/// <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);
}
