@Override
public double[][] predict(List<PredictionPaper> testDocs) {
String testData = "lda/test.dat";
createLdaInputTest(testData, testDocs);
Utils.runCommand(
"lib/lda-c-dist/lda inf "
+ " lib/lda-c-dist/settings.txt "
+ "lda/final "
+ testData
+ " lda/output",
false);
double[][] gammasMatrix = Utils.readMatrix("lda/output-gamma.dat", false);
double alpha = Utils.readAlpha("lda/final.other");
for (int i = 0; i < gammasMatrix.length; i++) {
for (int j = 0; j < gammasMatrix[i].length; j++) {
gammasMatrix[i][j] -= alpha;
}
}
SimpleMatrix gammas = new SimpleMatrix(gammasMatrix);
SimpleMatrix beta = new SimpleMatrix(betaMatrix);
SimpleMatrix probabilities = gammas.mult(beta);
double[][] result = new double[probabilities.numRows()][probabilities.numCols()];
for (int row = 0; row < probabilities.numRows(); row++) {
for (int col = 0; col < probabilities.numCols(); col++) {
result[row][col] = probabilities.get(row, col);
}
}
return result;
}
public int predictState(int from_state, int number_of_steps) {
long lStartTime = System.currentTimeMillis();
int from_bin = getBinNumber((float) from_state);
SimpleMatrix result = new SimpleMatrix(transition_matrix);
for (int i = 1; i < number_of_steps; i++) result = result.mult(transition_matrix);
SimpleMatrix row_result = result.extractVector(true, from_bin);
// row_result.print();
double maxVal = row_result.get(0, 0);
int maxValIndex = 0;
for (int i = 1; i < row_result.numCols(); i++) {
if (row_result.get(0, i) >= maxVal) {
maxVal = row_result.get(0, i);
maxValIndex = i;
}
}
long lEndTime = System.currentTimeMillis();
logger.info(
("From: "
+ from_state
+ " In NumberOfSteps: "
+ number_of_steps
+ " MaxProbabilityBin: "
+ maxValIndex
+ " MostProbablyTo: "
+ getOrgValFromBinNumber(maxValIndex)));
logger.info(("Time taken for prediction = " + (lEndTime - lStartTime)));
return getOrgValFromBinNumber(maxValIndex);
}
// ecuatia sferei
// sum from i=1 to m of x(i)^2
// x(i) is coded with 8 bits
public double fitness(SimpleMatrix cromosom) {
int value = 0;
int n = cromosom.numCols();
for (int i = 0; i < n; i++) {
value += Math.pow(cromosom.get(i), 2);
}
return value;
}
// ecuatia Rastrigin
// x(i) is coded with 8 bits
public double fitness(SimpleMatrix cromosom) {
int value = 0;
int n = cromosom.numCols();
double x1;
for (int i = 0; i < n; i++) {
x1 = cromosom.get(i);
value += (x1 * x1 - 10 * Math.cos(Math.PI * x1) + 10);
}
return value;
}
// ecuatia Griewank
// x(i) is coded with 8 bits
public double fitness(SimpleMatrix cromosom) {
int sum = 0, product = 1;
int n = cromosom.numCols();
double x1;
for (int i = 0; i < n; i++) {
x1 = cromosom.get(i);
sum += x1 * x1;
product *= Math.cos(x1 / Math.sqrt(i + 1));
}
return 1 / 4000 * sum - product + 1;
}
public static void main(String[] args) {
try {
if (args.length < 5) {
System.out.println(
"Invalid Syntax usage. \n The Syntax is KMeans inputfile distance-metric #Centroids #Iterations Tolerance featureSet crossValidation testDataSet");
}
String inputFile = args[0];
String distanceMetric = args[1];
int centroids = Integer.parseInt(args[2]);
int iterations = Integer.parseInt(args[3]);
double tolerance = Double.parseDouble(args[4]);
String inpFeatures = args[5];
String crossValidation = args[6];
String testFile = args[7];
String[] temp = inpFeatures.split(",");
int[] featureSet = new int[temp.length];
boolean hasConvered = false;
for (int i = 0; i < temp.length; i++) {
featureSet[i] = Integer.parseInt(temp[i]);
}
System.out.println("Features Considered are" + Arrays.toString(featureSet));
SimpleMatrix dataSet = new SimpleMatrix().loadCSV(inputFile);
// Cluster Parameters
int dsRows = dataSet.numRows();
int dsCol = dataSet.numCols();
// Cluster Initialization
List<Cluster> kcentroids = new ArrayList<Cluster>();
for (int i = 0; i < centroids; i++) {
int random = genRandom(0, dsRows - 1);
int[] currPoints = new int[dsRows];
int[] intIndex = new int[dsRows];
// This will have remnance of the first chosen element
Random r = new Random();
SimpleMatrix t = new SimpleMatrix().random(1, dsCol, 0, 0, r);
Cluster centers =
new Cluster(i, dataSet.extractVector(true, random), t, currPoints, intIndex);
kcentroids.add(centers);
}
// printKCentroids(kcentroids);
// dataSet.print();
SimpleMatrix distMatrix = compDist(kcentroids, dataSet, featureSet, distanceMetric);
// distMatrix.print();
// System.out.println(distMatrix.get(0, 1));
// ReassignCentrids(kcentroids, distMatrix, dataSet,featureSet);
// printKCentroids(kcentroids);
for (int k = 0; k < iterations; k++) {
System.out.println("------------------------Iteration " + k + " ------------------------");
distMatrix = compDist(kcentroids, dataSet, featureSet, distanceMetric);
// distMatrix.print();
ReassignCentrids(kcentroids, distMatrix, dataSet, featureSet);
printKCentroids(kcentroids);
hasConvered = detectConvergence(kcentroids, featureSet, tolerance);
// System.out.println(hasConvered);
if (hasConvered) {
System.out.println(
"------------------------Has Converged : Tolerance------------------------");
break;
}
}
if (!hasConvered)
System.out.println(
"------------------------Has Converged : Iterations------------------------");
if (crossValidation.equals("true")) {
SimpleMatrix test = new SimpleMatrix().loadCSV(testFile);
SimpleMatrix dist = compDist(kcentroids, test, featureSet, distanceMetric);
System.out.println("----------Associating Set Data Sets to Calculated Centroid-------");
// dist.print();
List<Cluster> kCentroids_l = kcentroids;
int[] clusterLoc = new int[test.numRows()];
for (int iRows = 0; iRows < test.numRows(); iRows++) {
int clusterNo = 1;
double minvalue = dist.get(iRows, 1);
for (int iCentroid = 0; iCentroid < kCentroids_l.size(); iCentroid++) {
// System.out.println(iRows+" "+iCentroid);
if (dist.get(iRows, iCentroid) < minvalue) {
clusterNo = iCentroid;
minvalue = dist.get(iRows, iCentroid);
}
}
clusterLoc[iRows] = clusterNo;
}
// System.out.println(Arrays.toString(clusterLoc));
for (int i = 0; i < kCentroids_l.size(); i++) {
kCentroids_l.get(i).backup();
kCentroids_l.get(i).noPoints = 0;
Arrays.fill(kCentroids_l.get(i).currPoints, -1);
Arrays.fill(kCentroids_l.get(i).intIndex, -1);
// System.out.println("Clusters Backed Up!");
}
// printKCentroids(kCentroids_l);
for (int i = 0; i < clusterLoc.length; i++) {
int insLoc = kCentroids_l.get(clusterLoc[i]).noPoints;
// System.out.println("Getting element"+dataSet.get(i, 0));
kCentroids_l.get(clusterLoc[i]).currPoints[insLoc] = (int) test.get(i, 0);
kCentroids_l.get(clusterLoc[i]).intIndex[insLoc] = i;
kCentroids_l.get(clusterLoc[i]).noPoints++;
}
printKCentroids(kCentroids_l);
}
} catch (Exception e) {
System.out.println("Unfortunately There is an error.");
e.printStackTrace();
}
}
