Package storm.trident.operation.builtin

Examples of storm.trident.operation.builtin.Count

44
45
46
47
48
49
50
51
52
53
54
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("user"), new OnlyEnglish())
                .each(new Fields("content", "user"), new ExtractFollowerClassAndContentName(), new Fields("followerClass", "contentName"))
                .parallelismHint(3)
                .groupBy(new Fields("followerClass", "contentName"))
                .persistentAggregate(new HazelCastStateFactory(), new Count(), new Fields("count"))
                .parallelismHint(3)
        ;


        topology
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
                .project(new Fields("content", "user", "status"))
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("status"), new OnlyGeo())
                .each(new Fields("status", "content"), new ExtractLocation(), new Fields("country", "contentName"))
                .groupBy(new Fields("country", "contentName"))
                .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
        ;


        topology
                .newDRPCStream("location_hashtag_count")
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
                .project(new Fields("content", "user"))
                .each(new Fields("content"), new OnlyHashtags())
                .each(new Fields("user"), new OnlyEnglish())
                .each(new Fields("content", "user"), new ExtractFollowerClassAndContentName(), new Fields("followerClass", "contentName"))
                .groupBy(new Fields("followerClass", "contentName"))
                .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
        ;


        topology
                .newDRPCStream("hashtag_count")
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
        TridentTopology topology = new TridentTopology();
        TridentState countState =
                topology
                        .newStream("spout", fakeTweets)
                        .groupBy(new Fields("actor"))
                        .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"));

        topology
                .newDRPCStream("count_per_actor")
                .stateQuery(countState, new Fields("args"), new MapGet(), new Fields("count"));
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
        // The aggregated values can then be processed further, in this case into mean
        topology
                .newStream("aggregation", spout)
                .groupBy(new Fields("city"))
                .chainedAgg()
                .aggregate(new Count(), new Fields("count"))
                .aggregate(new Fields("age"), new Sum(), new Fields("age_sum"))
                .chainEnd()
                .each(new Fields("age_sum", "count"), new DivideAsDouble(), new Fields("mean_age"))
                .each(new Fields("city", "mean_age"), new Print())
        ;

        // What if we want to persist results of an aggregation, but want to further process these
        // results? You can use "newValuesStream" for that
        topology
                .newStream("further",spout)
                .groupBy(new Fields("city"))
                .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
                .newValuesStream()
                .each(new Fields("city", "count"), new Print());

        return topology.build();
    }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
        // Here we are simply using a hash map
        TridentState countState =
                topology
                        .newStream("spout", spout)
                        .groupBy(new Fields("actor"))
                        .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"));

        // There are a few ready-made state libraries that you can use
        // Below is an example to use memcached
//        List<InetSocketAddress> memcachedServerLocations = ImmutableList.of(new InetSocketAddress("some.memcached.server",12000));
//        TridentState countStateMemcached =
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
        // Note how each actor appears more than once. We are aggregating inside small batches (aka micro batches)
        // This is useful for pre-processing before storing the result to databases
        topology
                .newStream("aggregation", spout)
                .groupBy(new Fields("actor"))
                .aggregate(new Count(),new Fields("count"))
                .each(new Fields("actor", "count"),new Print())
        ;

        // In order ot aggregate across batches, we need persistentAggregate.
        // This example is incrementing a count in the DB, using the result of these micro batch aggregations
        // (here we are simply using a hash map for the "database")
        topology
                .newStream("aggregation", spout)
                .groupBy(new Fields("actor"))
                .persistentAggregate(new MemoryMapState.Factory(),new Count(),new Fields("count"))
        ;

        return topology.build();
    }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
        // Let's setup another state that keeps track of actor's appearance counts per location
        TridentState countState =
                topology
                        .newStream("spout", spout)
                        .groupBy(new Fields("actor","location"))
                        .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"));

        // Now, let's calculate the average age of actors seen
        topology
                .newDRPCStream("age_stats", drpc)
                .stateQuery(countState, new TupleCollectionGet(), new Fields("actor", "location"))
                .stateQuery(nameToAge, new Fields("actor"), new MapGet(), new Fields("age"))
                .each(new Fields("actor","location","age"), new Print())
                .groupBy(new Fields("location"))
                .chainedAgg()
                .aggregate(new Count(), new Fields("count"))
                .aggregate(new Fields("age"), new Sum(), new Fields("sum"))
                .chainEnd()
                .each(new Fields("sum", "count"), new DivideAsDouble(), new Fields("avg"))
                .project(new Fields("location", "count", "avg"))
        ;
View Full Code Here
TOP

Related Classes of storm.trident.operation.builtin.Count

  • backtype.storm.contrib.hbase.examples.HBaseTridentAggregateTopology
  • com.datasalt.trident.Demo
  • com.datasalt.trident.examples.PerLocationCounts2
  • com.hmsonline.storm.cassandra.bolt.CassandraMapStateTest
  • storm.starter.trident.TridentWordCount
  • trident.TridentUpdater
  • trident.TridentWordCount
  • tutorial.storm.trident.ClusterTestTopology
  • tutorial.storm.trident.example.GlobalTop20Hashtags
  • tutorial.storm.trident.example.TopHashtagByCountry
    • Copyright © 2018 www.massapicom. 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.