public static TwoDimTable createCenterTable(
KMeansModel.KMeansOutput output, boolean standardized) {
String name = standardized ? "Standardized Cluster Means" : "Cluster Means";
if (output._size == null
|| output._names == null
|| output._domains == null
|| output._centers_raw == null
|| (standardized && output._centers_std_raw == null)) {
TwoDimTable table =
new TwoDimTable(
name,
null,
new String[] {"1"},
new String[] {"C1"},
new String[] {"double"},
new String[] {"%f"},
"Centroid");
table.set(0, 0, Double.NaN);
return table;
}
String[] rowHeaders = new String[output._size.length];
for (int i = 0; i < rowHeaders.length; i++) rowHeaders[i] = String.valueOf(i + 1);
String[] colTypes = new String[output._names.length];
String[] colFormats = new String[output._names.length];
for (int i = 0; i < output._domains.length; ++i) {
colTypes[i] = output._domains[i] == null ? "double" : "String";
colFormats[i] = output._domains[i] == null ? "%f" : "%s";
}
TwoDimTable table =
new TwoDimTable(name, null, rowHeaders, output._names, colTypes, colFormats, "Centroid");
for (int j = 0; j < output._domains.length; ++j) {
boolean string = output._domains[j] != null;
if (string) {
for (int i = 0; i < output._centers_raw.length; ++i) {
table.set(i, j, output._domains[j][(int) output._centers_raw[i][j]]);
}
} else {
for (int i = 0; i < output._centers_raw.length; ++i) {
table.set(i, j, standardized ? output._centers_std_raw[i][j] : output._centers_raw[i][j]);
}
}
}
return table;
}
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;
}
private TwoDimTable createScoringHistoryTable(KMeansModel.KMeansOutput output) {
List<String> colHeaders = new ArrayList<>();
List<String> colTypes = new ArrayList<>();
List<String> colFormat = new ArrayList<>();
colHeaders.add("Timestamp");
colTypes.add("string");
colFormat.add("%s");
colHeaders.add("Duration");
colTypes.add("string");
colFormat.add("%s");
colHeaders.add("Iteration");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Avg. Change of Std. Centroids");
colTypes.add("double");
colFormat.add("%.5f");
colHeaders.add("Within Cluster Sum Of Squares");
colTypes.add("double");
colFormat.add("%.5f");
final int rows = output._avg_centroids_chg.length;
TwoDimTable table =
new TwoDimTable(
"Scoring History",
null,
new String[rows],
colHeaders.toArray(new String[0]),
colTypes.toArray(new String[0]),
colFormat.toArray(new String[0]),
"");
int row = 0;
for (int i = 0; i < rows; i++) {
int col = 0;
assert (row < table.getRowDim());
assert (col < table.getColDim());
DateTimeFormatter fmt = DateTimeFormat.forPattern("yyyy-MM-dd HH:mm:ss");
table.set(row, col++, fmt.print(output._training_time_ms[i]));
table.set(row, col++, PrettyPrint.msecs(output._training_time_ms[i] - _start_time, true));
table.set(row, col++, i);
table.set(row, col++, output._avg_centroids_chg[i]);
table.set(row, col++, output._history_withinss[i]);
row++;
}
return table;
}
private TwoDimTable createModelSummaryTable(SharedTreeModel.SharedTreeOutput _output) {
List<String> colHeaders = new ArrayList<>();
List<String> colTypes = new ArrayList<>();
List<String> colFormat = new ArrayList<>();
colHeaders.add("Number of Trees");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Model Size in Bytes");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Min. Depth");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Max. Depth");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Mean Depth");
colTypes.add("double");
colFormat.add("%.5f");
colHeaders.add("Min. Leaves");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Max. Leaves");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Mean Leaves");
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++, _output._treeStats._num_trees);
table.set(row, col++, _output._treeStats._byte_size);
table.set(row, col++, _output._treeStats._min_depth);
table.set(row, col++, _output._treeStats._max_depth);
table.set(row, col++, _output._treeStats._mean_depth);
table.set(row, col++, _output._treeStats._min_leaves);
table.set(row, col++, _output._treeStats._max_leaves);
table.set(row, col++, _output._treeStats._mean_leaves);
return table;
}
private TwoDimTable createScoringHistoryTable(SharedTreeModel.SharedTreeOutput _output) {
List<String> colHeaders = new ArrayList<>();
List<String> colTypes = new ArrayList<>();
List<String> colFormat = new ArrayList<>();
colHeaders.add("Timestamp");
colTypes.add("string");
colFormat.add("%s");
colHeaders.add("Duration");
colTypes.add("string");
colFormat.add("%s");
colHeaders.add("Number of Trees");
colTypes.add("long");
colFormat.add("%d");
colHeaders.add("Training MSE");
colTypes.add("double");
colFormat.add("%.5f");
if (_output.isClassifier()) {
colHeaders.add("Training LogLoss");
colTypes.add("double");
colFormat.add("%.5f");
}
if (_output.getModelCategory() == ModelCategory.Binomial) {
colHeaders.add("Training AUC");
colTypes.add("double");
colFormat.add("%.5f");
}
if (_output.getModelCategory() == ModelCategory.Binomial
|| _output.getModelCategory() == ModelCategory.Multinomial) {
colHeaders.add("Training Classification Error");
colTypes.add("double");
colFormat.add("%.5f");
}
if (valid() != null) {
colHeaders.add("Validation MSE");
colTypes.add("double");
colFormat.add("%.5f");
if (_output.isClassifier()) {
colHeaders.add("Validation LogLoss");
colTypes.add("double");
colFormat.add("%.5f");
}
if (_output.getModelCategory() == ModelCategory.Binomial) {
colHeaders.add("Validation AUC");
colTypes.add("double");
colFormat.add("%.5f");
}
if (_output.isClassifier()) {
colHeaders.add("Validation Classification Error");
colTypes.add("double");
colFormat.add("%.5f");
}
}
int rows = 0;
for (int i = 1; i < _output._scored_train.length; i++) {
if (!Double.isNaN(_output._scored_train[i]._mse)) ++rows;
}
TwoDimTable table =
new TwoDimTable(
"Scoring History",
null,
new String[rows],
colHeaders.toArray(new String[0]),
colTypes.toArray(new String[0]),
colFormat.toArray(new String[0]),
"");
int row = 0;
for (int i = 1; i < _output._scored_train.length; i++) {
if (Double.isNaN(_output._scored_train[i]._mse)) continue;
int col = 0;
assert (row < table.getRowDim());
assert (col < table.getColDim());
DateTimeFormatter fmt = DateTimeFormat.forPattern("yyyy-MM-dd HH:mm:ss");
table.set(row, col++, fmt.print(_output._training_time_ms[i]));
table.set(row, col++, PrettyPrint.msecs(_output._training_time_ms[i] - _start_time, true));
table.set(row, col++, i);
ScoreKeeper st = _output._scored_train[i];
table.set(row, col++, st._mse);
if (_output.isClassifier()) table.set(row, col++, st._logloss);
if (_output.getModelCategory() == ModelCategory.Binomial) table.set(row, col++, st._AUC);
if (_output.isClassifier()) table.set(row, col++, st._classError);
if (_valid != null) {
st = _output._scored_valid[i];
table.set(row, col++, st._mse);
if (_output.isClassifier()) table.set(row, col++, st._logloss);
if (_output.getModelCategory() == ModelCategory.Binomial) table.set(row, col++, st._AUC);
if (_output.isClassifier()) table.set(row, col++, st._classError);
}
row++;
}
return table;
}