Example usage for org.apache.hadoop.mapred JobConf setOutputFormat

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf setOutputFormat.

Prototype

public void setOutputFormat(Class<? extends OutputFormat> theClass) 

Source Link

Document

Set the OutputFormat implementation for the map-reduce job.

Usage

From source file:com.yahoo.semsearch.fastlinking.io.ExtractWikipediaAnchorText.java

License:Apache License

/**
 * Maps from (targetID, (anchor, count)) to (anchor, (targetID, count)).
 *
 * @param inputPath// w  w  w. j av  a 2s  .  c  om
 * @param outputPath
 * @throws IOException
 */
private void task4(String inputPath, String outputPath) throws IOException {
    LOG.info("Extracting anchor text (phase 4)...");
    LOG.info(" - input:   " + inputPath);
    LOG.info(" - output:  " + outputPath);

    JobConf conf = new JobConf(getConf(), ExtractWikipediaAnchorText.class);
    conf.setJobName(
            String.format("ExtractWikipediaAnchorText:phase4[input: %s, output: %s]", inputPath, outputPath));

    conf.setNumReduceTasks(1);

    //FileInputFormat.addInputPath(conf, new Path(inputPath + "/part-00000/data"));
    FileInputFormat.addInputPath(conf, new Path(inputPath + "/part-*/data"));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(MapFileOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(HMapSIW.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(HMapSIW.class);

    conf.setMapperClass(MyMapper4.class);
    conf.setReducerClass(MyReducer4.class);

    JobClient.runJob(conf);
}

---

From source file:com.zfylin.demo.bigdata.hadoop.mr.WordCount2.java

License:Apache License

public static void main(String[] args) throws Exception {
    System.setProperty("HADOOP_USER_NAME", "hdfs");

    //?     ???hadoop?
    String input = "hdfs://hadoop-master:8020/data/hive/warehouse/channel_test.db/tbl_student";
    /**//from  www . j  a v a 2s.  c o  m
     * HDFSout
     * ???
     */
    String output = "hdfs://hadoop-master:8020/data/hive/warehouse/channel_test.db/tbl_student/output/";

    JobConf conf = new JobConf(WordCount2.class);
    /**
     * ERROR: Exception message: /bin/bash: line 0: fg: no job control
       */
    conf.set("mapreduce.app-submission.cross-platform", "true");

    conf.setJobName("WordCount");
    //        conf.addResource("classpath:/hadoop/core-site.xml");
    //        conf.addResource("classpath:/hadoop/hdfs-site.xml");
    //        conf.addResource("classpath:/hadoop/mapred-site.xml");
    //??
    conf.setOutputKeyClass(Text.class);
    //?? int
    conf.setOutputValueClass(IntWritable.class);
    //mapper
    conf.setMapperClass(WordCountMapper.class);
    /**
     * ??Reducer
     * ???mapreduce??
     * ????
     * ????
     * ?
     * ???
     * ?????
     * ?
     */
    conf.setCombinerClass(WordCountReducer.class);
    //reduce
    conf.setReducerClass(WordCountReducer.class);
    /**
     * ?TextInputFormat?
     * ????
     * LongWritable????
     * Text
     */
    conf.setInputFormat(TextInputFormat.class);
    /**
     * ?TextOutpuTFormat?
     * ????toString()
     * 
     */
    conf.setOutputFormat(TextOutputFormat.class);
    //?
    FileInputFormat.setInputPaths(conf, new Path(input));
    //???
    FileOutputFormat.setOutputPath(conf, new Path(output));
    //?mapreduce
    JobClient.runJob(conf);
    System.exit(0);
}

---

From source file:com.zjy.mongo.util.MongoTool.java

License:Apache License

private int runMapredJob(final Configuration conf) {
    final JobConf job = new JobConf(conf, getClass());
    /**//from w  w w . j a  v  a  2s.co  m
     * Any arguments specified with -D <property>=<value>
     * on the CLI will be picked up and set here
     * They override any XML level values
     * Note that -D<space> is important - no space will
     * not work as it gets picked up by Java itself
     */
    // TODO - Do we need to set job name somehow more specifically?
    // This may or may not be correct/sane
    job.setJarByClass(getClass());
    final Class<? extends org.apache.hadoop.mapred.Mapper> mapper = MapredMongoConfigUtil.getMapper(conf);

    if (LOG.isDebugEnabled()) {
        LOG.debug("Mapper Class: " + mapper);
        LOG.debug("Input URI: " + conf.get(MapredMongoConfigUtil.INPUT_URI));
    }
    job.setMapperClass(mapper);
    Class<? extends org.apache.hadoop.mapred.Reducer> combiner = MapredMongoConfigUtil.getCombiner(conf);
    if (combiner != null) {
        job.setCombinerClass(combiner);
    }
    job.setReducerClass(MapredMongoConfigUtil.getReducer(conf));

    job.setOutputFormat(MapredMongoConfigUtil.getOutputFormat(conf));
    job.setOutputKeyClass(MapredMongoConfigUtil.getOutputKey(conf));
    job.setOutputValueClass(MapredMongoConfigUtil.getOutputValue(conf));
    job.setInputFormat(MapredMongoConfigUtil.getInputFormat(conf));
    Class mapOutputKeyClass = MapredMongoConfigUtil.getMapperOutputKey(conf);
    Class mapOutputValueClass = MapredMongoConfigUtil.getMapperOutputValue(conf);

    if (mapOutputKeyClass != null) {
        job.setMapOutputKeyClass(mapOutputKeyClass);
    }
    if (mapOutputValueClass != null) {
        job.setMapOutputValueClass(mapOutputValueClass);
    }

    /**
     * Determines if the job will run verbosely e.g. print debug output
     * Only works with foreground jobs
     */
    final boolean verbose = MapredMongoConfigUtil.isJobVerbose(conf);
    /**
     * Run job in foreground aka wait for completion or background?
     */
    final boolean background = MapredMongoConfigUtil.isJobBackground(conf);
    try {
        RunningJob runningJob = JobClient.runJob(job);
        if (background) {
            LOG.info("Setting up and running MapReduce job in background.");
            return 0;
        } else {
            LOG.info("Setting up and running MapReduce job in foreground, will wait for results.  {Verbose? "
                    + verbose + "}");
            runningJob.waitForCompletion();
            return 0;
        }
    } catch (final Exception e) {
        LOG.error("Exception while executing job... ", e);
        return 1;
    }

}

---

From source file:combiner.CombinerDriver.java

public static void main(String[] args) {
    JobClient client = new JobClient();
    // Configurations for Job set in this variable
    JobConf conf = new JobConf(combiner.CombinerDriver.class);

    // Name of the Job
    conf.setJobName("BookCrossing1.0");

    // Data type of Output Key and Value
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    // Setting the Mapper and Reducer Class
    conf.setMapperClass(combiner.CombinerMapper.class);
    conf.setCombinerClass(combiner.CombinerReducer.class);
    conf.setReducerClass(combiner.CombinerReducer.class);

    // Formats of the Data Type of Input and output
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    // Specify input and output DIRECTORIES (not files)
    FileInputFormat.setInputPaths(conf, new Path(args[1]));
    FileOutputFormat.setOutputPath(conf, new Path(args[2]));

    client.setConf(conf);/*w ww  .ja v a  2s .c o m*/
    try {
        // Running the job with Configurations set in the conf.
        JobClient.runJob(conf);
    } catch (Exception e) {
        e.printStackTrace();
    }
}

---

From source file:contrail.stages.GraphToFasta.java

License:Open Source License

@Override
public RunningJob runJob() throws Exception {
    String inputPath = (String) stage_options.get("inputpath");
    String outputPath = (String) stage_options.get("outputpath");

    sLogger.info(" - inputpath: " + inputPath);
    sLogger.info(" - outputpath: " + outputPath);

    JobConf conf = new JobConf(GraphToFasta.class);

    AvroJob.setInputSchema(conf, GraphNodeData.SCHEMA$);

    initializeJobConfiguration(conf);/*from   w  w  w  .java2s.c o  m*/

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    AvroInputFormat<GraphNodeData> input_format = new AvroInputFormat<GraphNodeData>();
    conf.setInputFormat(input_format.getClass());
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(Text.class);

    // Make it mapper only.
    conf.setNumReduceTasks(0);
    conf.setMapperClass(GraphToFastqMapper.class);

    if (stage_options.containsKey("writeconfig")) {
        writeJobConfig(conf);
    } else {
        // Delete the output directory if it exists already
        Path out_path = new Path(outputPath);
        if (FileSystem.get(conf).exists(out_path)) {
            // TODO(jlewi): We should only delete an existing directory
            // if explicitly told to do so.
            sLogger.info("Deleting output path: " + out_path.toString() + " " + "because it already exists.");
            FileSystem.get(conf).delete(out_path, true);
        }

        long starttime = System.currentTimeMillis();
        RunningJob result = JobClient.runJob(conf);
        long endtime = System.currentTimeMillis();

        float diff = (float) ((endtime - starttime) / 1000.0);

        System.out.println("Runtime: " + diff + " s");
        return result;
    }
    return null;
}

---

From source file:Corrector.Correction.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: Correction [0/7]");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(Correction.class);
    conf.setJobName("Correction " + inputPath + " " + Config.K);

    Config.initializeConfiguration(conf);

    FileInputFormat.addInputPaths(conf, inputPath);
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(Text.class);
    //conf.setBoolean("mapred.output.compress", true);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);

    conf.setMapperClass(CorrectionMapper.class);
    conf.setReducerClass(CorrectionReducer.class);

    //delete the output directory if it exists already
    FileSystem.get(conf).delete(new Path(outputPath), true);

    return JobClient.runJob(conf);
}

---

From source file:Corrector.FindError.java

License:Apache License

public RunningJob run(String inputPath, String outputPath, int idx, String hkmerlist) throws Exception {
    sLogger.info("Tool name: FindError");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(FindError.class);
    conf.setJobName("FindError " + inputPath + " " + Config.K);
    conf.setLong("IDX", idx);
    //\\//from  w  w  w .  j a  v a2 s.c o m
    DistributedCache.addCacheFile(new URI(hkmerlist), conf);
    //\\

    Config.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(Text.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);

    conf.setMapperClass(FindErrorMapper.class);
    conf.setReducerClass(FindErrorReducer.class);

    //delete the output directory if it exists already
    FileSystem.get(conf).delete(new Path(outputPath), true);

    return JobClient.runJob(conf);
}

---

From source file:Corrector.Graph2Fasta.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: Graph2Fasta [7/7]");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(Graph2Fasta.class);
    conf.setJobName("Graph2Fasta " + inputPath);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(Text.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);

    conf.setMapperClass(Graph2FastaMapper.class);

    Config.initializeConfiguration(conf);
    conf.setNumReduceTasks(0);//from w w w . j  a  va2 s  .  co m

    //delete the output directory if it exists already
    FileSystem.get(conf).delete(new Path(outputPath), true);

    return JobClient.runJob(conf);
}

---

From source file:Corrector.Graph2Sfa.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: Graph2Sfa [0/7]");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(Graph2Sfa.class);
    conf.setJobName("Graph2Sfa " + inputPath);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(Text.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);

    conf.setMapperClass(Graph2SfaMapper.class);

    Config.initializeConfiguration(conf);
    conf.setNumReduceTasks(0);//from ww w  .j  av a  2s  . com

    //delete the output directory if it exists already
    FileSystem.get(conf).delete(new Path(outputPath), true);

    return JobClient.runJob(conf);
}

---

From source file:Corrector.IdentifyTrustedReads.java

License:Apache License

public RunningJob run(String inputPath, String outputPath, long kmer_threshold) throws Exception {
    sLogger.info("Tool name: IdentifyTrustedReads");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(IdentifyTrustedReads.class);
    conf.setJobName("IdentifyTrustedReads " + inputPath + " " + Config.K);
    conf.setLong("KmerThreshold", kmer_threshold);
    // conf.setLong("AllKmer", allkmer);

    Config.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(IntWritable.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setMapperClass(IdentifyTrustedReads.IdentifyTrustedReadsMapper.class);
    conf.setReducerClass(IdentifyTrustedReads.IdentifyTrustedReadsReducer.class);

    //delete the output directory if it exists already
    FileSystem.get(conf).delete(new Path(outputPath), true);

    return JobClient.runJob(conf);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »