Package org.apache.hadoop.mapred

Examples of org.apache.hadoop.mapred.JobClient

126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
                             String measureClassName,
                             double t1,
                             double t2,
                             double convergenceDelta,
                             int maxIterations) throws IOException {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(Job.class);
   
    Path outPath = new Path(output);
    client.setConf(conf);
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
    if (dfs.exists(outPath)) {
      dfs.delete(outPath, true);
    }
    String directoryContainingConvertedInput = output + Constants.DIRECTORY_CONTAINING_CONVERTED_INPUT;
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
      CommandLineUtil.printHelp(group);
    }
  }
 
  public static void runJob(String input, String output) throws IOException {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(org.apache.mahout.clustering.syntheticcontrol.meanshift.OutputDriver.class);
   
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    conf.setInputFormat(SequenceFileInputFormat.class);
   
    FileInputFormat.setInputPaths(conf, new Path(input));
    FileOutputFormat.setOutputPath(conf, new Path(output));
   
    conf.setMapperClass(OutputMapper.class);
   
    conf.setReducerClass(Reducer.class);
    conf.setNumReduceTasks(0);
   
    client.setConf(conf);
    JobClient.runJob(conf);
  }
View Full Code Here
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
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
131
132
133
134
135
136
137
138
139
140
   * @throws ClassNotFoundException
   */
  @Override
  public void runJob(String input, String output, BayesParameters params) throws IOException {
   
    Configurable client = new JobClient();
    JobConf conf = new JobConf(BayesWeightSummerDriver.class);
    conf.setJobName("TfIdf Driver running over input: " + input);
   
    conf.setOutputKeyClass(StringTuple.class);
    conf.setOutputValueClass(DoubleWritable.class);
   
    FileInputFormat.addInputPath(conf, new Path(output + "/trainer-termDocCount"));
    FileInputFormat.addInputPath(conf, new Path(output + "/trainer-wordFreq"));
    FileInputFormat.addInputPath(conf, new Path(output + "/trainer-featureCount"));
    Path outPath = new Path(output + "/trainer-tfIdf/");
    FileOutputFormat.setOutputPath(conf, outPath);
   
    // conf.setNumMapTasks(100);
   
    conf.setJarByClass(BayesTfIdfDriver.class);
   
    conf.setMapperClass(BayesTfIdfMapper.class);
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setCombinerClass(BayesTfIdfReducer.class);
   
    conf.setReducerClass(BayesTfIdfReducer.class);
   
    conf.setOutputFormat(BayesTfIdfOutputFormat.class);
   
    conf
        .set("io.serializations",
          "org.apache.hadoop.io.serializer.JavaSerialization,org.apache.hadoop.io.serializer.WritableSerialization");
    // Dont ever forget this. People should keep track of how hadoop conf
    // parameters and make or break a piece of code
   
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
    if (dfs.exists(outPath)) {
      dfs.delete(outPath, true);
    }
   
    Path interimFile = new Path(output + "/trainer-docCount/part-*");
   
    Map<String,Double> labelDocumentCounts = SequenceFileModelReader.readLabelDocumentCounts(dfs,
      interimFile, conf);
   
    DefaultStringifier<Map<String,Double>> mapStringifier = new DefaultStringifier<Map<String,Double>>(conf,
        GenericsUtil.getClass(labelDocumentCounts));
   
    String labelDocumentCountString = mapStringifier.toString(labelDocumentCounts);
    log.info("Counts of documents in Each Label");
    Map<String,Double> c = mapStringifier.fromString(labelDocumentCountString);
    log.info("{}", c);
   
    conf.set("cnaivebayes.labelDocumentCounts", labelDocumentCountString);
    log.info(params.print());
    if (params.get("dataSource").equals("hbase")) {
      HBaseConfiguration hc = new HBaseConfiguration(new Configuration());
      HTableDescriptor ht = new HTableDescriptor(output);
      HColumnDescriptor hcd = new HColumnDescriptor(BayesConstants.HBASE_COLUMN_FAMILY + ':');
      hcd.setBloomfilter(true);
      hcd.setInMemory(true);
      hcd.setMaxVersions(1);
      hcd.setBlockCacheEnabled(true);
      ht.addFamily(hcd);
     
      log.info("Connecting to hbase...");
      HBaseAdmin hba = new HBaseAdmin(hc);
      log.info("Creating Table {}", output);
     
      if (hba.tableExists(output)) {
        hba.disableTable(output);
        hba.deleteTable(output);
        hba.majorCompact(".META.");
      }
      hba.createTable(ht);
      conf.set("output.table", output);
    }
    conf.set("bayes.parameters", params.toString());
   
    client.setConf(conf);
   
    JobClient.runJob(conf);
  }
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
   * @param t2
   *          the canopy T2 threshold
   */
  private static void runJob(String input, String output, String measureClassName,
                             double t1, double t2) throws IOException {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(Job.class);
   
    Path outPath = new Path(output);
    client.setConf(conf);
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
    if (dfs.exists(outPath)) {
      dfs.delete(outPath, true);
    }
    String directoryContainingConvertedInput = output + Constants.DIRECTORY_CONTAINING_CONVERTED_INPUT;
View Full Code Here
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
   * @param output
   *          the output pathname String
   */
  @Override
  public void runJob(String input, String output, BayesParameters params) throws IOException {
    Configurable client = new JobClient();
    JobConf conf = new JobConf(BayesWeightSummerDriver.class);
    conf.setJobName("Bayes Weight Summer Driver running over input: " + input);
   
    conf.setOutputKeyClass(StringTuple.class);
    conf.setOutputValueClass(DoubleWritable.class);
   
    FileInputFormat.addInputPath(conf, new Path(output + "/trainer-tfIdf/trainer-tfIdf"));
    Path outPath = new Path(output + "/trainer-weights");
    FileOutputFormat.setOutputPath(conf, outPath);
    // conf.setNumReduceTasks(1);
    // conf.setNumMapTasks(100);
    conf.setMapperClass(BayesWeightSummerMapper.class);
    // see the javadoc for the spec for file input formats: first token is key,
    // rest is input. Whole document on one line
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setCombinerClass(BayesWeightSummerReducer.class);
    conf.setReducerClass(BayesWeightSummerReducer.class);
    conf.setOutputFormat(BayesWeightSummerOutputFormat.class);
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
    if (dfs.exists(outPath)) {
      dfs.delete(outPath, true);
    }
    conf.set("bayes.parameters", params.toString());
   
    conf.set("output.table", output);
   
    client.setConf(conf);
   
    JobClient.runJob(conf);
  }
View Full Code Here
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
   *
   * @param params
   *          The Job parameters containing the gramSize, input output folders, defaultCat, encoding
   */
  public static void runJob(Parameters params) throws IOException {
    Configurable client = new JobClient();
    JobConf conf = new JobConf(BayesClassifierDriver.class);
    conf.setJobName("Bayes Classifier Driver running over input: " + params.get("testDirPath"));
    conf.setOutputKeyClass(StringTuple.class);
    conf.setOutputValueClass(DoubleWritable.class);
   
    FileInputFormat.setInputPaths(conf, new Path(params.get("testDirPath")));
    Path outPath = new Path(params.get("testDirPath") + "-output");
    FileOutputFormat.setOutputPath(conf, outPath);
   
    conf.setInputFormat(KeyValueTextInputFormat.class);
    conf.setMapperClass(BayesClassifierMapper.class);
    conf.setCombinerClass(BayesClassifierReducer.class);
    conf.setReducerClass(BayesClassifierReducer.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
   
    conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization,"
                                  + "org.apache.hadoop.io.serializer.WritableSerialization");
   
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
    if (dfs.exists(outPath)) {
      dfs.delete(outPath, true);
    }
    conf.set("bayes.parameters", params.toString());
   
    client.setConf(conf);
    JobClient.runJob(conf);
   
    Path outputFiles = new Path(outPath.toString() + "/part*");
    ConfusionMatrix matrix = readResult(dfs, outputFiles, conf, params);
    log.info("{}", matrix.summarize());
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
      clusterIdToPoints = Collections.emptyMap();
    }
  }

  public void printClusters() throws IOException, InstantiationException, IllegalAccessException {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(Job.class);
    client.setConf(conf);

    String[] dictionary = null;
    if (this.termDictionary != null) {
      if (dictionaryFormat.equals("text")) {
        dictionary = VectorHelper.loadTermDictionary(new File(this.termDictionary));
View Full Code Here
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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
   * @param output
   *          the output pathname String
   */
  @Override
  public void runJob(String input, String output, BayesParameters params) throws IOException {
    Configurable client = new JobClient();
    JobConf conf = new JobConf(CBayesThetaNormalizerDriver.class);
    conf.setJobName("Complementary Bayes Theta Normalizer Driver running over input: " + input);
   
    conf.setOutputKeyClass(StringTuple.class);
    conf.setOutputValueClass(DoubleWritable.class);
    FileInputFormat.addInputPath(conf, new Path(output + "/trainer-weights/Sigma_j"));
    FileInputFormat.addInputPath(conf, new Path(output + "/trainer-tfIdf/trainer-tfIdf"));
    Path outPath = new Path(output + "/trainer-thetaNormalizer");
    FileOutputFormat.setOutputPath(conf, outPath);
    // conf.setNumMapTasks(100);
    // conf.setNumReduceTasks(1);
    conf.setMapperClass(CBayesThetaNormalizerMapper.class);
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setCombinerClass(CBayesThetaNormalizerReducer.class);
    conf.setReducerClass(CBayesThetaNormalizerReducer.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    conf
        .set("io.serializations",
          "org.apache.hadoop.io.serializer.JavaSerialization,org.apache.hadoop.io.serializer.WritableSerialization");
    // Dont ever forget this. People should keep track of how hadoop conf
    // parameters and make or break a piece of code
   
    FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
    if (dfs.exists(outPath)) {
      dfs.delete(outPath, true);
    }
   
    Path sigmaKFiles = new Path(output + "/trainer-weights/Sigma_k/*");
    Map<String,Double> labelWeightSum = SequenceFileModelReader.readLabelSums(dfs, sigmaKFiles, conf);
    DefaultStringifier<Map<String,Double>> mapStringifier = new DefaultStringifier<Map<String,Double>>(conf,
        GenericsUtil.getClass(labelWeightSum));
    String labelWeightSumString = mapStringifier.toString(labelWeightSum);
   
    log.info("Sigma_k for Each Label");
    Map<String,Double> c = mapStringifier.fromString(labelWeightSumString);
    log.info("{}", c);
    conf.set("cnaivebayes.sigma_k", labelWeightSumString);
   
    Path sigmaKSigmaJFile = new Path(output + "/trainer-weights/Sigma_kSigma_j/*");
    double sigmaJSigmaK = SequenceFileModelReader.readSigmaJSigmaK(dfs, sigmaKSigmaJFile, conf);
    DefaultStringifier<Double> stringifier = new DefaultStringifier<Double>(conf, Double.class);
    String sigmaJSigmaKString = stringifier.toString(sigmaJSigmaK);
   
    log.info("Sigma_kSigma_j for each Label and for each Features");
    double retSigmaJSigmaK = stringifier.fromString(sigmaJSigmaKString);
    log.info("{}", retSigmaJSigmaK);
    conf.set("cnaivebayes.sigma_jSigma_k", sigmaJSigmaKString);
   
    Path vocabCountFile = new Path(output + "/trainer-tfIdf/trainer-vocabCount/*");
    double vocabCount = SequenceFileModelReader.readVocabCount(dfs, vocabCountFile, conf);
    String vocabCountString = stringifier.toString(vocabCount);
   
    log.info("Vocabulary Count");
    conf.set("cnaivebayes.vocabCount", vocabCountString);
    double retvocabCount = stringifier.fromString(vocabCountString);
    log.info("{}", retvocabCount);
    conf.set("bayes.parameters", params.toString());
    conf.set("output.table", output);
    client.setConf(conf);
   
    JobClient.runJob(conf);
   
  }
View Full Code Here
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
                                         int maxDFPercent,
                                         Path dictionaryFilePath,
                                         Path output,
                                         boolean sequentialAccess) throws IOException {
   
    Configurable client = new JobClient();
    JobConf conf = new JobConf(TFIDFConverter.class);
    conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization,"
                                  + "org.apache.hadoop.io.serializer.WritableSerialization");
    // this conf parameter needs to be set enable serialisation of conf values
   
    conf.setJobName(": MakePartialVectors: input-folder: " + input + ", dictionary-file: "
                    + dictionaryFilePath.toString());
    conf.setLong(FEATURE_COUNT, featureCount);
    conf.setLong(VECTOR_COUNT, vectorCount);
    conf.setInt(MIN_DF, minDf);
    conf.setInt(MAX_DF_PERCENTAGE, maxDFPercent);
    conf.setBoolean(PartialVectorMerger.SEQUENTIAL_ACCESS, sequentialAccess);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(VectorWritable.class);
    DistributedCache.setCacheFiles(new URI[] {dictionaryFilePath.toUri()}, conf);
    FileInputFormat.setInputPaths(conf, new Path(input));
   
    FileOutputFormat.setOutputPath(conf, output);
   
    conf.setMapperClass(IdentityMapper.class);
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setReducerClass(TFIDFPartialVectorReducer.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    FileSystem dfs = FileSystem.get(output.toUri(), conf);
    if (dfs.exists(output)) {
      dfs.delete(output, true);
    }
   
    client.setConf(conf);
    JobClient.runJob(conf);
  }
View Full Code Here
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
   * Count the document frequencies of features in parallel using Map/Reduce. The input documents have to be
   * in {@link SequenceFile} format
   */
  private static void startDFCounting(Path input, Path output) throws IOException {
   
    Configurable client = new JobClient();
    JobConf conf = new JobConf(TFIDFConverter.class);
    conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization,"
                                  + "org.apache.hadoop.io.serializer.WritableSerialization");
    // this conf parameter needs to be set enable serialisation of conf values
   
    conf.setJobName("VectorTfIdf Document Frequency Count running over input: " + input.toString());
    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(LongWritable.class);
   
    FileInputFormat.setInputPaths(conf, input);
    FileOutputFormat.setOutputPath(conf, output);
   
    conf.setMapperClass(TermDocumentCountMapper.class);
   
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setCombinerClass(TermDocumentCountReducer.class);
    conf.setReducerClass(TermDocumentCountReducer.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
   
    FileSystem dfs = FileSystem.get(output.toUri(), conf);
    if (dfs.exists(output)) {
      dfs.delete(output, true);
    }
    client.setConf(conf);
    JobClient.runJob(conf);
  }
View Full Code Here
TOP

Related Classes of org.apache.hadoop.mapred.JobClient

  • com.atlantbh.jmeter.plugins.hadooputilities.jobstatistics.JobLayer
  • com.atlantbh.jmeter.plugins.hadooputilities.jobstatistics.TaskLayer
  • com.cloudera.circus.test.TestXTest
  • com.cloudera.lib.service.hadoop.HadoopService
  • com.cloudera.lib.service.hadoop.TestHadoopService
  • com.fb2pdf.hadoop.cluster.MeanShiftCanopyDriver
  • com.ikanow.infinit.e.processing.custom.CustomProcessingController
  • com.linkedin.camus.etl.kafka.CamusJob
  • com.netflix.lipstick.pigtolipstick.BasicP2LClient
  • com.netflix.lipstick.warnings.JobWarnings
    • 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.