@Test
public void testGroupingByEnum() {
EnumMap<TimeUnit, Long> expected = new EnumMap<>(TimeUnit.class);
EnumSet.allOf(TimeUnit.class).forEach(tu -> expected.put(tu, 0L));
expected.put(TimeUnit.SECONDS, 1L);
expected.put(TimeUnit.DAYS, 2L);
expected.put(TimeUnit.NANOSECONDS, 1L);
checkCollector(
"groupingByEnum",
expected,
() -> Stream.of(TimeUnit.SECONDS, TimeUnit.DAYS, TimeUnit.DAYS, TimeUnit.NANOSECONDS),
MoreCollectors.groupingByEnum(TimeUnit.class, Function.identity(), Collectors.counting()));
}
@Test
public void vote() throws Exception {
ObjectMapper mapper = new ObjectMapper();
Restaurant restaurantB =
mapper.readValue(new StringReader(testRestaurantJson1), Restaurant.class);
restaurantRepository.saveAndFlush(restaurantB);
Restaurant restaurantA =
mapper.readValue(new StringReader(testRestaurantJson2), Restaurant.class);
restaurantRepository.saveAndFlush(restaurantA);
doVote(restaurantB.getRestaurantName(), "qqq");
doVote(restaurantB.getRestaurantName(), "www");
doVote(restaurantB.getRestaurantName(), "ddd");
doVote(restaurantA.getRestaurantName(), "kkk");
doVote(restaurantA.getRestaurantName(), "lll");
List<Vote> votes = votesRepository.findAll();
// check all votes are here
assertEquals(MAX_TOTAL_VOTES, votes.size());
Map<Long, Long> res =
votes.stream().collect(Collectors.groupingBy(Vote::getRestaurantId, Collectors.counting()));
// check all votes counter correctly
assertEquals(3l, res.get(restaurantB.getId()).longValue());
assertEquals(2l, res.get(restaurantA.getId()).longValue());
}
public static void main(String[] args) {
// stream.collect(collector): values
// Collectors.groupingBy(classifier)
Stream<Locale> locales = Stream.of(Locale.getAvailableLocales());
Map<String, List<Locale>> languageToLocales =
locales.collect(Collectors.groupingBy(Locale::getDisplayLanguage));
System.out.println(languageToLocales);
System.out.println("--------------");
// stream.collect(collector): values
// Collectors.groupingBy(classifier, downstream)
locales = Stream.of(Locale.getAvailableLocales());
Map<String, Long> languageToLocalesCounting =
locales.collect(Collectors.groupingBy(Locale::getDisplayLanguage, Collectors.counting()));
System.out.println(languageToLocalesCounting);
System.out.println("--------------");
// stream.collect(collector): values
// Collectors.partitioningBy(predicate)
locales = Stream.of(Locale.getAvailableLocales());
Map<Boolean, List<Locale>> englishAndOtherLocales =
locales.collect(Collectors.partitioningBy(l -> l.getLanguage().equals("en")));
List<Locale> englishLocales = englishAndOtherLocales.get(true);
System.out.println(englishLocales);
System.out.println("--------------");
}
private Availability firstAssignation(AID alumn) {
if (this.groups.containsKey(alumn)) {
System.err.println("WARN: Requested first assignation for already registered alumn " + alumn);
return this.groups.get(alumn);
}
// TODO: This could be more optimized, for example, having the
// availabilityCount map cached
// Get the count of the current availabilities
final Map<Availability, Long> availabilityCount =
this.groups.values().stream().collect(Collectors.groupingBy(a -> a, Collectors.counting()));
// Get the current available groups
final List<Availability> availableGroups =
TeacherBehaviour.AVAILABLE_GROUPS
.stream()
.filter(
a -> availabilityCount.getOrDefault(a, 0l) < TeacherBehaviour.MAX_ALUMNS_PER_GROUP)
.collect(Collectors.toList());
// Pick a random one
final Availability result = availableGroups.get(this.random.nextInt(availableGroups.size()));
this.groups.put(alumn, result);
return result;
}
private void checkResults(Restaurant restA, Restaurant restB) {
List<Vote> votes = votesRepository.findAll();
// check changing vote doesn't create new entries
assertEquals(MAX_TOTAL_VOTES, votes.size());
Map<Long, Long> res =
votes.stream().collect(Collectors.groupingBy(Vote::getRestaurantId, Collectors.counting()));
// check that vote actually changed
assertEquals(2l, res.get(restB.getId()).longValue());
assertEquals(3l, res.get(restA.getId()).longValue());
}
/**
* Run time: O(n) can use bit vector also
*
* @param input
* @return
*/
static boolean hasUnique(String input) {
if (input == null || input.isEmpty()) return true;
Map<Character, Long> map =
input
.chars()
.mapToObj(c -> (char) c)
.collect(Collectors.groupingBy(Function.identity(), Collectors.counting()));
return !map.entrySet().stream().anyMatch(x -> x.getValue() > 1);
}
@Test
public void testFiltering() {
Collector<Integer, ?, Optional<Integer>> firstEven =
MoreCollectors.filtering(x -> x % 2 == 0, MoreCollectors.first());
Collector<Integer, ?, Optional<Integer>> firstOdd =
MoreCollectors.filtering(x -> x % 2 != 0, MoreCollectors.first());
Collector<Integer, ?, Integer> sumOddEven =
MoreCollectors.pairing(firstEven, firstOdd, (e, o) -> e.get() + o.get());
List<Integer> ints = Arrays.asList(1, 3, 5, 7, 9, 10, 8, 6, 4, 2, 3, 7, 11);
checkShortCircuitCollector("sumOddEven", 11, 6, ints::stream, sumOddEven);
Collector<Integer, ?, Long> countEven =
MoreCollectors.filtering(x -> x % 2 == 0, Collectors.counting());
checkCollector("filtering", 5L, ints::stream, countEven);
}
// Good reading: https://en.wikipedia.org/wiki/Permutation
private static double numOfPerms(int[] seq) {
// Note that the sequence may potentially have repeating elements
Map<Integer, Long> freq =
Arrays.stream(seq)
.boxed()
.collect(Collectors.groupingBy(Function.identity(), Collectors.counting()));
// https://en.wikipedia.org/wiki/Permutation#Permutations_of_multisets
double numOfPerms = factorial(seq.length);
for (long uniqElemFreq : freq.values()) {
// according to the problem description, max size of permutation is in [2..18] range
numOfPerms /= factorial((int) uniqElemFreq);
}
return numOfPerms;
}
/** {@inheritDoc} */
@Override
public RequestAggregationValues aggregate(RequestCollector requests) {
IntSummaryStatistics stats =
requests
.getReqTimestamps()
.stream()
.collect(
Collectors.groupingBy(
timestamp -> DateUtils.round(new Date(timestamp), timestampAggregation),
Collectors.counting()))
.values()
.stream()
.mapToInt(p -> toInt(p))
.summaryStatistics();
return new RequestAggregationValuesImpl(
stats.getMin(), stats.getMax(), stats.getAverage(), stats.getSum(), stats.getCount());
}
private void validateKeys(MappingNode node) {
Map<String, Long> keyCounts =
node.getValue()
.stream()
.map(NodeTuple::getKeyNode)
.filter(n -> n instanceof ScalarNode)
.map(ScalarNode.class::cast)
.filter(n -> !"!include".equals(n.getTag().getValue())) // exclude !include tag
.collect(Collectors.groupingBy(ScalarNode::getValue, Collectors.counting()));
List<String> duplicatedKeys =
keyCounts
.entrySet()
.stream()
.filter(it -> it.getValue() > 1)
.map(Map.Entry<String, Long>::getKey)
.collect(Collectors.toList());
if (!duplicatedKeys.isEmpty()) {
throw new DuplicateKeyYAMLException(duplicatedKeys);
}
}
private int classify(List<Classifier> classifiers, Instance instance) {
List<Double> predictedClasses =
classifiers
.stream()
.map(
classifier -> {
try {
return classifier.classifyInstance(instance);
} catch (Exception e) {
return -1.0;
}
})
.collect(Collectors.toList());
System.out.println("Resultados de clasificar muestra:");
System.out.println(predictedClasses);
Map<Double, Long> predictedClassOcurrencesMap =
predictedClasses
.stream()
.collect(Collectors.groupingBy(Function.identity(), Collectors.counting()));
System.out.println("Mapa de ocurrencias:");
System.out.println(predictedClassOcurrencesMap);
Double predictedClass =
predictedClassOcurrencesMap
.entrySet()
.stream()
.max(Map.Entry.comparingByValue())
.get()
.getKey();
System.out.println("Resultado final:");
System.out.println(predictedClass);
return predictedClass.intValue();
}
@SuppressWarnings("unchecked")
public static void main(String... args) throws Exception {
Stream<String> scrabbleWordsStream = Files.lines(Paths.get("files", "ospd.txt"));
Set<String> scrabbleWords =
scrabbleWordsStream.map(String::toLowerCase).collect(Collectors.toSet());
Stream<String> shakespeareWordsStream =
Files.lines(Paths.get("files", "words.shakespeare.txt"));
Set<String> shakespeareWords =
shakespeareWordsStream.map(String::toLowerCase).collect(Collectors.toSet());
System.out.println("# de mots autorisés au Scrabble : " + scrabbleWords.size());
// mots utilisés par Shakespeare
Long nWords1 = shakespeareWords.stream().count();
System.out.println("# ofmots utilisés par Shakespeare : " + nWords1);
// number of words used by Shakespeare and allowed at Scrabble
long count =
shakespeareWords.stream().map(String::toLowerCase).filter(scrabbleWords::contains).count();
System.out.println("# number of words used by Shakespeare and allowed at Scrabble = " + count);
// words of Shakespeare grouped by their length
Map<Integer, Long> map1 =
shakespeareWords
.stream()
.collect(Collectors.groupingBy(String::length, Collectors.counting()));
System.out.println("Words of Shakespeare grouped by their length = " + map1);
// words of Shakespeare of 16 letters and more
Map<Integer, List<String>> map2 =
shakespeareWords
.stream()
.filter(word -> word.length() > 15)
.collect(Collectors.groupingBy(String::length));
System.out.println("Words of Shakespeare of 16 letters and more = " + map2);
// words of Shakespeare grouped by their Scrabble score
// in ascending order
Function<String, Integer> score = word -> word.chars().map(scrabbleLetterValueEN).sum();
Map<Integer, Long> map3 =
shakespeareWords
.stream()
.map(String::toLowerCase)
.filter(scrabbleWords::contains)
.collect(Collectors.groupingBy(score, TreeMap::new, Collectors.counting()));
System.out.println("Words of Shakespeare grouped by their Scrabble score = " + map3);
// words of Shakespeare grouped by their Scrabble score, with a score greater than 29
// in ascending order
Predicate<String> scoreGT28 = word -> score.apply(word) > 28;
Map<Integer, List<String>> map4 =
shakespeareWords
.stream()
.map(String::toLowerCase)
.filter(scrabbleWords::contains)
.filter(scoreGT28)
.collect(Collectors.groupingBy(score, TreeMap::new, Collectors.toList()));
System.out.println("Words of Shakespeare grouped by their Scrabble score = " + map4);
// histogram of the letters in a given word
Function<String, Map<Integer, Long>> lettersHisto =
word ->
word.chars()
.mapToObj(Integer::new)
.collect(Collectors.groupingBy(Function.identity(), Collectors.counting()));
// score of a given word, taking into account that the given word
// might contain blank letters
Function<String, Integer> scoreWithBlanks =
word ->
lettersHisto
.apply(word)
.entrySet()
.stream() // Map.Entry<letters, # used>
.mapToInt(
entry ->
scrabbleENScore[entry.getKey() - 'a']
* (int)
Long.min(
entry.getValue(), scrabbleENDistribution[entry.getKey() - 'a']))
.sum();
// number of blanks used for the given word
Function<String, Integer> blanksUsed =
word ->
lettersHisto
.apply(word)
.entrySet()
.stream() // Map.Entry<letters, # used>
.mapToInt(
entry ->
(int)
Long.max(
0L,
entry.getValue() - scrabbleENDistribution[entry.getKey() - 'a']))
.sum();
System.out.println("Number of blanks in [buzzards] = " + blanksUsed.apply("buzzards"));
System.out.println("Real score of [buzzards] = " + scoreWithBlanks.apply("buzzards"));
System.out.println("Number of blanks in [whizzing] = " + blanksUsed.apply("whizzing"));
System.out.println("Real score of [whizzing] = " + scoreWithBlanks.apply("whizzing"));
// best words of Shakespeare and their scores
Map<Integer, List<String>> map =
shakespeareWords
.stream()
.filter(scrabbleWords::contains)
.filter(word -> blanksUsed.apply(word) <= 2L)
.filter(word -> scoreWithBlanks.apply(word) >= 24)
.collect(Collectors.groupingBy(scoreWithBlanks, Collectors.toList()));
System.out.println("Best words of Shakespeare : " + map);
}
@Test
public void testMaxAll() {
List<String> input = Arrays.asList("a", "bb", "c", "", "cc", "eee", "bb", "ddd");
checkCollector(
"maxAll",
Arrays.asList("eee", "ddd"),
input::stream,
MoreCollectors.maxAll(Comparator.comparingInt(String::length)));
Collector<String, ?, String> maxAllJoin =
MoreCollectors.maxAll(Comparator.comparingInt(String::length), Collectors.joining(","));
checkCollector("maxAllJoin", "eee,ddd", input::stream, maxAllJoin);
checkCollector(
"minAll",
1L,
input::stream,
MoreCollectors.minAll(Comparator.comparingInt(String::length), Collectors.counting()));
checkCollector(
"minAllEmpty",
Arrays.asList(""),
input::stream,
MoreCollectors.minAll(Comparator.comparingInt(String::length)));
checkCollectorEmpty(
"maxAll",
Collections.emptyList(),
MoreCollectors.maxAll(Comparator.comparingInt(String::length)));
checkCollectorEmpty("maxAllJoin", "", maxAllJoin);
List<Integer> ints = IntStreamEx.of(new Random(1), 10000, 1, 1000).boxed().toList();
List<Integer> expectedMax = getMaxAll(ints, Comparator.naturalOrder());
List<Integer> expectedMin = getMaxAll(ints, Comparator.reverseOrder());
Collector<Integer, ?, SimpleEntry<Integer, Long>> downstream =
MoreCollectors.pairing(
MoreCollectors.first(),
Collectors.counting(),
(opt, cnt) -> new AbstractMap.SimpleEntry<>(opt.get(), cnt));
checkCollector("maxAll", expectedMax, ints::stream, MoreCollectors.maxAll(Integer::compare));
checkCollector("minAll", expectedMin, ints::stream, MoreCollectors.minAll());
checkCollector(
"entry",
new SimpleEntry<>(expectedMax.get(0), (long) expectedMax.size()),
ints::stream,
MoreCollectors.maxAll(downstream));
checkCollector(
"entry",
new SimpleEntry<>(expectedMin.get(0), (long) expectedMin.size()),
ints::stream,
MoreCollectors.minAll(downstream));
Integer a = new Integer(1), b = new Integer(1), c = new Integer(1000), d = new Integer(1000);
ints = IntStreamEx.range(10, 100).boxed().append(a, c).prepend(b, d).toList();
for (StreamExSupplier<Integer> supplier : streamEx(ints::stream)) {
List<Integer> list = supplier.get().collect(MoreCollectors.maxAll());
assertEquals(2, list.size());
assertSame(d, list.get(0));
assertSame(c, list.get(1));
list = supplier.get().collect(MoreCollectors.minAll());
assertEquals(2, list.size());
assertSame(b, list.get(0));
assertSame(a, list.get(1));
}
}
@Override
public Map<Long, Long> findFS() {
int[] usedCounts = Arrays.copyOfRange(counts, 0, capwidth);
// initial frequency is the same as what we see from counters
Map<Integer, Long> freq =
Arrays.stream(usedCounts)
.boxed()
.collect(Collectors.groupingBy(Integer::intValue, Collectors.counting()));
Long zeroNum = freq.get(0);
if (zeroNum != null && zeroNum == capwidth) {
return new HashMap<>();
}
// estimate the number of items
int num = (int) (capwidth * Math.log(1.0 * capwidth / zeroNum));
Distribution newDistribution = new Distribution(freq);
Distribution oldDistribution = new Distribution();
// A pattern is a setting of itmes+frequencies that sum to sumI
// All patterns in this list will map to a common number sumI
List<Map<Integer, Integer>> patterns = new ArrayList<>();
List<Double> probabilities = new ArrayList<>();
int iterations = 0;
// iteratively update the distribution
// while (notConverged()) {
while (iterations < MAXIMUM_ITERATIONS) {
oldDistribution.fillFrom(newDistribution);
newDistribution.clear();
for (Map.Entry<Integer, Long> entry : freq.entrySet()) {
int sumI = entry.getKey();
int freqI = entry.getValue().intValue();
if (sumI == 0) { // skip key=0
continue;
}
// find new probable patterns, get their probabilities and update the distribution
getPatterns(patterns, sumI, freqI, oldDistribution);
computeProbabilities(patterns, oldDistribution, probabilities);
Iterator<Double> probabilityIterator = probabilities.iterator();
for (Map<Integer, Integer> pattern : patterns) { // for each pattern
double probability = probabilityIterator.next();
for (Map.Entry<Integer, Integer> patternEntry : pattern.entrySet()) {
newDistribution.addFreq(
patternEntry.getKey(), freqI * patternEntry.getValue() * probability);
}
}
}
// scale factor to make sum of distribution equal to 1
double scale = num / newDistribution.sumFreq();
pw.println(
String.format(
DISTRIBUTION_TRACE_FORMATTER,
getStep() + 1,
iterations + 1,
newDistribution.toString(scale)));
iterations++;
}
pw.flush();
System.out.println(getStep());
Map<Long, Long> output = new HashMap<>();
double freqSum = newDistribution.sumFreq();
for (Map.Entry<Integer, Double> entry : newDistribution.freq.entrySet()) {
output.put(entry.getKey().longValue(), (long) (entry.getValue() / freqSum * num));
}
return output;
}
public static <K, V> Map<K, Long> countBy(Function<V, K> keyFn, Collection<V> xs) {
if (xs == null) {
return emptyMap();
}
return xs.stream().collect(Collectors.groupingBy(keyFn, Collectors.counting()));
}
