@Override
protected void map(T key, VectorWritable v, Context context)
throws IOException, InterruptedException {
double d = scale(v);
if (d == 1.0) {
outputVector.assign(v.get(), Functions.PLUS);
} else if (d != 0.0) {
outputVector.assign(v.get(), Functions.plusMult(d));
}
}
@Test
public void testInitialization() {
// start with super clusterable data
List<? extends WeightedVector> data = cubishTestData(0.01);
// just do initialization of ball k-means. This should drop a point into each of the clusters
BallKMeans r = new BallKMeans(new BruteSearch(new EuclideanDistanceMeasure()), 6, 20);
r.cluster(data);
// put the centroids into a matrix
Matrix x = new DenseMatrix(6, 5);
int row = 0;
for (Centroid c : r) {
x.viewRow(row).assign(c.viewPart(0, 5));
row++;
}
// verify that each column looks right. Should contain zeros except for a single 6.
final Vector columnNorms =
x.aggregateColumns(
new VectorFunction() {
@Override
public double apply(Vector f) {
// return the sum of three discrepancy measures
return Math.abs(f.minValue())
+ Math.abs(f.maxValue() - 6)
+ Math.abs(f.norm(1) - 6);
}
});
// verify all errors are nearly zero
assertEquals(0, columnNorms.norm(1) / columnNorms.size(), 0.1);
// verify that the centroids are a permutation of the original ones
SingularValueDecomposition svd = new SingularValueDecomposition(x);
Vector s = svd.getS().viewDiagonal().assign(Functions.div(6));
assertEquals(5, s.getLengthSquared(), 0.05);
assertEquals(5, s.norm(1), 0.05);
}
