Examples of cascading.tuple.Tuple

cascading.tuple.Tuple
A Tuple represents a set of values. Consider a Tuple the same as a database record where every value is a column in that table.
A "tuple stream" is a set of Tuple instances passed consecutively through a Pipe assembly.
Tuples work in tandem with {@link Fields} and the {@link TupleEntry} classes. A TupleEntry holds an instance ofFields and a Tuple. It allows a tuple to be accessed by its field names, and will help maintain consistent types if any are given on the Fields instance. That is, if a field is specified at an Integer, calling {@link #set(int,Object)}with a String will force the String to be coerced into a Integer instance.
For managing custom types, see the {@link CoercibleType} interface which extends {@link Type}.
Tuple instances created by user code, by default, are mutable (or modifiable). Tuple instances created by the system are immutable (or unmodifiable, tested by calling {@link #isUnmodifiable()}).
For example tuples returned by {@link cascading.operation.FunctionCall#getArguments()}, will always be unmodifiable. Thus they must be copied if they will be changed by user code or cached in the local context. See the Tuple copy constructor, or {@code *Copy()} methodson {@link TupleEntry}.
Because a Tuple can hold any Object type, it is suitable for storing custom types. But all custom types must have a serialization support per the underlying framework.
For Hadoop, a {@link org.apache.hadoop.io.serializer.Serialization} implementationmust be registered with Hadoop. For further performance improvements, see the {@link cascading.tuple.hadoop.SerializationToken} Java annotation. @see org.apache.hadoop.io.serializer.Serialization @see cascading.tuple.hadoop.SerializationToken

    clusteringSpec.addCluster( new Cluster( "3", 6.85277777777778d, 3.075d, 5.78611111111111d, 2.09722222222222d ) );


    ClusteringFunction clusteringFunction = new ClusteringFunction( clusteringSpec );


//    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 6.9d, 3.1d, 4.9d, 1.5d ) );
    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 6.4d, 3.1d, 5.5d, 1.8d ) );


    TupleListCollector collector = invokeFunction( clusteringFunction, tupleArguments, predictedFields );


//    assertEquals( new Tuple( "2" ), collector.entryIterator().next().getTuple() );
    assertEquals( new Tuple( "3" ), collector.entryIterator().next().getTuple() );
    }

View Full Code Here


    treeSpec.setTree( tree );


    TreeFunction treeFunction = new TreeFunction( treeSpec );


    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 0d, 1d, 0d ) );


    TupleListCollector collector = invokeFunction( treeFunction, tupleArguments, predictedFields );


    assertEquals( new Tuple( "1" ), collector.entryIterator().next().getTuple() );
    }

View Full Code Here


    regressionSpec.addRegressionTable( table );


    PredictionRegressionFunction regressionFunction = new PredictionRegressionFunction( regressionSpec );


    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 5.1d, 3.8d, 1.6d, 0.2d ) );


    TupleListCollector collector = invokeFunction( regressionFunction, tupleArguments, predictedFields );


    assertEquals( 1.0d, collector.entryIterator().next().getTuple().getDouble( 0 ), 0.00001d );
    }

View Full Code Here


    regressionSpec.addRegressionTable( regressionTable );


    PredictionRegressionFunction regressionFunction = new PredictionRegressionFunction( regressionSpec );


    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 3d, 1.3d, 0.2d, "setosa" ) );


    TupleListCollector collector = invokeFunction( regressionFunction, tupleArguments, predictedFields );


    assertEquals( new Tuple( 4.70048473693065d ), collector.entryIterator().next().getTuple() );
    }

View Full Code Here

    }


    CategoricalRegressionFunction regressionFunction = new CategoricalRegressionFunction( regressionSpec );


    {
    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 7d, 3.2d, 4.7d, 1.4d ) );


    TupleListCollector collector = invokeFunction( regressionFunction, tupleArguments, modelSchema.getDeclaredFields() );


    assertEquals( "versicolor", collector.entryIterator().next().getTuple().getObject( 0 ) );
    }


    {
    TupleEntry tupleArguments = new TupleEntry( expectedFields, new Tuple( 5.8d, 4d, 1.2d, 0.2d ) );


    TupleListCollector collector = invokeFunction( regressionFunction, tupleArguments, modelSchema.getDeclaredFields() );


    assertEquals( "setosa", collector.entryIterator().next().getTuple().getObject( 0 ) );
    }

View Full Code Here

    expectedFields = Fields.NONE
      .append( new Fields( "var0", double.class ) )
      .append( new Fields( "var1", String.class ) )
      .append( new Fields( "var2", double.class ) );


    Tuple tuple = new Tuple( 0.d, "value", null );


    tupleEntry = new TupleEntry( expectedFields, tuple );
    }

View Full Code Here


  public void sink( TupleEntry tupleEntry, OutputCollector outputCollector ) throws IOException
    {
    if( updateBy != null )
      {
      Tuple allValues = tupleEntry.selectTuple( updateValueFields );
      Tuple updateValues = tupleEntry.selectTuple( updateByFields );


      allValues = cleanTuple( allValues );


      TupleRecord key = new TupleRecord( allValues );


      if( updateValues.equals( updateIfTuple ) )
        outputCollector.collect( key, null );
      else
        outputCollector.collect( key, key );


      return;
      }


    Tuple result = tupleEntry.selectTuple( getSinkFields() );


    result = cleanTuple( result );


    outputCollector.collect( new TupleRecord( result ), null );
    }

View Full Code Here

      statement.setObject( i + 1, tuple.get( i ) );
    }


  public void readFields( ResultSet resultSet ) throws SQLException
    {
    tuple = new Tuple();


    for( int i = 0; i < resultSet.getMetaData().getColumnCount(); i++ )
      tuple.add( (Comparable) resultSet.getObject( i + 1 ) );
    }

View Full Code Here


public class Split extends CascalogFunction {
  public void operate(FlowProcess flowProcess, FunctionCall fnCall) {
    String sentence = fnCall.getArguments().getString(0);
    for (String word : sentence.split(" ")) {
      fnCall.getOutputCollector().add(new Tuple(word));
    }
  }

View Full Code Here

        boolean result = sourceCall.getInput().next(key, value);


        if (!result)
            return false;


        sourceCall.getIncomingEntry().setTuple(new Tuple(key.toString(), value));
        return true;
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cascading.tuple.Tuple

bixo.config.BixoPlatform

bixo.datum.FetchSetDatum

bixo.datum.ParsedDatum

bixo.examples.webmining.AnalyzedDatum

bixo.operations.FilterAndScoreByUrlAndRobotsTest

cascading.BasicPipesPlatformTest

cascading.BufferPipesPlatformTest

cascading.CoGroupFieldedPipesPlatformTest

cascading.DistanceUseCasePlatformTest

cascading.FieldedPipesPlatformTest

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.