/**
* This method implements the clustering-based misclassified sample exploitation technique. In
* this method we sample around each of the clusters by creating queries such as the following:
* SELECT rowc, colc FROM testing WHERE (rowc >= 662.5 AND rowc <= 702.5 AND colc >= 992 AND colc
* <= 1053 )
*
* @param numberOfClusters the number of clusters to be explored.
* @return an arrayList containing the samples that we have selected from the misclassified
* sampling areas
* @throws Exception
*/
@Override
public ArrayList<Tuple> getNearestMissclassified(
int numberOfClusters, ArrayList<Tuple> misclassified) throws Exception {
Statement statement;
ResultSet rs;
ArrayList<Tuple> rand = new ArrayList<Tuple>();
double percenAroundMiscl = Global.PERCENT_AROUND_MISCLASSIFIED;
KMeans k = new KMeans();
ArrayList<Tuple> centroids = k.getCentroids(numberOfClusters);
int[] assignments = null;
if (k.centroidsExist == true) {
assignments = k.assignments;
}
System.out.println(
"Exploring the clusters of misclassified. Number of clusters: " + numberOfClusters);
// total number of tuples we should spend on the misclassified phase.
for (int im = 0; im < centroids.size(); im++) {
// System.out.println("This is the centroid: "+centroids.get(0));
ArrayList<Tuple> h = new ArrayList<Tuple>();
Tuple t = centroids.get(im);
String query = "SELECT " + Global.OBJECT_KEY + " , ";
for (int i = 0; i < Global.attributes.size(); i++) {
if (i != Global.attributes.size() - 1) query += Global.attributes.get(i).getName() + " , ";
else query += Global.attributes.get(i).getName();
}
query += " FROM " + Global.TABLE_NAME + " WHERE ";
for (int i = 0; i < Global.attributes.size(); i++) {
ArrayList<String> valuesForQuery =
getClosest(
Global.attributes.get(i).getDomain(), percenAroundMiscl, (double) t.valueAt(i));
if (k.centroidsExist == true) {
while (checkOK(misclassified, valuesForQuery, assignments, im, i) == false) {
percenAroundMiscl++;
valuesForQuery =
getClosest(
Global.attributes.get(i).getDomain(), percenAroundMiscl, (double) t.valueAt(i));
}
}
query +=
" ("
+ Global.attributes.get(i).getName()
+ " >= "
+ valuesForQuery.get(0)
+ " AND "
+ Global.attributes.get(i).getName()
+ " <= "
+ valuesForQuery.get(1)
+ ") ";
if (i < Global.attributes.size() - 1) {
query += " AND ";
}
}
query += " ORDER BY RANDOM() LIMIT " + Global.RANDOM_AROUND_MISCLASSIFIED;
Connection connection = DBConnection.getConnection();
statement =
connection.createStatement(ResultSet.TYPE_SCROLL_SENSITIVE, ResultSet.CONCUR_READ_ONLY);
rs = statement.executeQuery(query);
while (rs.next()) {
Object key = rs.getString(1);
Object[] attrValues = new Object[Global.attributes.size()];
for (int m = 1; m <= Global.attributes.size(); m++) {
attrValues[m - 1] = rs.getString(m + 1);
}
Tuple tuple = new Tuple(key, attrValues);
h.add(tuple);
}
rand.addAll(h);
}
return rand; // returns an ArrayList with the k nearest neighbors
}
/**
* This method calculates the density of a grid cell according to this type:
* numberOfUniqueExistingTuples/numberOfUniqueCombinations (in the cell)
*
* @param theBoundary the boundaries of the specific cell we are calculating the density for
* @return the density of the cell.
* @throws SQLException
* @throws IOException
* @throws NumberFormatException
*/
private double findDensity(Tuple center) throws SQLException, NumberFormatException, IOException {
double density = 0.0;
// calculates the size of each grid
double gridLength = 100 / (double) grids.getGridNumber();
String query = "SELECT count(*) AS count_1 FROM ( SELECT ";
for (int i = 0; i < Global.attributes.size(); i++) {
if (i != Global.attributes.size() - 1) query += Global.attributes.get(i).getName() + " , ";
else query += Global.attributes.get(i).getName();
}
query += " FROM " + Global.TABLE_NAME + " WHERE ";
for (int i = 0; i < Global.attributes.size(); i++) {
query +=
Global.attributes.get(i).getName()
+ " >= "
+ getClosest(
Global.attributes.get(i).getDomain(),
gridLength / 2,
Double.parseDouble("" + center.valueAt(i)),
false)
+ " AND "
+ Global.attributes.get(i).getName()
+ " <= "
+ getClosest(
Global.attributes.get(i).getDomain(),
gridLength / 2,
Double.parseDouble("" + center.valueAt(i)),
true);
if (i < Global.attributes.size() - 1) {
query += " AND ";
}
}
query += " GROUP BY ";
for (int i = 0; i < Global.attributes.size(); i++) {
if (i != Global.attributes.size() - 1) query += Global.attributes.get(i).getName() + " , ";
else query += Global.attributes.get(i).getName();
}
query += ") AS anon_1";
// System.out.println("Query: "+query);
Connection connection = DBConnection.getConnection();
java.sql.Statement statement =
connection.createStatement(ResultSet.TYPE_SCROLL_SENSITIVE, ResultSet.CONCUR_READ_ONLY);
java.sql.ResultSet rs = statement.executeQuery(query);
String result = "";
while (rs.next()) {
result = rs.getString(1);
}
int existing = Integer.parseInt(result);
rs.close();
statement.close();
ArrayList<Integer> uniques = new ArrayList<Integer>();
for (int i = 0; i < Global.attributes.size(); i++) {
String query1 = "SELECT count(distinct " + Global.attributes.get(i).getName();
query1 += ") FROM " + Global.TABLE_NAME + " WHERE ";
query1 +=
Global.attributes.get(i).getName()
+ " >= "
+ getClosest(
Global.attributes.get(i).getDomain(),
gridLength / 2,
Double.parseDouble("" + center.valueAt(i)),
false)
+ " AND "
+ Global.attributes.get(i).getName()
+ " <= "
+ getClosest(
Global.attributes.get(i).getDomain(),
gridLength / 2,
Double.parseDouble("" + center.valueAt(i)),
true);
java.sql.Statement statement1 =
connection.createStatement(ResultSet.TYPE_SCROLL_SENSITIVE, ResultSet.CONCUR_READ_ONLY);
java.sql.ResultSet rs1 = statement1.executeQuery(query1);
String result2 = "";
while (rs1.next()) {
result2 = rs1.getString(1);
}
uniques.add(Integer.parseInt(result2));
rs1.close();
statement1.close();
}
int possibleCombinations = uniques.get(0);
// System.out.println("First attr unique values in the cell: "+uniques.get(0));
// System.out.println("Second attr unique values in the cell: "+uniques.get(1));
// System.out.println("Here should be 2: "+uniques.size());
for (int i = 1; i < uniques.size(); i++) {
possibleCombinations *= uniques.get(i);
}
// System.out.println("Possible combinations: "+ possibleCombinations);
density = (double) existing / (double) possibleCombinations;
return density;
}