/// <summary> Computes entropy after splitting without considering the
/// class values.
/// </summary>
public double splitEnt(Distribution bags)
{
double returnValue = 0;
int i;
for (i = 0; i < bags.numBags(); i++)
returnValue = returnValue + logFunc(bags.perBag(i));
return logFunc(bags.total()) - returnValue;
}
/// <summary> This method computes the information gain in the same way
/// C4.5 does.
///
/// </summary>
/// <param name="distribution">the distribution
/// </param>
/// <param name="totalNoInst">weight of ALL instances (including the
/// ones with missing values).
/// </param>
public double splitCritValue(Distribution bags, double totalNoInst)
{
double numerator;
double noUnknown;
double unknownRate;
noUnknown = totalNoInst - bags.total();
unknownRate = noUnknown / totalNoInst;
numerator = (oldEnt(bags) - newEnt(bags));
numerator = (1 - unknownRate) * numerator;
// Splits with no gain are useless.
if (Utils.eq(numerator, 0))
return 0;
return numerator / bags.total();
}
/// <summary> Computes entropy of distribution before splitting.</summary>
public double oldEnt(Distribution bags)
{
double returnValue = 0;
int j;
for (j = 0; j < bags.numClasses(); j++)
returnValue = returnValue + logFunc(bags.perClass(j));
return logFunc(bags.total()) - returnValue;
}
/// <summary> This method is a straightforward implementation of the information
/// gain criterion for the given distribution.
/// </summary>
public override double splitCritValue(Distribution bags)
{
double numerator;
numerator = oldEnt(bags) - newEnt(bags);
// Splits with no gain are useless.
if (Utils.eq(numerator, 0))
{
//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'"
return System.Double.MaxValue;
}
// We take the reciprocal value because we want to minimize the
// splitting criterion's value.
return bags.total() / numerator;
}
/// <summary> Selects C4.5-type split for the given dataset.</summary>
public override ClassifierSplitModel selectModel(Instances data)
{
double minResult;
//double currentResult;
BinC45Split[] currentModel;
BinC45Split bestModel = null;
NoSplit noSplitModel = null;
double averageInfoGain = 0;
int validModels = 0;
bool multiVal = true;
Distribution checkDistribution;
double sumOfWeights;
int i;
try
{
// Check if all Instances belong to one class or if not
// enough Instances to split.
checkDistribution = new Distribution(data);
noSplitModel = new NoSplit(checkDistribution);
if (Utils.sm(checkDistribution.total(), 2 * m_minNoObj) || Utils.eq(checkDistribution.total(), checkDistribution.perClass(checkDistribution.maxClass())))
return noSplitModel;
// Check if all attributes are nominal and have a
// lot of values.
System.Collections.IEnumerator enu = data.enumerateAttributes();
//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'"
weka.core.Attribute attribute = (weka.core.Attribute)enu.Current;
if ((attribute.Numeric) || (Utils.sm((double) attribute.numValues(), (0.3 * (double) m_allData.numInstances()))))
{
multiVal = false;
break;
}
}
currentModel = new BinC45Split[data.numAttributes()];
sumOfWeights = data.sumOfWeights();
// For each attribute.
for (i = 0; i < data.numAttributes(); i++)
{
// Apart from class attribute.
if (i != (data).classIndex())
{
// Get models for current attribute.
currentModel[i] = new BinC45Split(i, m_minNoObj, sumOfWeights);
currentModel[i].buildClassifier(data);
// Check if useful split for current attribute
// exists and check for enumerated attributes with
// a lot of values.
if (currentModel[i].checkModel())
if ((data.attribute(i).Numeric) || (multiVal || Utils.sm((double) data.attribute(i).numValues(), (0.3 * (double) m_allData.numInstances()))))
{
averageInfoGain = averageInfoGain + currentModel[i].infoGain();
validModels++;
}
}
else
currentModel[i] = null;
}
// Check if any useful split was found.
if (validModels == 0)
return noSplitModel;
averageInfoGain = averageInfoGain / (double) validModels;
// Find "best" attribute to split on.
minResult = 0;
for (i = 0; i < data.numAttributes(); i++)
{
if ((i != (data).classIndex()) && (currentModel[i].checkModel()))
// Use 1E-3 here to get a closer approximation to the original
// implementation.
if ((currentModel[i].infoGain() >= (averageInfoGain - 1e-3)) && Utils.gr(currentModel[i].gainRatio(), minResult))
{
bestModel = currentModel[i];
minResult = currentModel[i].gainRatio();
}
}
// Check if useful split was found.
if (Utils.eq(minResult, 0))
return noSplitModel;
// Add all Instances with unknown values for the corresponding
// attribute to the distribution for the model, so that
// the complete distribution is stored with the model.
bestModel.distribution().addInstWithUnknown(data, bestModel.attIndex());
// Set the split point analogue to C45 if attribute numeric.
bestModel.SplitPoint = m_allData;
return bestModel;
}
catch (System.Exception e)
{
System.Console.WriteLine(e.StackTrace + " " + e.Message);
}
return null;
}
/// <summary> Computes estimated errors for leaf.</summary>
private double getEstimatedErrorsForDistribution(Distribution theDistribution)
{
if (Utils.eq(theDistribution.total(), 0))
return 0;
else
return theDistribution.numIncorrect() + Stats.addErrs(theDistribution.total(), theDistribution.numIncorrect(), m_CF);
}
/// <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> Help method for computing the split entropy.</summary>
private double splitEnt(Distribution bags, double totalnoInst)
{
double returnValue = 0;
double noUnknown;
int i;
noUnknown = totalnoInst - bags.total();
if (Utils.gr(bags.total(), 0))
{
for (i = 0; i < bags.numBags(); i++)
returnValue = returnValue - logFunc(bags.perBag(i));
returnValue = returnValue - logFunc(noUnknown);
returnValue = returnValue + logFunc(totalnoInst);
}
return returnValue;
}
