/**
* Compares two sets of counts to see which items are interestingly over-represented in the first
* set.
*
* @param a The first counts.
* @param b The reference counts.
* @param maxReturn The maximum number of items to return. Use maxReturn >= a.elementSet.size() to
* return all scores above the threshold.
* @param threshold The minimum score for items to be returned. Use 0 to return all items more
* common in a than b. Use -Double.MAX_VALUE (not Double.MIN_VALUE !) to not use a threshold.
* @return A list of scored items with their scores.
*/
public static <T> List<ScoredItem<T>> compareFrequencies(
Multiset<T> a, Multiset<T> b, int maxReturn, double threshold) {
int totalA = a.size();
int totalB = b.size();
Ordering<ScoredItem<T>> byScoreAscending =
new Ordering<ScoredItem<T>>() {
@Override
public int compare(ScoredItem<T> tScoredItem, ScoredItem<T> tScoredItem1) {
return Double.compare(tScoredItem.score, tScoredItem1.score);
}
};
Queue<ScoredItem<T>> best = new PriorityQueue<ScoredItem<T>>(maxReturn + 1, byScoreAscending);
for (T t : a.elementSet()) {
compareAndAdd(a, b, maxReturn, threshold, totalA, totalB, best, t);
}
// if threshold >= 0 we only iterate through a because anything not there can't be as or more
// common than in b.
if (threshold < 0) {
for (T t : b.elementSet()) {
// only items missing from a need be scored
if (a.count(t) == 0) {
compareAndAdd(a, b, maxReturn, threshold, totalA, totalB, best, t);
}
}
}
List<ScoredItem<T>> r = new ArrayList<ScoredItem<T>>(best);
Collections.sort(r, byScoreAscending.reverse());
return r;
}
public static void main(String[] args) {
// Parse text to separate words
String INPUT_TEXT = "Hello World! Hello All! Hi World!";
// Create Multiset
Multiset<String> multiset = LinkedHashMultiset.create(Arrays.asList(INPUT_TEXT.split(" ")));
// Print count words
System.out.println(
multiset); // print [Hello x 2, World! x 2, All!, Hi]- in predictable iteration order
// Print all unique words
System.out.println(
multiset.elementSet()); // print [Hello, World!, All!, Hi] - in predictable iteration order
// Print count occurrences of words
System.out.println("Hello = " + multiset.count("Hello")); // print 2
System.out.println("World = " + multiset.count("World!")); // print 2
System.out.println("All = " + multiset.count("All!")); // print 1
System.out.println("Hi = " + multiset.count("Hi")); // print 1
System.out.println("Empty = " + multiset.count("Empty")); // print 0
// Print count all words
System.out.println(multiset.size()); // print 6
// Print count unique words
System.out.println(multiset.elementSet().size()); // print 4
}
/**
* @param scores
* @param restrictionSet
* @return intersection of set (Multiset<Integer>) and restrictionSet (if restrictionSet non-null
* & non-empty); otherwise return set
*/
public static Multiset<Integer> intersect(
final Multiset<Integer> scores, final Set<Integer> restrictionSet) {
if (restrictionSet != null && !restrictionSet.isEmpty()) {
int prevSize = scores.size();
Multiset<Integer> intersection = HashMultiset.create(scores);
intersection.retainAll(restrictionSet);
log.debug(
prevSize != 0
? ("Size saving by retainAll = "
+ (((prevSize - intersection.size()) * 100) / prevSize))
+ "%"
: "");
return intersection;
}
return scores;
}
public static void main(String args[]) {
// create a multiset collection
Multiset<String> multiset = HashMultiset.create();
multiset.add("a");
multiset.add("b");
multiset.add("c");
multiset.add("d");
multiset.add("a");
multiset.add("b");
multiset.add("c");
multiset.add("b");
multiset.add("b");
multiset.add("b");
// print the occurrence of an element
System.out.println("Occurrence of 'b' : " + multiset.count("b"));
// print the total size of the multiset
System.out.println("Total Size : " + multiset.size());
// get the distinct elements of the multiset as set
Set<String> set = multiset.elementSet();
// display the elements of the set
System.out.println("Set [");
for (String s : set) {
System.out.println(s);
}
System.out.println("]");
// display all the elements of the multiset using iterator
Iterator<String> iterator = multiset.iterator();
System.out.println("MultiSet [");
while (iterator.hasNext()) {
System.out.println(iterator.next());
}
System.out.println("]");
// display the distinct elements of the multiset with their occurrence count
System.out.println("MultiSet [");
for (Multiset.Entry<String> entry : multiset.entrySet()) {
System.out.println("Element: " + entry.getElement() + ", Occurrence(s): " + entry.getCount());
}
System.out.println("]");
// remove extra occurrences
multiset.remove("b", 2);
// print the occurrence of an element
System.out.println("Occurence of 'b' : " + multiset.count("b"));
}
private static Variable computeFrame(Multiset<Variable> collectionVariables) {
return collectionVariables.size() == 1 ? collectionVariables.iterator().next() : null;
}
