Examples of pairs()


Examples of org.apache.crunch.types.PTypeFamily.pairs()

    return grouped.parallelDo(joinFn.getJoinType() + grouped.getName(), joinFn, ret);
  }

  static <K, U, V> PGroupedTable<Pair<K, Integer>, Pair<U, V>> preJoin(PTable<K, U> left, PTable<K, V> right) {
    PTypeFamily ptf = left.getTypeFamily();
    PTableType<Pair<K, Integer>, Pair<U, V>> ptt = ptf.tableOf(ptf.pairs(left.getKeyType(), ptf.ints()),
        ptf.pairs(left.getValueType(), right.getValueType()));

    PTable<Pair<K, Integer>, Pair<U, V>> tag1 = left.parallelDo("joinTagLeft",
        new MapFn<Pair<K, U>, Pair<Pair<K, Integer>, Pair<U, V>>>() {
          @Override
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

  }

  static <K, U, V> PGroupedTable<Pair<K, Integer>, Pair<U, V>> preJoin(PTable<K, U> left, PTable<K, V> right) {
    PTypeFamily ptf = left.getTypeFamily();
    PTableType<Pair<K, Integer>, Pair<U, V>> ptt = ptf.tableOf(ptf.pairs(left.getKeyType(), ptf.ints()),
        ptf.pairs(left.getValueType(), right.getValueType()));

    PTable<Pair<K, Integer>, Pair<U, V>> tag1 = left.parallelDo("joinTagLeft",
        new MapFn<Pair<K, U>, Pair<Pair<K, Integer>, Pair<U, V>>>() {
          @Override
          public Pair<Pair<K, Integer>, Pair<U, V>> map(Pair<K, U> input) {
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

      ParallelDoOptions.Builder optionsBuilder = ParallelDoOptions.builder();
      if (mi.isSourceTarget()) {
        optionsBuilder.sourceTargets((SourceTarget) mi.getSource());
      }
      return left.parallelDo("mapjoin", mapJoinDoFn,
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())),
          optionsBuilder.build());
    } else { // in-memory pipeline
      return left.parallelDo(new InMemoryJoinFn<K, U, V>(iterable, includeUnmatchedLeftValues),
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())));
    }
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

      return left.parallelDo("mapjoin", mapJoinDoFn,
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())),
          optionsBuilder.build());
    } else { // in-memory pipeline
      return left.parallelDo(new InMemoryJoinFn<K, U, V>(iterable, includeUnmatchedLeftValues),
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())));
    }
  }

  static class InMemoryJoinFn<K, U, V> extends DoFn<Pair<K, U>, Pair<K, Pair<U, V>>> {
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

   * @return table containing the top N values from the incoming table
   */
  public static <K, V> PTable<K, V> top(PTable<K, V> ptable, int limit, boolean maximize) {
    PTypeFamily ptf = ptable.getTypeFamily();
    PTableType<K, V> base = ptable.getPTableType();
    PType<Pair<K, V>> pairType = ptf.pairs(base.getKeyType(), base.getValueType());
    PTableType<Integer, Pair<K, V>> inter = ptf.tableOf(ptf.ints(), pairType);
    return ptable.parallelDo("top" + limit + "map", new TopKFn<K, V>(limit, maximize, pairType), inter)
        .groupByKey(1).combineValues(new TopKCombineFn<K, V>(limit, maximize, pairType))
        .parallelDo("top" + limit + "reduce", new DoFn<Pair<Integer, Pair<K, V>>, Pair<K, V>>() {
          public void process(Pair<Integer, Pair<K, V>> input, Emitter<Pair<K, V>> emitter) {
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

      ParallelDoOptions.Builder optionsBuilder = ParallelDoOptions.builder();
      if (mi.isSourceTarget()) {
        optionsBuilder.sourceTargets((SourceTarget) mi.getSource());
      }
      return left.parallelDo("mapjoin", mapJoinDoFn,
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())),
          optionsBuilder.build());
    } else { // in-memory pipeline
      return left.parallelDo(new InMemoryJoinFn<K, U, V>(iterable),
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())));
    }
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

      return left.parallelDo("mapjoin", mapJoinDoFn,
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())),
          optionsBuilder.build());
    } else { // in-memory pipeline
      return left.parallelDo(new InMemoryJoinFn<K, U, V>(iterable),
          tf.tableOf(left.getKeyType(), tf.pairs(left.getValueType(), right.getValueType())));
    }
  }

  static class InMemoryJoinFn<K, U, V> extends DoFn<Pair<K, U>, Pair<K, Pair<U, V>>> {
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

  public static <T> PCollection<T> reservorSample(
      PCollection<T> input,
      int sampleSize,
      Long seed) {
    PTypeFamily ptf = input.getTypeFamily();
    PType<Pair<T, Integer>> ptype = ptf.pairs(input.getPType(), ptf.ints());
    return weightedReservoirSample(
        input.parallelDo(new MapFn<T, Pair<T, Integer>>() {
          public Pair<T, Integer> map(T t) { return Pair.of(t, 1); }
        }, ptype),
        sampleSize,
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

      int[] sampleSizes,
      Long seed) {
    PTypeFamily ptf = input.getTypeFamily();
    PType<T> ttype = (PType<T>) input.getPTableType().getValueType().getSubTypes().get(0);
    PTableType<Integer, Pair<Double, T>> ptt = ptf.tableOf(ptf.ints(),
        ptf.pairs(ptf.doubles(), ttype));
   
    return input.parallelDo(new ReservoirSampleFn<T, N>(sampleSizes, seed, ttype), ptt)
        .groupByKey(1)
        .combineValues(new WRSCombineFn<T>(sampleSizes, ttype))
        .parallelDo(new MapFn<Pair<Integer, Pair<Double, T>>, Pair<Integer, T>>() {
View Full Code Here

Examples of org.apache.crunch.types.PTypeFamily.pairs()

        .parallelDo(new MapFn<Pair<Integer, Pair<Double, T>>, Pair<Integer, T>>() {
          @Override
          public Pair<Integer, T> map(Pair<Integer, Pair<Double, T>> p) {
            return Pair.of(p.first(), p.second().second());
          }
        }, ptf.pairs(ptf.ints(), ttype));
  }

}
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.