@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;
}
private void train() {
if (!new File("kmeans").exists()) {
new File("kmeans").mkdir();
}
createKmeansInput("kmeans/documents", trainingSet);
Utils.runCommand(
"python src/plusone/clustering/kmeans.py "
+ "kmeans/documents -k "
+ numTopics
+ " -m cosine "
+ "-w kmeans -i 50 -q",
true);
betaMatrix = Utils.readMatrix("kmeans/centers", false);
System.out.print("moving kmeans beta to lda folder...");
Utils.runCommand("cp kmeans/centers lda", false);
Utils.runCommand("mv lda/centers lda/final.beta", true);
Utils.createLdaInfo("kmeans/final.other", numTopics, terms.size(), synthetic);
Utils.runCommand("cp kmeans/final.other lda", true);
System.out.println("done.");
}
