Package com.datasalt.pangool.io

Examples of com.datasalt.pangool.io.ITuple

172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
  public void testSplits(long maxSplitSize, int generatedRows) throws IOException, InterruptedException, IllegalArgumentException, SecurityException, ClassNotFoundException, InstantiationException, IllegalAccessException, InvocationTargetException, NoSuchMethodException {
    logger.info("Testing maxSplitSize: " + maxSplitSize + " and generatedRows:" + generatedRows);
    FileSystem fS = FileSystem.get(getConf());
    Random r = new Random(1);
    Schema schema = new Schema("schema", Fields.parse("i:int,s:string"));
    ITuple tuple = new Tuple(schema);

    Path outPath = new Path(OUT);
    TupleFile.Writer writer = new TupleFile.Writer(FileSystem.get(getConf()), getConf(), outPath, schema);
    for(int i = 0; i < generatedRows; i++) {
      tuple.set("i", r.nextInt());
      tuple.set("s", r.nextLong() + "");
      writer.append(tuple);
    }
    writer.close();

    TupleInputFormat format = ReflectionUtils.newInstance(TupleInputFormat.class, getConf());
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
  public static class MyHandler extends TupleMapper<LongWritable, Text> {

    @Override
    public void map(LongWritable key, Text value, TupleMRContext context, Collector collector) throws IOException,
        InterruptedException {
      ITuple tuple = new Tuple(schema1);
      tuple.set("a", (int) (Math.random() * 1000));
      tuple.set("b", value.toString());

      ITuple mTuple = new Tuple(getMetaSchema1());
      mTuple.set("partition", (int) (Math.random() * 10));
      mTuple.set("tuple", tuple);

      ITuple mTuple2 = new Tuple(getMetaSchema2());
      mTuple2.set("group", value.toString());
      mTuple2.set("metatuple", mTuple);

      collector.write(mTuple2);
    }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
    Schema targetSchema = new Schema("target", Fields.parse("a:string, b:int?, c:double, d:long?, e:boolean?"));
   
    Configuration conf = new Configuration();
    HadoopSerialization hadoopSerDe = new HadoopSerialization(conf);

    ITuple tuple = new Tuple(schema);
    tuple.set("a", "foo");
    tuple.set("b", 10);
    tuple.set("c", 5d);
   
    SimpleTupleSerializer ser = new SimpleTupleSerializer(schema, hadoopSerDe, conf);
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    ser.open(bos);
   
    for(int i = 0; i < 10; i++) {
      ser.serialize(tuple);
    }
   
    ser.close();
   
    bos.close();
    ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
   
    SimpleTupleDeserializer des = new SimpleTupleDeserializer(schema, targetSchema, hadoopSerDe, conf);
    des.open(bis);
   
    ITuple targetTuple = new Tuple(targetSchema);
    for(int i = 0; i < 10; i++) {
      des.deserialize(targetTuple);
    }
   
    assertEquals("foo", targetTuple.getString("a"));
    assertEquals(10, targetTuple.get("b"));
    assertEquals(5d, targetTuple.get("c"));
    assertNull(targetTuple.get("d"));
    assertNull(targetTuple.get("e"));
   
    // Something important is that if we read a file that doesn't contains a field
    // just after a file that contains this field, we should clear the field even
    // in the case that no default value was provided.
    schema = new Schema("schema", Fields.parse("a:string, c:double"));
    tuple = new Tuple(schema);
    tuple.set("a", "foo");
    tuple.set("c", 5d);
   
    bos = new ByteArrayOutputStream();
    ser = new SimpleTupleSerializer(schema, hadoopSerDe, conf);
    ser.open(bos);
   
    for(int i = 0; i < 10; i++) {
      ser.serialize(tuple);
    }
   
    ser.close();
    bos.close();   
    bis = new ByteArrayInputStream(bos.toByteArray());   
    des = new SimpleTupleDeserializer(schema, targetSchema, hadoopSerDe, conf);
    des.open(bis);
   
    for(int i = 0; i < 10; i++) {
      des.deserialize(targetTuple);
    }
   
    assertEquals("foo", targetTuple.getString("a"));
    assertNull(targetTuple.get("b"));
    assertEquals(5d, targetTuple.get("c"));
    assertNull(targetTuple.get("d"));
    assertNull(targetTuple.get("e"));
   
    bis.close();
  }
View Full Code Here
111
112
113
114
115
116
117
118
119
120
121
122
    @Override
    public void reduce(ITuple group, Iterable<ITuple> tuples, TupleMRContext context, Collector collector)
        throws IOException, InterruptedException, TupleMRException {
      Iterator<ITuple> iterator = tuples.iterator();
      while(iterator.hasNext()) {
        ITuple tuple = iterator.next();
        Utf8 text = (Utf8) tuple.get("word");
        countToEmit.set((Integer) tuple.get("count"));
        collector.write(text, countToEmit);
        Assert.assertFalse(iterator.hasNext());
      }
    }
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
    Schema targetSchema = Mutator.superSetOf(schema, cField, dField);
   
    Configuration conf = new Configuration();
    HadoopSerialization hadoopSerDe = new HadoopSerialization(conf);

    ITuple tuple = new Tuple(schema);
    tuple.set("a", "foo");
    tuple.set("b", 10);
   
    SimpleTupleSerializer ser = new SimpleTupleSerializer(schema, hadoopSerDe, conf);
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    ser.open(bos);
   
    for(int i = 0; i < 100000; i++) {
      ser.serialize(tuple);
    }
   
    ser.close();
   
    bos.close();
    ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
   
    SimpleTupleDeserializer des = new SimpleTupleDeserializer(schema, targetSchema, hadoopSerDe, conf);
    des.open(bis);
   
    ITuple targetTuple = new Tuple(targetSchema);
    long start = System.currentTimeMillis();
    for(int i = 0; i < 100000; i++) {
      des.deserialize(targetTuple);
    }
    long end = System.currentTimeMillis();
    System.out.println(end - start);
   
    assertEquals("foo", targetTuple.getString("a"));
    assertEquals(10, targetTuple.get("b"));
    assertEquals(100d, targetTuple.get("c"));
    assertEquals(1000l, targetTuple.get("d"));
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
    Configuration conf = getConf();
    String input = TestTupleMRJob.class + "-input";
    String output = TestTupleMRJob.class + "-output";

    ITuple tuple = new Tuple(SCHEMA);
    for(int i = 0; i < NUM_ROWS_TO_GENERATE; i++) {
      withTupleInput(input, fillTuple(true, tuple));
    }

    TupleMRBuilder builder = new TupleMRBuilder(getConf(), "test");
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
    FileSystem fs = FileSystem.get(inPath.toUri(), conf);
    TupleFile.Writer writer = new TupleFile.Writer(fs, conf, inPath, TopicalWordCount.getSchema());

    // Topic 1, words: { a, 10 } { b, 1 } , { c, 5 }
    // Top 2 words = a(10), c(5)
    ITuple tuple = new Tuple(TopicalWordCount.getSchema());
    tuple.set("word", "a");
    tuple.set("topic", 1);
    tuple.set("count", 10);
    writer.append(tuple);
   
    tuple.set("word", "b");
    tuple.set("topic", 1);
    tuple.set("count", 1);
    writer.append(tuple);

    tuple.set("word", "c");
    tuple.set("topic", 1);
    tuple.set("count", 5);
    writer.append(tuple);
   
    // Topic 2, words: { a, 10 } { b, 9 } , { c, 5 }
    // Top 2 words = a(10), b(9)
    tuple.set("word", "a");
    tuple.set("topic", 2);
    tuple.set("count", 10);
    writer.append(tuple);
   
    tuple.set("word", "b");
    tuple.set("topic", 2);
    tuple.set("count", 9);
    writer.append(tuple);

    tuple.set("word", "c");
    tuple.set("topic", 2);
    tuple.set("count", 5);
    writer.append(tuple);

    writer.close();
  }
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
      public void reduce(ITuple group, Iterable<ITuple> tuples, TupleMRContext context, Collector collector)
          throws IOException, InterruptedException, TupleMRException {
       
        Iterator<ITuple> iterator = tuples.iterator();
        ITuple currentTuple;
       
        assertEquals(0, group.get("partitionId"));
       
        currentTuple = iterator.next();
        assertEquals("foo1", ((ITuple)currentTuple.get("tuple1")).get("a").toString());
        assertEquals(30, ((ITuple)currentTuple.get("tuple1")).get("b"));
       
        currentTuple = iterator.next();
        assertEquals("foo2", ((ITuple)currentTuple.get("tuple1")).get("a").toString());
        assertEquals(20, ((ITuple)currentTuple.get("tuple1")).get("b"));

        currentTuple = iterator.next();
        assertEquals("foo3", ((ITuple)currentTuple.get("tuple1")).get("a").toString());
        assertEquals(140, ((ITuple)currentTuple.get("tuple1")).get("b"));

        currentTuple = iterator.next();
        assertEquals("foo4", ((ITuple)currentTuple.get("tuple1")).get("a").toString());
        assertEquals(110, ((ITuple)currentTuple.get("tuple1")).get("b"));

        currentTuple = iterator.next();
        assertEquals("foo5", ((ITuple)currentTuple.get("tuple1")).get("a").toString());
        assertEquals(220, ((ITuple)currentTuple.get("tuple1")).get("b"));

        currentTuple = iterator.next();
        assertEquals("foo6", ((ITuple)currentTuple.get("tuple1")).get("a").toString());
        assertEquals(260, ((ITuple)currentTuple.get("tuple1")).get("b"));

        // Second data source BEGINS
        currentTuple = iterator.next();
        assertEquals(4.5, ((ITuple)currentTuple.get("tuple2")).get("c"));
        assertEquals(true, ((ITuple)currentTuple.get("tuple2")).get("d"));
       
        currentTuple = iterator.next();
        assertEquals(4.6, ((ITuple)currentTuple.get("tuple2")).get("c"));
        assertEquals(false, ((ITuple)currentTuple.get("tuple2")).get("d"));
      };
    });
    builder.setGroupByFields("partitionId");
    builder.setOutput(new Path(OUTPUT), new HadoopOutputFormat(TextOutputFormat.class), Text.class, NullWritable.class);
    Job job = builder.createJob();
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
    public void reduce(ITuple group, Iterable<ITuple> tuples, TupleMRContext context, Collector collector)
        throws IOException, InterruptedException {
      Iterator<ITuple> iterator = tuples.iterator();
      outputKey.set("ELEMENT");
      while(iterator.hasNext()) {
        ITuple tuple = iterator.next();
        outputValue.set(tuple.toString());
        collector.write(outputKey, outputValue);
        System.out.println(outputKey + " => " + outputValue);
      }
    }
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
        for (ITuple tuple : tuples) {
          fillTuple(true, tuple, minIndex, maxIndex);
        }
        for (int indexTuple1 = 0; indexTuple1 < tuples.length; indexTuple1++) {
          for (int indexTuple2 = indexTuple1 + 1; indexTuple2 < tuples.length; indexTuple2++) {
            ITuple tuple1 = tuples[indexTuple1];
            ITuple tuple2 = tuples[indexTuple2];
            assertSameComparison("Sort comparator", sortComparator, tuple1, tuple2);
            assertOppositeOrEqualsComparison(sortComparator, tuple1, tuple2);
            assertSameComparison("Group comparator", groupComparator, tuple1, tuple2);
            assertOppositeOrEqualsComparison(groupComparator, tuple1, tuple2);
          }
View Full Code Here
TOP

Related Classes of com.datasalt.pangool.io.ITuple

  • com.datasalt.pangool.examples.avro.AvroCustomSerializationJob$CountReducer
  • com.datasalt.pangool.examples.avro.AvroTopicalWordCount$CountReducer
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesClassifier
  • com.datasalt.pangool.examples.naivebayes.NaiveBayesGenerate
  • com.datasalt.pangool.examples.topicalwordcount.TestTopicFingerprint
  • com.datasalt.pangool.examples.topicalwordcount.TopicalWordCount$CountReducer
  • com.datasalt.pangool.examples.topicalwordcount.TopicFingerprint$TopNWords
  • com.datasalt.pangool.tuplemr.mapred.lib.output.TestTupleInputOutputFormat
  • com.datasalt.pangool.tuplemr.mapred.RollupReducer
  • com.datasalt.pangool.tuplemr.mapred.SimpleCombiner
    • 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.