// 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;
}
// Compute all interesting KMeans stats (errors & variances of clusters,
// etc). Return new centers.
double[][] computeStatsFillModel(
Lloyds task,
KMeansModel model,
final Vec[] vecs,
final double[] means,
final double[] mults,
final int[] modes) {
// Fill in the model based on original destandardized centers
if (model._parms._standardize) {
model._output._centers_std_raw = task._cMeans;
}
model._output._centers_raw = destandardize(task._cMeans, _isCats, means, mults);
model._output._size = task._size;
model._output._withinss = task._cSqr;
double ssq = 0; // sum squared error
for (int i = 0; i < _parms._k; i++)
ssq += model._output._withinss[i]; // sum squared error all clusters
model._output._tot_withinss = ssq;
// Sum-of-square distance from grand mean
if (_parms._k == 1) model._output._totss = model._output._tot_withinss;
else {
// If data already standardized, grand mean is just the origin
TotSS totss =
new TotSS(means, mults, modes, _parms.train().domains(), _parms.train().cardinality())
.doAll(vecs);
model._output._totss = totss._tss;
}
model._output._betweenss =
model._output._totss - model._output._tot_withinss; // MSE between-cluster
model._output._iterations++;
// add to scoring history
model._output._history_withinss =
ArrayUtils.copyAndFillOf(
model._output._history_withinss,
model._output._history_withinss.length + 1,
model._output._tot_withinss);
// Two small TwoDimTables - cheap
model._output._model_summary = createModelSummaryTable(model._output);
model._output._scoring_history = createScoringHistoryTable(model._output);
// Take the cluster stats from the model, and assemble them into a model metrics object
model._output._training_metrics = makeTrainingMetrics(model);
return task._cMeans; // New centers
}