/**
* This method takes in all the unique terms present in our DB, calculates the Gini Coefficient of
* each term. If the term satisfies both the Gini Coefficient and Support factor requirements,
* it's considered to be a feature.
*
* @return
*/
public ArrayList<String> calculateFeaturesList() {
ArrayList<String> termsList = databaseConnector.getTermsList(false);
ArrayList<String> userDataTermsList = databaseConnector.getTermsList(true);
for (String term : userDataTermsList) {
if (!termsList.contains(term)) {
termsList.add(term);
}
}
ArrayList<String> featuresList = new ArrayList<String>();
for (String term : termsList) {
double giniCoefficient = calculateGiniCoefficient(term);
if (giniCoefficient >= GINI_THRESHOLD) {
featuresList.add(term);
}
}
return featuresList;
}
/**
* Simple method that calculates the gini values for each term and returns that mapping. Uses the
* ValueComparator class to get the values in a descending order. Perfect for testing and
* analysis.
*
* @return
*/
public Map<String, Double> getGiniMapping() {
ArrayList<String> termsList = databaseConnector.getTermsList(false);
ArrayList<String> userDataTermsList = databaseConnector.getTermsList(true);
for (String term : userDataTermsList) {
if (!termsList.contains(term)) {
termsList.add(term);
}
}
Map<String, Double> termGiniMapping = new HashMap<String, Double>();
ValueComparator valueComparator = new ValueComparator(termGiniMapping);
TreeMap<String, Double> sortedTermGiniMapping = new TreeMap<String, Double>(valueComparator);
for (String term : termsList) {
double giniCoefficient = calculateGiniCoefficient(term);
termGiniMapping.put(term, giniCoefficient);
}
sortedTermGiniMapping.putAll(termGiniMapping);
return sortedTermGiniMapping;
}