double calculateConditionalMutualInformation(double *dataVector, double *targetVector, double *conditionVector, int vectorLength) { double mutualInformation = 0.0; double firstCondition, secondCondition; double *mergedVector = (double *) CALLOC_FUNC(vectorLength,sizeof(double)); mergeArrays(targetVector,conditionVector,mergedVector,vectorLength); /* I(X;Y|Z) = H(X|Z) - H(X|YZ) */ /* double calculateConditionalEntropy(double *dataVector, double *conditionVector, int vectorLength); */ firstCondition = calculateConditionalEntropy(dataVector,conditionVector,vectorLength); secondCondition = calculateConditionalEntropy(dataVector,mergedVector,vectorLength); mutualInformation = firstCondition - secondCondition; FREE_FUNC(mergedVector); mergedVector = NULL; return mutualInformation; }/*calculateConditionalMutualInformation(double *,double *,double *,int)*/
double* BetaGamma(int k, int noOfSamples, int noOfFeatures, double *featureMatrix, double *classColumn, double *outputFeatures, double betaParam, double gammaParam) { double **feature2D = (double **) CALLOC_FUNC(noOfFeatures,sizeof(double *)); /*holds the class MI values*/ double *classMI = (double *)CALLOC_FUNC(noOfFeatures,sizeof(double)); char *selectedFeatures = (char *)CALLOC_FUNC(noOfFeatures,sizeof(char)); /*holds the intra feature MI values*/ int sizeOfMatrix = k*noOfFeatures; double *featureMIMatrix = (double *)CALLOC_FUNC(sizeOfMatrix,sizeof(double)); double maxMI = 0.0; int maxMICounter = -1; double score, currentScore, totalFeatureMI; int currentHighestFeature, arrayPosition; int i,j,m; /*********************************************************** ** because the array is passed as ** s a m p l e s ** f ** e ** a ** t ** u ** r ** e ** s ** ** this pulls out a pointer to the first sample of ** each feature and stores it as a multidimensional array ** so it can be indexed nicely ***********************************************************/ for(j = 0; j < noOfFeatures; j++) { feature2D[j] = featureMatrix + (int)j*noOfSamples; } for (i = 0; i < sizeOfMatrix; i++) { featureMIMatrix[i] = -1; }/*for featureMIMatrix - blank to -1*/ /*********************************************************** ** SETUP COMPLETE ** Algorithm starts here ***********************************************************/ for (i = 0; i < noOfFeatures; i++) { classMI[i] = calculateMutualInformation(feature2D[i], classColumn, noOfSamples); if (classMI[i] > maxMI) { maxMI = classMI[i]; maxMICounter = i; }/*if bigger than current maximum*/ }/*for noOfFeatures - filling classMI*/ selectedFeatures[maxMICounter] = 1; outputFeatures[0] = maxMICounter; /************* ** Now we have populated the classMI array, and selected the highest ** MI feature as the first output feature ** Now we move into the JMI algorithm *************/ for (i = 1; i < k; i++) { /************************************************************ ** to ensure it selects some features ** if this is zero then it will not pick features where the ** redundancy is greater than the relevance ************************************************************/ score = -HUGE_VAL; currentHighestFeature = 0; currentScore = 0.0; totalFeatureMI = 0.0; for (j = 0; j < noOfFeatures; j++) { /*if we haven't selected j*/ if (!selectedFeatures[j]) { currentScore = classMI[j]; totalFeatureMI = 0.0; for (m = 0; m < i; m++) { arrayPosition = m*noOfFeatures + j; if (featureMIMatrix[arrayPosition] == -1) { /*double calculateMutualInformation(double *firstVector, double *secondVector, int vectorLength);*/ featureMIMatrix[arrayPosition] = betaParam*calculateMutualInformation(feature2D[(int) outputFeatures[m]], feature2D[j], noOfSamples); /*double calculateConditionalMutualInformation(double *firstVector, double *targetVector, double* conditionVector, int vectorLength);*/ featureMIMatrix[arrayPosition] -= gammaParam*calculateConditionalMutualInformation(feature2D[(int) outputFeatures[m]], feature2D[j], classColumn, noOfSamples); }/*if not already known*/ totalFeatureMI += featureMIMatrix[arrayPosition]; }/*for the number of already selected features*/ currentScore -= (totalFeatureMI); if (currentScore > score) { score = currentScore; currentHighestFeature = j; } }/*if j is unselected*/ }/*for number of features*/ selectedFeatures[currentHighestFeature] = 1; outputFeatures[i] = currentHighestFeature; }/*for the number of features to select*/ for (i = 0; i < k; i++) { outputFeatures[i] += 1; /*C++ indexes from 0 not 1*/ }/*for number of selected features*/ return outputFeatures; }/*BetaGamma(int,int,int,double[][],double[],double[],double,double)*/
double* CMIM(int k, int noOfSamples, int noOfFeatures, double *featureMatrix, double *classColumn, double *outputFeatures) { /*holds the class MI values **the class MI doubles as the partial score from the CMIM paper */ double *classMI = (double *)CALLOC_FUNC(noOfFeatures,sizeof(double)); /*in the CMIM paper, m = lastUsedFeature*/ int *lastUsedFeature = (int *)CALLOC_FUNC(noOfFeatures,sizeof(int)); double score, conditionalInfo; int iMinus, currentFeature; double maxMI = 0.0; int maxMICounter = -1; int j,i; double **feature2D = (double**) CALLOC_FUNC(noOfFeatures,sizeof(double*)); for(j = 0; j < noOfFeatures; j++) { feature2D[j] = featureMatrix + (int)j*noOfSamples; } for (i = 0; i < noOfFeatures;i++) { classMI[i] = calculateMutualInformation(feature2D[i], classColumn, noOfSamples); if (classMI[i] > maxMI) { maxMI = classMI[i]; maxMICounter = i; }/*if bigger than current maximum*/ }/*for noOfFeatures - filling classMI*/ outputFeatures[0] = maxMICounter; /***************************************************************************** ** We have populated the classMI array, and selected the highest ** MI feature as the first output feature ** Now we move into the CMIM algorithm *****************************************************************************/ for (i = 1; i < k; i++) { score = 0.0; iMinus = i-1; for (j = 0; j < noOfFeatures; j++) { while ((classMI[j] > score) && (lastUsedFeature[j] < i)) { /*double calculateConditionalMutualInformation(double *firstVector, double *targetVector, double *conditionVector, int vectorLength);*/ currentFeature = (int) outputFeatures[lastUsedFeature[j]]; conditionalInfo = calculateConditionalMutualInformation(feature2D[j],classColumn,feature2D[currentFeature],noOfSamples); if (classMI[j] > conditionalInfo) { classMI[j] = conditionalInfo; }/*reset classMI*/ /*moved due to C indexing from 0 rather than 1*/ lastUsedFeature[j] += 1; }/*while partial score greater than score & not reached last feature*/ if (classMI[j] > score) { score = classMI[j]; outputFeatures[i] = j; }/*if partial score still greater than score*/ }/*for number of features*/ }/*for the number of features to select*/ for (i = 0; i < k; i++) { outputFeatures[i] += 1; /*C indexes from 0 not 1*/ }/*for number of selected features*/ FREE_FUNC(classMI); FREE_FUNC(lastUsedFeature); FREE_FUNC(feature2D); classMI = NULL; lastUsedFeature = NULL; feature2D = NULL; return outputFeatures; }/*CMIM(int,int,int,double[][],double[],double[])*/
double* CondMI(int k, int noOfSamples, int noOfFeatures, double *featureMatrix, double *classColumn, double *outputFeatures) { /*holds the class MI values*/ double *classMI = (double *)CALLOC_FUNC(noOfFeatures,sizeof(double)); char *selectedFeatures = (char *)CALLOC_FUNC(noOfFeatures,sizeof(char)); /*holds the intra feature MI values*/ int sizeOfMatrix = k*noOfFeatures; double *featureMIMatrix = (double *)CALLOC_FUNC(sizeOfMatrix,sizeof(double)); double maxMI = 0.0; int maxMICounter = -1; double **feature2D = (double**) CALLOC_FUNC(noOfFeatures,sizeof(double*)); double score, currentScore, totalFeatureMI; int currentHighestFeature; double *conditionVector = (double *) CALLOC_FUNC(noOfSamples,sizeof(double)); int arrayPosition; double mi, tripEntropy; int i,j,x; for(j = 0; j < noOfFeatures; j++) { feature2D[j] = featureMatrix + (int)j*noOfSamples; } for (i = 0; i < sizeOfMatrix; i++) { featureMIMatrix[i] = -1; }/*for featureMIMatrix - blank to -1*/ for (i = 0; i < noOfFeatures; i++) { /*calculate mutual info **double calculateMutualInformation(double *firstVector, double *secondVector, int vectorLength); */ classMI[i] = calculateMutualInformation(feature2D[i], classColumn, noOfSamples); if (classMI[i] > maxMI) { maxMI = classMI[i]; maxMICounter = i; }/*if bigger than current maximum*/ }/*for noOfFeatures - filling classMI*/ selectedFeatures[maxMICounter] = 1; outputFeatures[0] = maxMICounter; memcpy(conditionVector,feature2D[maxMICounter],sizeof(double)*noOfSamples); /***************************************************************************** ** We have populated the classMI array, and selected the highest ** MI feature as the first output feature ** Now we move into the CondMI algorithm *****************************************************************************/ for (i = 1; i < k; i++) { score = 0.0; currentHighestFeature = -1; currentScore = 0.0; totalFeatureMI = 0.0; for (j = 0; j < noOfFeatures; j++) { /*if we haven't selected j*/ if (selectedFeatures[j] == 0) { currentScore = 0.0; totalFeatureMI = 0.0; /*double calculateConditionalMutualInformation(double *firstVector, double *targetVector, double *conditionVector, int vectorLength);*/ currentScore = calculateConditionalMutualInformation(feature2D[j],classColumn,conditionVector,noOfSamples); if (currentScore > score) { score = currentScore; currentHighestFeature = j; } }/*if j is unselected*/ }/*for number of features*/ outputFeatures[i] = currentHighestFeature; if (currentHighestFeature != -1) { selectedFeatures[currentHighestFeature] = 1; mergeArrays(feature2D[currentHighestFeature],conditionVector,conditionVector,noOfSamples); } }/*for the number of features to select*/ FREE_FUNC(classMI); FREE_FUNC(conditionVector); FREE_FUNC(feature2D); FREE_FUNC(featureMIMatrix); FREE_FUNC(selectedFeatures); classMI = NULL; conditionVector = NULL; feature2D = NULL; featureMIMatrix = NULL; selectedFeatures = NULL; return outputFeatures; }/*CondMI(int,int,int,double[][],double[],double[])*/