/** @return the splitNames selected by the editor. */
public static DataModel createSplits(DataSet dataSet, SplitCasesParams params) {
List<Integer> indices = new ArrayList<Integer>(dataSet.getNumRows());
for (int i = 0; i < dataSet.getNumRows(); i++) {
indices.add(i);
}
if (params.isDataShuffled()) {
Collections.shuffle(indices);
}
SplitCasesSpec spec = params.getSpec();
int numSplits = params.getNumSplits();
int sampleSize = spec.getSampleSize();
int[] breakpoints = spec.getBreakpoints();
List<String> splitNames = spec.getSplitNames();
int[] _breakpoints = new int[breakpoints.length + 2];
_breakpoints[0] = 0;
_breakpoints[_breakpoints.length - 1] = sampleSize;
System.arraycopy(breakpoints, 0, _breakpoints, 1, breakpoints.length);
DataModelList list = new DataModelList();
int ncols = dataSet.getNumColumns();
for (int n = 0; n < numSplits; n++) {
int _sampleSize = _breakpoints[n + 1] - _breakpoints[n];
DataSet _data = new ColtDataSet(_sampleSize, dataSet.getVariables());
_data.setName(splitNames.get(n));
for (int i = 0; i < _sampleSize; i++) {
int oldCase = indices.get(i + _breakpoints[n]);
for (int j = 0; j < ncols; j++) {
_data.setObject(i, j, dataSet.getObject(oldCase, j));
}
}
list.add(_data);
}
return list;
}
/**
* Generates a simple exemplar of this class to test serialization.
*
* @see edu.cmu.TestSerialization
* @see TetradSerializableUtils
*/
public static DataWrapper serializableInstance() {
SplitCasesParams params = new SplitCasesParams();
params.setNumSplits(1);
params.setSpec(new SplitCasesSpec(1, new int[1], Collections.singletonList("1")));
return new SplitCasesWrapper(DataWrapper.serializableInstance(), params);
}
