List of usage examples for com.google.common.collect Iterators limit
public static <T> Iterator<T> limit(final Iterator<T> iterator, final int limitSize)
From source file:edu.umd.jyothivinjumur.AnalyzeBigramRelativeFrequencyTuple.java
@SuppressWarnings({ "static-access" })
public static void main(String[] args) throws Exception {
Options options = new Options();
options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
CommandLine cmdline = null;//www .ja v a2s . c om
CommandLineParser parser = new GnuParser();
try {
cmdline = parser.parse(options, args);
} catch (ParseException exp) {
System.err.println("Error parsing command line: " + exp.getMessage());
System.exit(-1);
}
if (!cmdline.hasOption(INPUT)) {
System.out.println("args: " + Arrays.toString(args));
HelpFormatter formatter = new HelpFormatter();
formatter.setWidth(120);
formatter.printHelp(AnalyzeBigramRelativeFrequencyJson.class.getName(), options);
ToolRunner.printGenericCommandUsage(System.out);
System.exit(-1);
}
String inputPath = cmdline.getOptionValue(INPUT);
System.out.println("input path: " + inputPath);
List<PairOfWritables<Tuple, FloatWritable>> pairs = SequenceFileUtils.readDirectory(new Path(inputPath));
List<PairOfWritables<Tuple, FloatWritable>> list1 = Lists.newArrayList();
List<PairOfWritables<Tuple, FloatWritable>> list2 = Lists.newArrayList();
for (PairOfWritables<Tuple, FloatWritable> p : pairs) {
Tuple bigram = p.getLeftElement();
if (bigram.get(0).equals("light")) {
list1.add(p);
}
if (bigram.get(0).equals("contain")) {
list2.add(p);
}
}
Collections.sort(list1, new Comparator<PairOfWritables<Tuple, FloatWritable>>() {
@SuppressWarnings("unchecked")
public int compare(PairOfWritables<Tuple, FloatWritable> e1, PairOfWritables<Tuple, FloatWritable> e2) {
if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
Iterator<PairOfWritables<Tuple, FloatWritable>> iter1 = Iterators.limit(list1.iterator(), 10);
while (iter1.hasNext()) {
PairOfWritables<Tuple, FloatWritable> p = iter1.next();
Tuple bigram = p.getLeftElement();
System.out.println(bigram + "\t" + p.getRightElement());
}
Collections.sort(list2, new Comparator<PairOfWritables<Tuple, FloatWritable>>() {
@SuppressWarnings("unchecked")
public int compare(PairOfWritables<Tuple, FloatWritable> e1, PairOfWritables<Tuple, FloatWritable> e2) {
if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
Iterator<PairOfWritables<Tuple, FloatWritable>> iter2 = Iterators.limit(list2.iterator(), 10);
while (iter2.hasNext()) {
PairOfWritables<Tuple, FloatWritable> p = iter2.next();
Tuple bigram = p.getLeftElement();
System.out.println(bigram + "\t" + p.getRightElement());
}
}
From source file:edu.umd.cloud9.example.bigram.AnalyzeBigramCount.java
@SuppressWarnings({ "static-access" })
public static void main(String[] args) {
Options options = new Options();
options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
CommandLine cmdline = null;//w w w . j av a 2 s . co m
CommandLineParser parser = new GnuParser();
try {
cmdline = parser.parse(options, args);
} catch (ParseException exp) {
System.err.println("Error parsing command line: " + exp.getMessage());
System.exit(-1);
}
if (!cmdline.hasOption(INPUT)) {
System.out.println("args: " + Arrays.toString(args));
HelpFormatter formatter = new HelpFormatter();
formatter.setWidth(120);
formatter.printHelp(AnalyzeBigramCount.class.getName(), options);
ToolRunner.printGenericCommandUsage(System.out);
System.exit(-1);
}
String inputPath = cmdline.getOptionValue(INPUT);
System.out.println("input path: " + inputPath);
List<PairOfWritables<Text, IntWritable>> bigrams = SequenceFileUtils.readDirectory(new Path(inputPath));
Collections.sort(bigrams, new Comparator<PairOfWritables<Text, IntWritable>>() {
public int compare(PairOfWritables<Text, IntWritable> e1, PairOfWritables<Text, IntWritable> e2) {
if (e2.getRightElement().compareTo(e1.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
int singletons = 0;
int sum = 0;
for (PairOfWritables<Text, IntWritable> bigram : bigrams) {
sum += bigram.getRightElement().get();
if (bigram.getRightElement().get() == 1) {
singletons++;
}
}
System.out.println("total number of unique bigrams: " + bigrams.size());
System.out.println("total number of bigrams: " + sum);
System.out.println("number of bigrams that appear only once: " + singletons);
System.out.println("\nten most frequent bigrams: ");
Iterator<PairOfWritables<Text, IntWritable>> iter = Iterators.limit(bigrams.iterator(), 10);
while (iter.hasNext()) {
PairOfWritables<Text, IntWritable> bigram = iter.next();
System.out.println(bigram.getLeftElement() + "\t" + bigram.getRightElement());
}
}
From source file:edu.umd.cloud9.example.bigram.AnalyzeBigramRelativeFrequency.java
@SuppressWarnings({ "static-access" })
public static void main(String[] args) {
Options options = new Options();
options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
CommandLine cmdline = null;// w w w . j a v a 2s .c o m
CommandLineParser parser = new GnuParser();
try {
cmdline = parser.parse(options, args);
} catch (ParseException exp) {
System.err.println("Error parsing command line: " + exp.getMessage());
System.exit(-1);
}
if (!cmdline.hasOption(INPUT)) {
System.out.println("args: " + Arrays.toString(args));
HelpFormatter formatter = new HelpFormatter();
formatter.setWidth(120);
formatter.printHelp(AnalyzeBigramRelativeFrequency.class.getName(), options);
ToolRunner.printGenericCommandUsage(System.out);
System.exit(-1);
}
String inputPath = cmdline.getOptionValue(INPUT);
System.out.println("input path: " + inputPath);
List<PairOfWritables<PairOfStrings, FloatWritable>> pairs = SequenceFileUtils
.readDirectory(new Path(inputPath));
List<PairOfWritables<PairOfStrings, FloatWritable>> list1 = Lists.newArrayList();
List<PairOfWritables<PairOfStrings, FloatWritable>> list2 = Lists.newArrayList();
for (PairOfWritables<PairOfStrings, FloatWritable> p : pairs) {
PairOfStrings bigram = p.getLeftElement();
if (bigram.getLeftElement().equals("light")) {
list1.add(p);
}
if (bigram.getLeftElement().equals("contain")) {
list2.add(p);
}
}
Collections.sort(list1, new Comparator<PairOfWritables<PairOfStrings, FloatWritable>>() {
public int compare(PairOfWritables<PairOfStrings, FloatWritable> e1,
PairOfWritables<PairOfStrings, FloatWritable> e2) {
if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
Iterator<PairOfWritables<PairOfStrings, FloatWritable>> iter1 = Iterators.limit(list1.iterator(), 10);
while (iter1.hasNext()) {
PairOfWritables<PairOfStrings, FloatWritable> p = iter1.next();
PairOfStrings bigram = p.getLeftElement();
System.out.println(bigram + "\t" + p.getRightElement());
}
Collections.sort(list2, new Comparator<PairOfWritables<PairOfStrings, FloatWritable>>() {
public int compare(PairOfWritables<PairOfStrings, FloatWritable> e1,
PairOfWritables<PairOfStrings, FloatWritable> e2) {
if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
Iterator<PairOfWritables<PairOfStrings, FloatWritable>> iter2 = Iterators.limit(list2.iterator(), 10);
while (iter2.hasNext()) {
PairOfWritables<PairOfStrings, FloatWritable> p = iter2.next();
PairOfStrings bigram = p.getLeftElement();
System.out.println(bigram + "\t" + p.getRightElement());
}
}
From source file:edu.umd.jyothivinjumur.AnalyzeBigramRelativeFrequencyJson.java
@SuppressWarnings({ "static-access" })
public static void main(String[] args) {
Options options = new Options();
options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
CommandLine cmdline = null;/*from w w w. j a v a 2s. c o m*/
CommandLineParser parser = new GnuParser();
try {
cmdline = parser.parse(options, args);
} catch (ParseException exp) {
System.err.println("Error parsing command line: " + exp.getMessage());
System.exit(-1);
}
if (!cmdline.hasOption(INPUT)) {
System.out.println("args: " + Arrays.toString(args));
HelpFormatter formatter = new HelpFormatter();
formatter.setWidth(120);
formatter.printHelp(AnalyzeBigramRelativeFrequencyJson.class.getName(), options);
ToolRunner.printGenericCommandUsage(System.out);
System.exit(-1);
}
String inputPath = cmdline.getOptionValue(INPUT);
System.out.println("input path: " + inputPath);
List<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>> pairs = SequenceFileUtils
.readDirectory(new Path(inputPath));
List<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>> list1 = Lists.newArrayList();
List<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>> list2 = Lists.newArrayList();
for (PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> p : pairs) {
BigramRelativeFrequencyJson.MyTuple bigram = p.getLeftElement();
if (bigram.getJsonObject().get("Left").getAsString().equals("light")) {
list1.add(p);
}
if (bigram.getJsonObject().get("Left").getAsString().equals("contain")) {
list2.add(p);
}
}
Collections.sort(list1,
new Comparator<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>>() {
public int compare(PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> e1,
PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> e2) {
if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
Iterator<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>> iter1 = Iterators
.limit(list1.iterator(), 10);
while (iter1.hasNext()) {
PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> p = iter1.next();
BigramRelativeFrequencyJson.MyTuple bigram = p.getLeftElement();
System.out.println(bigram + "\t" + p.getRightElement());
}
Collections.sort(list2,
new Comparator<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>>() {
public int compare(PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> e1,
PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> e2) {
if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) {
return e1.getLeftElement().compareTo(e2.getLeftElement());
}
return e2.getRightElement().compareTo(e1.getRightElement());
}
});
Iterator<PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable>> iter2 = Iterators
.limit(list2.iterator(), 10);
while (iter2.hasNext()) {
PairOfWritables<BigramRelativeFrequencyJson.MyTuple, FloatWritable> p = iter2.next();
BigramRelativeFrequencyJson.MyTuple bigram = p.getLeftElement();
System.out.println(bigram + "\t" + p.getRightElement());
}
}
From source file:org.nickelproject.nickel.dataflow.Sources.java
public static <S> Source<S> limit(final Source<S> pSource, final int pLimit) { return new Source<S>() { private static final long serialVersionUID = 1L; @Override/* w w w. j a v a 2 s. com*/ public CloseableIterator<S> iterator() { return TrivialCloseableIterator.create(Iterators.limit(pSource.iterator(), pLimit)); } @Override public Source<? extends Source<S>> partition(final int sizeGuideline) { return Sources.singleton(this); } @Override public int size() { return pLimit; } }; }
From source file:edu.byu.nlp.util.Collections3.java
/** * Only if list:/*from w ww .j av a2 s .c o m*/ * The semantics of the collection returned by this method become undefined if the backing collection (i.e., this * collection) is structurally modified in any way other than via the returned collection. (Structural modifications * are those that change the size of this collection, or otherwise perturb it in such a fashion that iterations in * progress may yield incorrect results.) */ public static <E> Collection<E> limit(final Collection<E> coll, final int limitSize) { if (coll instanceof List) { return ((List<E>) coll).subList(0, limitSize); } return new AbstractCollection<E>() { @Override public Iterator<E> iterator() { return Iterators.limit(coll.iterator(), limitSize); } @Override public int size() { return Math.min(limitSize, coll.size()); } }; }
From source file:org.apache.hive.ptest.conf.QFileTestBatch.java
public QFileTestBatch(String driver, String queryFilesProperty, Set<String> tests, boolean isParallel) { this.driver = driver; this.queryFilesProperty = queryFilesProperty; this.tests = tests; String name = Joiner.on("-").join(driver, Joiner.on("-").join(Iterators.toArray(Iterators.limit(tests.iterator(), 3), String.class))); if (tests.size() > 3) { name = Joiner.on("-").join(name, "and", (tests.size() - 3), "more"); }/*from w w w . jav a 2s . c o m*/ this.name = name; this.isParallel = isParallel; }
From source file:com.google.devtools.build.skyframe.DepsReport.java
@Override public Iterator<SkyKey> iterator() { return Iterators.limit(Iterators.forArray(arr), size); }
From source file:com.addthis.hydra.task.source.DataSourceConstant.java
@Override public void init() { Iterator<Bundle> iter;/*from w ww .j a v a2s . c o m*/ if (repeat == 0) { iter = bundles.iterator(); } else { iter = Iterators.cycle(bundles); if (repeat > 0) { iter = Iterators.limit(iter, (repeat + 1) * bundles.size()); } } iterator = Iterators.peekingIterator(iter); }
From source file:com.eightkdata.mongowp.server.api.pojos.IteratorMongoCursor.java
@Override public Batch<E> fetchBatch() throws MongoException, DeadCursorException { return new CollectionBatch<>(Lists.newArrayList(Iterators.limit(iterator, batchSize)), System.currentTimeMillis()); }