// Stopping criteria
boolean isDone(KMeansModel model, double[][] newCenters, double[][] oldCenters) {
if (!isRunning()) return true; // Stopped/cancelled
// Stopped for running out iterations
if (model._output._iterations >= _parms._max_iterations) return true;
// Compute average change in standardized cluster centers
if (oldCenters == null) return false; // No prior iteration, not stopping
double average_change = 0;
for (int clu = 0; clu < _parms._k; clu++)
average_change +=
hex.genmodel.GenModel.KMeans_distance(
oldCenters[clu], newCenters[clu], _isCats, null, null);
average_change /= _parms._k; // Average change per cluster
model._output._avg_centroids_chg =
ArrayUtils.copyAndFillOf(
model._output._avg_centroids_chg,
model._output._avg_centroids_chg.length + 1,
average_change);
model._output._training_time_ms =
ArrayUtils.copyAndFillOf(
model._output._training_time_ms,
model._output._training_time_ms.length + 1,
System.currentTimeMillis());
return average_change < TOLERANCE;
}
@Override
public void map(Chunk[] cs) {
for (int row = 0; row < cs[0]._len; row++) {
double[] values = new double[cs.length];
// fetch the data - using consistent NA and categorical data handling (same as for training)
data(values, cs, row, _means, _mults, _modes);
// compute the distance from the (standardized) cluster centroids
_tss += hex.genmodel.GenModel.KMeans_distance(_gc, values, _isCats, null, null);
}
}
/** Return both nearest of N cluster center/centroids, and the square-distance. */
private static ClusterDist closest(
double[][] centers, double[] point, String[][] isCats, ClusterDist cd, int count) {
int min = -1;
double minSqr = Double.MAX_VALUE;
for (int cluster = 0; cluster < count; cluster++) {
double sqr =
hex.genmodel.GenModel.KMeans_distance(centers[cluster], point, isCats, null, null);
if (sqr < minSqr) { // Record nearest cluster
min = cluster;
minSqr = sqr;
}
}
cd._cluster = min; // Record nearest cluster
cd._dist = minSqr; // Record square-distance
return cd; // Return for flow-coding
}