Examples of JobClient

Examples of org.apache.hadoop.mapred.JobClient

71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
      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.InputDriver.class);
   
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(MeanShiftCanopy.class);
   
    FileInputFormat.setInputPaths(conf, new Path(input));
    FileOutputFormat.setOutputPath(conf, new Path(output));
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    conf.setMapperClass(org.apache.mahout.clustering.syntheticcontrol.meanshift.InputMapper.class);
    conf.setReducerClass(Reducer.class);
    conf.setNumReduceTasks(0);
   
    client.setConf(conf);
    JobClient.runJob(conf);
  }
View Full Code Here

Examples of org.apache.hadoop.mapred.JobClient

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
      CommandLineUtil.printHelp(group);
    }
  }
 
  public static void runJob(String input, String output, String vectorClassName) throws IOException {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(InputDriver.class);
   
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(VectorWritable.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    conf.set("vector.implementation.class.name", vectorClassName);
    FileInputFormat.setInputPaths(conf, new Path(input));
    FileOutputFormat.setOutputPath(conf, new Path(output));
   
    conf.setMapperClass(InputMapper.class);
   
    conf.setReducerClass(Reducer.class);
    conf.setNumReduceTasks(0);
   
    client.setConf(conf);
    JobClient.runJob(conf);
  }
View Full Code Here

Examples of org.apache.hadoop.mapred.JobClient

133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
                             String measureClass,
                             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

Examples of org.apache.hadoop.mapred.JobClient

98
99
100
101
102
103
104
105
106
107
108
109
110
      }
     
      if (cmdLine.hasOption(seqOpt)) {
        Path path = new Path(cmdLine.getValue(seqOpt).toString());
        System.out.println("Input Path: " + path);
        JobClient client = new JobClient();
        JobConf conf = new JobConf(Job.class);
        client.setConf(conf);
       
        FileSystem fs = FileSystem.get(path.toUri(), conf);
       
        String dictionaryType = "text";
        if (cmdLine.hasOption(dictTypeOpt)) {
View Full Code Here

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

Examples of org.apache.hadoop.mapred.JobClient

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

Examples of org.apache.hadoop.mapred.JobClient

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

Examples of org.apache.hadoop.mapred.JobClient

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

Examples of org.apache.hadoop.mapred.JobClient

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

Examples of org.apache.hadoop.mapred.JobClient

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
TOP
Copyright © 2018 www.massapi.com. 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.