public static final @Nullable Tuple4<Long, Long, Long, Long> contentSizeStats( JavaRDD<ApacheAccessLog> accessLogRDD) { JavaDoubleRDD contentSizes = accessLogRDD.mapToDouble(new GetContentSize()).cache(); long count = contentSizes.count(); if (count == 0) { return null; } Object ordering = Ordering.natural(); final Comparator<Double> cmp = (Comparator<Double>)ordering; return new Tuple4<>(count, contentSizes.reduce(new SumReducer()).longValue(), contentSizes.min(cmp).longValue(), contentSizes.max(cmp).longValue()); }
@Test public void map() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); JavaDoubleRDD doubles = rdd.mapToDouble(Integer::doubleValue).cache(); doubles.collect(); JavaPairRDD<Integer, Integer> pairs = rdd.mapToPair(x -> new Tuple2<>(x, x)).cache(); pairs.collect(); JavaRDD<String> strings = rdd.map(Object::toString).cache(); strings.collect(); }
@Test public void map() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); JavaDoubleRDD doubles = rdd.mapToDouble(Integer::doubleValue).cache(); doubles.collect(); JavaPairRDD<Integer, Integer> pairs = rdd.mapToPair(x -> new Tuple2<>(x, x)).cache(); pairs.collect(); JavaRDD<String> strings = rdd.map(Object::toString).cache(); strings.collect(); }
@Test public void map() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); JavaDoubleRDD doubles = rdd.mapToDouble(x -> 1.0 * x).cache(); doubles.collect(); JavaPairRDD<Integer, Integer> pairs = rdd.mapToPair(x -> new Tuple2<>(x, x)) .cache(); pairs.collect(); JavaRDD<String> strings = rdd.map(Object::toString).cache(); strings.collect(); }
@Test public void map() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); JavaDoubleRDD doubles = rdd.mapToDouble(x -> 1.0 * x).cache(); doubles.collect(); JavaPairRDD<Integer, Integer> pairs = rdd.mapToPair(x -> new Tuple2<>(x, x)) .cache(); pairs.collect(); JavaRDD<String> strings = rdd.map(Object::toString).cache(); strings.collect(); }
@Test public void map() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); JavaDoubleRDD doubles = rdd.mapToDouble(x -> 1.0 * x).cache(); doubles.collect(); JavaPairRDD<Integer, Integer> pairs = rdd.mapToPair(x -> new Tuple2<>(x, x)) .cache(); pairs.collect(); JavaRDD<String> strings = rdd.map(Object::toString).cache(); strings.collect(); }
@Test public void map() { JavaRDD<Integer> rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); JavaDoubleRDD doubles = rdd.mapToDouble(Integer::doubleValue).cache(); doubles.collect(); JavaPairRDD<Integer, Integer> pairs = rdd.mapToPair(x -> new Tuple2<>(x, x)).cache(); pairs.collect(); JavaRDD<String> strings = rdd.map(Object::toString).cache(); strings.collect(); }
@Test public void javaDoubleRDD() { JavaDoubleRDD rdd = sc.parallelizeDoubles(Arrays.asList(1.0, 1.0, 2.0, 3.0, 5.0, 8.0)); JavaDoubleRDD distinct = rdd.distinct(); assertEquals(5, distinct.count()); JavaDoubleRDD filter = rdd.filter(x -> x > 2.0); assertEquals(3, filter.count()); JavaDoubleRDD union = rdd.union(rdd); assertEquals(12, union.count()); union = union.cache(); assertEquals(12, union.count()); assertEquals(20, rdd.sum(), 0.01); StatCounter stats = rdd.stats(); assertEquals(20, stats.sum(), 0.01); assertEquals(20/6.0, rdd.mean(), 0.01); assertEquals(20/6.0, rdd.mean(), 0.01); assertEquals(6.22222, rdd.variance(), 0.01); assertEquals(rdd.variance(), rdd.popVariance(), 1e-14); assertEquals(7.46667, rdd.sampleVariance(), 0.01); assertEquals(2.49444, rdd.stdev(), 0.01); assertEquals(rdd.stdev(), rdd.popStdev(), 1e-14); assertEquals(2.73252, rdd.sampleStdev(), 0.01); rdd.first(); rdd.take(5); }
@Test public void javaDoubleRDD() { JavaDoubleRDD rdd = sc.parallelizeDoubles(Arrays.asList(1.0, 1.0, 2.0, 3.0, 5.0, 8.0)); JavaDoubleRDD distinct = rdd.distinct(); assertEquals(5, distinct.count()); JavaDoubleRDD filter = rdd.filter(x -> x > 2.0); assertEquals(3, filter.count()); JavaDoubleRDD union = rdd.union(rdd); assertEquals(12, union.count()); union = union.cache(); assertEquals(12, union.count()); assertEquals(20, rdd.sum(), 0.01); StatCounter stats = rdd.stats(); assertEquals(20, stats.sum(), 0.01); assertEquals(20/6.0, rdd.mean(), 0.01); assertEquals(20/6.0, rdd.mean(), 0.01); assertEquals(6.22222, rdd.variance(), 0.01); assertEquals(rdd.variance(), rdd.popVariance(), 1e-14); assertEquals(7.46667, rdd.sampleVariance(), 0.01); assertEquals(2.49444, rdd.stdev(), 0.01); assertEquals(rdd.stdev(), rdd.popStdev(), 1e-14); assertEquals(2.73252, rdd.sampleStdev(), 0.01); rdd.first(); rdd.take(5); }
@Test public void javaDoubleRDD() { JavaDoubleRDD rdd = sc.parallelizeDoubles(Arrays.asList(1.0, 1.0, 2.0, 3.0, 5.0, 8.0)); JavaDoubleRDD distinct = rdd.distinct(); assertEquals(5, distinct.count()); JavaDoubleRDD filter = rdd.filter(x -> x > 2.0); assertEquals(3, filter.count()); JavaDoubleRDD union = rdd.union(rdd); assertEquals(12, union.count()); union = union.cache(); assertEquals(12, union.count()); assertEquals(20, rdd.sum(), 0.01); StatCounter stats = rdd.stats(); assertEquals(20, stats.sum(), 0.01); assertEquals(20/6.0, rdd.mean(), 0.01); assertEquals(20/6.0, rdd.mean(), 0.01); assertEquals(6.22222, rdd.variance(), 0.01); assertEquals(rdd.variance(), rdd.popVariance(), 1e-14); assertEquals(7.46667, rdd.sampleVariance(), 0.01); assertEquals(2.49444, rdd.stdev(), 0.01); assertEquals(rdd.stdev(), rdd.popStdev(), 1e-14); assertEquals(2.73252, rdd.sampleStdev(), 0.01); rdd.first(); rdd.take(5); }
@Override public MDoubleStream cache() { return new SparkDoubleStream(doubleStream.cache()); }
/** * The main function to take the input IDs. * @param args the arguments for the function * @throws IOException due to an error reading from the URL */ public static void main(String[] args) throws IOException { long start = System.currentTimeMillis(); StructureDataRDD structureDataRDD = new StructureDataRDD("/path/to/hadoopfolder"); SegmentDataRDD calphaChains = structureDataRDD.getCalpha().filterLength(10, 300); JavaDoubleRDD lengthDist = calphaChains.getLengthDist().cache(); System.out.println(lengthDist.mean()); System.out.println(lengthDist.min()); System.out.println(lengthDist.max()); System.out.println(lengthDist.count()); System.out.println(System.currentTimeMillis()-start); }