/**
* Normalizes data in a cluster
*
* @param data
* @return
*/
public DataCluster normalizeData(DataCluster data) {
DataCluster temp = new DataCluster();
temp.setAttributes(data.getAttributes());
List<Double> max = new ArrayList<Double>();
List<Double> min = new ArrayList<Double>();
for (int i = 0; i < data.getAttributes().size(); i++) {
if (data.getAttributesat(i).getType() == TypeAttribute.continuous) {
List<Double> listDouble = data.getColumnAt(i);
max.add(Collections.max(listDouble));
min.add(Collections.min(listDouble));
}
}
for (int k = 0; k < data.sizeOfRecords(); k++) {
RecordCluster rec = new RecordCluster();
// List<String> str = new ArrayList<>();
int mark = 0;
for (int i = 0; i < data.numberOfAttributes(); i++) {
if (data.getAttributes().get(i).getType() == TypeAttribute.continuous) {
rec.addValue(
new ErrorsAndGain()
.roundOff(
((Double.parseDouble(data.getRecordAt(k).getValueat(i)) - min.get(mark))
/ (max.get(mark) - min.get(mark))),
4));
mark++;
} else {
rec.addValue(data.getRecordAt(k).getValueat(i));
}
}
temp.addRecord(rec);
}
return temp;
}
/**
* Gets the point in record excluding ID and Class
*
* @param attrb header
* @param recCluster
* @return array of points
*/
public String[] getPoints(List<AttributeCluster> attrb, RecordCluster recCluster) {
List<String> strlist = new ArrayList<String>();
for (int i = 0; i < attrb.size(); i++) {
if (attrb.get(i).getType() == TypeAttribute.continuous) {
strlist.add(recCluster.getValueat(i));
}
}
return (String[]) strlist.toArray(new String[0]);
}