private TwoDimTable createModelSummaryTable(KMeansModel.KMeansOutput output) {
List<String> colHeaders = new ArrayList<>();
List<String> colTypes = new ArrayList<>();
List<String> colFormat = new ArrayList<>();
colHeaders.add("Number of Rows");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Number of Clusters");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Number of Categorical Columns");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Number of Iterations");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Within Cluster Sum of Squares");
colTypes.add("double");
colFormat.add("%.5f");
colHeaders.add("Total Sum of Squares");
colTypes.add("double");
colFormat.add("%.5f");
colHeaders.add("Between Cluster Sum of Squares");
colTypes.add("double");
colFormat.add("%.5f");
final int rows = 1;
TwoDimTable table =
new TwoDimTable(
"Model Summary",
null,
new String[rows],
colHeaders.toArray(new String[0]),
colTypes.toArray(new String[0]),
colFormat.toArray(new String[0]),
"");
int row = 0;
int col = 0;
table.set(
row,
col++,
Math.round(_train.numRows() * (hasWeightCol() ? _train.lastVec().mean() : 1)));
table.set(row, col++, output._centers_raw.length);
table.set(row, col++, output._categorical_column_count);
table.set(row, col++, output._iterations);
table.set(row, col++, output._tot_withinss);
table.set(row, col++, output._totss);
table.set(row, col++, output._betweenss);
return table;
}
TotSS(double[] means, double[] mults, int[] modes, String[][] isCats, int[] card) {
_means = means;
_mults = mults;
_modes = modes;
_tss = 0;
_isCats = isCats;
_card = card;
// Mean of numeric col is zero when standardized
_gc = mults != null ? new double[means.length] : Arrays.copyOf(means, means.length);
for (int i = 0; i < means.length; i++) {
if (isCats[i] != null)
_gc[i] =
Math.min(
Math.round(means[i]),
_card[i] - 1); // TODO: Should set to majority class of categorical column
}
}