Package org.apache.spark.api.java

Examples of org.apache.spark.api.java.JavaSparkContext

28
29
30
31
32
33
34
35
36
  private static JavaSparkContext sc = null;
  private static SparkConf sparkConf = null;

  public synchronized static JavaSparkContext getSparkContext() {
    if (sc == null) {
      sc = new JavaSparkContext(getSparkConf());
    }
    return sc;
  }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
    String outFile= arg(args, "-out", null);
    String sparkhome = arg(args,  "-spark", System.getenv("SPARK_HOME"));
    String jars[] = arg(args, "-jars", "AR.jar:ARApp.jar:ARExt.jar").split(":");
    boolean partition = Boolean.parseBoolean(arg(args, "-partitions", "true"));
   
    JavaSparkContext ctx = new JavaSparkContext(host, "Abstract-Rendering", sparkhome, jars);
   
   
    OptionDataset<G,I> dataset;
    try {
      dataset= (OptionDataset) OptionDataset.class.getField(config).get(null);
    } catch (
        IllegalAccessException |
        IllegalArgumentException |
        NoSuchFieldException | NullPointerException | SecurityException e) {
      throw new IllegalArgumentException("Could not find -config indicated: " + config);
    }
   
    JavaRDD<Indexed> base;
    File sourceFile = dataset.sourceFile;
    if (!sourceFile.getName().endsWith(".csv")) {
      JavaPairRDD<LongWritable, DataInputRecord> source = ctx.hadoopFile(sourceFile.getPath(), HBINInputFormat.class, LongWritable.class, DataInputRecord.class);
      base = (JavaRDD<Indexed>) (JavaRDD) source.map(new Function<Tuple2<LongWritable, DataInputRecord>, DataInputRecord>() {
        public DataInputRecord call(Tuple2<LongWritable, DataInputRecord> pair) throws Exception {return pair._2;}
      });
    } else {
      JavaRDD<String> source = ctx.textFile(sourceFile.getCanonicalPath());
      base = source.map(new StringToIndexed("\\s*,\\s*"));
    }

    Glypher<G,I> glypher = new Glypher<G,I>(dataset.shaper,dataset.valuer);
    GlyphsetRDD<G, I> glyphs = new GlyphsetRDD<>(base.map(glypher), true, partition);
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
    String inFile = arg(args, "-in", "../data/circlepoints.csv");
    String outFile= arg(args, "-out", null);
    String sparkhome = arg(args,  "-spark", System.getenv("SPARK_HOME"));
    String jars[] = arg(args, "-jars", "AR.jar:ARApp.jar:ARExt.jar").split(":");
   
    JavaSparkContext ctx = new JavaSparkContext(host, "Abstract-Rendering", sparkhome, jars);
    JavaRDD<String> source = ctx.textFile(inFile);
    JavaRDD<Indexed> base = source.map(new StringToIndexed("\\s*,\\s*"));
    Shaper<Indexed, Rectangle2D> shaper = new ToRect(.1, .1, false, 2, 3);
    Valuer<Indexed,Integer> valuer = new Valuer.Constant<Indexed,Integer>(1);

    GlyphsetRDD<Rectangle2D, Integer> glyphs = new GlyphsetRDD<>(base.map(new Glypher<>(shaper, valuer)));
View Full Code Here
157
158
159
160
161
162
163
164
165
166
167
168
    } else if (opts.pipelineType == PipelineType.spark) {
      SparkConf sconf = new SparkConf();
      if (!sconf.contains("spark.app.name") || sconf.get("spark.app.name").equals(getClass().getName())) {
        sconf.setAppName(Utils.getShortClassName(getClass()));
      }
      JavaSparkContext sparkContext = new JavaSparkContext(sconf);
      pipeline = new SparkPipeline(sparkContext, sparkContext.appName());
      pipeline.setConfiguration(getConf());
    } else {
      throw new IllegalArgumentException("Unsupported --pipeline-type: " + opts.pipelineType);
    }
View Full Code Here
25
26
27
28
29
30
31
32
33
34
35
36
     
      List<SampleVector> trainList = new ArrayList<SampleVector>();
      List<SampleVector> testList = new ArrayList<SampleVector>();
      DataInput.splitList(samples, trainList, testList, 0.8);
     
      JavaSparkContext context = SparkContextBuild.getContext(args);
      JavaRDD<SampleVector> rdds = context.parallelize(trainList);
      rdds.count();
      logger.info("RDD ok.");
     
      LR lr = new LR(x_feature, y_feature);
            SGDTrainConfig config = new SGDTrainConfig();
View Full Code Here
26
27
28
29
30
31
32
33
34
35
36
37
     
      List<SampleVector> trainList = new ArrayList<SampleVector>();
      List<SampleVector> testList = new ArrayList<SampleVector>();
      DataInput.splitList(samples, trainList, testList, 0.7);
     
      JavaSparkContext context = SparkContextBuild.getContext(args);
      JavaRDD<SampleVector> rdds = context.parallelize(trainList);
      rdds.count();
      logger.info("RDD ok.");
     
      AutoEncoder da = new AutoEncoder(x_feature, n_hidden);
            SGDTrainConfig config = new SGDTrainConfig();
View Full Code Here
26
27
28
29
30
31
32
33
34
35
36
37
     
      List<SampleVector> trainList = new ArrayList<SampleVector>();
      List<SampleVector> testList = new ArrayList<SampleVector>();
      DataInput.splitList(samples, trainList, testList, 0.7);
     
      JavaSparkContext context = SparkContextBuild.getContext(args);
      JavaRDD<SampleVector> rdds = context.parallelize(trainList);
      rdds.count();
      logger.info("RDD ok.");
     
      RBM rbm = new RBM(x_feature, n_hidden);
            SGDTrainConfig config = new SGDTrainConfig();
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
        for (int i = 0; i < sparkJobJarList.length; i++) {
            sparkJobJarList[i] = jars.get(i);
        }
     
        System.setProperty("spark.local.dir", cmd.getOptionValue("sparkHomePath") + File.separator + "temp");
      return new JavaSparkContext(cmd.getOptionValue("sparkMasterURL"),
          cmd.getOptionValue("sparkJobName", "spark-job-" + System.currentTimeMillis()),
          cmd.getOptionValue("sparkHomePath"),
          sparkJobJarList,
          new HashMap<String,String>());
    }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
    SparkConf sparkConf = new SparkConf()
        .setAppName("Correlate Events")
        // Configure the use of Kryo serialization including our Avro registrator
        .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
        .set("spark.kryo.registrator", "org.kitesdk.examples.spark.AvroKyroRegistrator");
    JavaSparkContext sparkContext = new JavaSparkContext(sparkConf);

    JavaPairRDD<StandardEvent, Void> events = sparkContext.newAPIHadoopRDD(conf,
        DatasetKeyInputFormat.class, StandardEvent.class, Void.class);

    // Map each event to two correlation keys. One with the IP address and the
    // nearest 5 minute interval that happened before the event and one with the
    // IP address and the nearest 5 minute interval that happened after the event
View Full Code Here
36
37
38
39
40
41
42
43
  private transient JavaSparkContext sc;
  private transient JavaSQLContext sqlContext;

  @Before
  public void setUp() {
    sc = new JavaSparkContext("local", "JavaAPISuite");
    sqlContext = new JavaSQLContext(sc);
  }
View Full Code Here
TOP

Related Classes of org.apache.spark.api.java.JavaSparkContext

  • ar.ext.spark.SimpleSparkApp
  • ar.ext.spark.SparkDemoApp
  • com.cloudera.oryx.lambda.BatchLayer
  • com.cloudera.oryx.lambda.speed.SpeedLayer
  • com.datastax.spark.connector.CassandraJavaUtilTest
  • com.datastax.spark.connector.demo.JavaApiDemo
  • net.hydromatic.optiq.impl.spark.SparkRules
  • org.apache.crunch.impl.spark.SparkPipeline
  • org.apache.solr.crunch.CrunchIndexerTool
  • org.apache.spark.examples.JavaHdfsLR
    • 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.