndex] = m_perClass[classIndex] + weight;
totaL = totaL + weight;
for (j = 0; j < m_perBag.Length; j++)
{
newWeight = probs[j] * weight;
m_perClassPerBag[j][classIndex] = m_perClassPerBag[j][classIndex] + newWeight;
m_perBag[j] = m_perBag[j] + newWeight;
}
}
}
}
/// <summary> Creates a distribution according to given instances and
/// split model.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
public Distribution(Instances source, ClassifierSplitModel modelToUse)
{
int index;
Instance instance;
double[] weights;
m_perClassPerBag = new double[modelToUse.numSubsets()][];
for (int i = 0; i < modelToUse.numSubsets(); i++)
{
m_perClassPerBag[i] = new double[0];
}
m_perBag = new double[modelToUse.numSubsets()];
totaL = 0;
m_perClass = new double[source.numClasses()];
for (int i = 0; i < modelToUse.numSubsets(); i++)
m_perClassPerBag[i] = new double[source.numClasses()];
System.Collections.IEnumerator enu = source.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
instance = (Instance) enu.Current;
index = modelToUse.whichSubset(instance);
if (index != - 1)
add(index, instance);
else
{
weights = modelToUse.GetWeights(instance);
addWeights(instance, weights);
}
}
}
/// <summary> Creates a distribution with only one bag according
/// to instances in source.
///
/// </summary>
/// <exception cref="Exception">if something goes wrong
/// </exception>
public Distribution(Instances source)
{
m_perClassPerBag = new double[1][];
for (int i = 0; i < 1; i++)
{
m_perClassPerBag[i] = new double[0];
}
m_perBag = new double[1];
totaL = 0;
m_perClass = new double[source.numClasses()];
m_perClassPerBag[0] = new double[source.numClasses()];
System.Collections.IEnumerator enu = source.enumerateInstances();
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
while (enu.MoveNext())
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
add(0, (Instance) enu.Current);
}
}
