/// <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> Computes entropy of distribution after splitting.</summary> public double newEnt(Distribution bags) { double returnValue = 0; int i, j; for (i = 0; i < bags.numBags(); i++) { for (j = 0; j < bags.numClasses(); j++) returnValue = returnValue + logFunc(bags.perClassPerBag(i, j)); returnValue = returnValue - logFunc(bags.perBag(i)); } return - returnValue; }
/// <summary> Computes entropy of test distribution with respect to training distribution.</summary> public override double splitCritValue(Distribution train, Distribution test) { double result = 0; int numClasses = 0; int i, j; // Find out relevant number of classes for (j = 0; j < test.numClasses(); j++) if (Utils.gr(train.perClass(j), 0) || Utils.gr(test.perClass(j), 0)) numClasses++; // Compute entropy of test data with respect to training data for (i = 0; i < test.numBags(); i++) if (Utils.gr(test.perBag(i), 0)) { for (j = 0; j < test.numClasses(); j++) if (Utils.gr(test.perClassPerBag(i, j), 0)) result -= test.perClassPerBag(i, j) * System.Math.Log(train.perClassPerBag(i, j) + 1); result += test.perBag(i) * System.Math.Log(train.perBag(i) + numClasses); } return result / log2; }
/// <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) { 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> 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; }