List of usage examples for org.apache.hadoop.mapreduce Job setNumReduceTasks
public void setNumReduceTasks(int tasks) throws IllegalStateException
From source file:BigramRelativeFrequencyTuple.java
License:Apache License
/** * Runs this tool.// w ww . ja v a 2 s.c o m */ public int run(String[] args) throws Exception { if (args.length != 3) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int reduceTasks = Integer.parseInt(args[2]); LOG.info("Tool name: " + BigramRelativeFrequencyTuple.class.getSimpleName()); LOG.info(" - input path: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - num reducers: " + reduceTasks); Job job = Job.getInstance(getConf()); job.setJobName(BigramRelativeFrequencyTuple.class.getSimpleName()); job.setJarByClass(BigramRelativeFrequencyTuple.class); job.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setMapOutputKeyClass(BinSedesTuple.class); job.setMapOutputValueClass(FloatWritable.class); job.setOutputKeyClass(BinSedesTuple.class); job.setOutputValueClass(FloatWritable.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setMapperClass(MyMapper.class); job.setCombinerClass(MyCombiner.class); job.setReducerClass(MyReducer.class); job.setPartitionerClass(MyPartitioner.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(getConf()).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:accismus.benchmark.Generator.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 3) { System.err.println(//from w w w .j av a 2 s .c o m "Usage : " + this.getClass().getSimpleName() + " <props file> <num task> <num documents>"); return 1; } Job job = new Job(getConf(), this.getClass().getSimpleName() + "_" + System.currentTimeMillis()); job.setJarByClass(this.getClass()); job.setInputFormatClass(DocumentInputFormat.class); DocumentInputFormat.setNumTask(job, Integer.parseInt(args[1]), Integer.parseInt(args[2])); job.setMapOutputKeyClass(Loader.class); job.setMapOutputValueClass(NullWritable.class); job.setMapperClass(GMapper.class); job.setNumReduceTasks(0); job.setOutputFormatClass(AccismusOutputFormat.class); Properties accisumusProps = new Properties(); accisumusProps.load(new FileReader(args[0])); AccismusOutputFormat.configure(job, accisumusProps); job.waitForCompletion(true); return 0; }
From source file:adts.CreateCorrespondences.java
License:Open Source License
public static void main(String[] args) throws Exception { Configuration config = HBaseConfiguration.create(); Job job = new Job(config, "CreateCorrespondences"); job.setJarByClass(CreateCorrespondences.class); Scan scan = new Scan(); scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs scan.setCacheBlocks(false); // don't set to true for MR jobs TableMapReduceUtil.initTableMapperJob("content", // input HBase table name scan, // Scan instance to control CF and attribute selection Map.class, // mapper Text.class, // mapper output key Text.class, // mapper output value job);/*from w ww .j av a 2 s . c om*/ job.setReducerClass(Reduce.class); job.setNumReduceTasks(1); FileOutputFormat.setOutputPath(job, new Path(args[0])); boolean b = job.waitForCompletion(true); if (!b) { throw new IOException("error with job!"); } }
From source file:adts.PopularKeywords.java
License:Open Source License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "PopularKeywords"); job.setJarByClass(PopularKeywords.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setReducerClass(Reduce.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); Path queriesInputPath = new Path(args[0]); Path StopWordsInputPath = new Path(args[1]); MultipleInputs.addInputPath(job, queriesInputPath, TextInputFormat.class, Map.class); MultipleInputs.addInputPath(job, StopWordsInputPath, TextInputFormat.class, StopwordsMap.class); FileOutputFormat.setOutputPath(job, new Path("/root/temporary")); job.waitForCompletion(true);/*from w ww . ja v a 2 s . co m*/ Job sortingJob = new Job(conf, "PopularKeywords"); sortingJob.setJarByClass(PopularKeywords.class); sortingJob.setOutputKeyClass(Text.class); sortingJob.setOutputValueClass(LongWritable.class); sortingJob.setMapperClass(ReverseMap.class); sortingJob.setReducerClass(ReverseReduce.class); sortingJob.setInputFormatClass(TextInputFormat.class); sortingJob.setOutputFormatClass(TextOutputFormat.class); sortingJob.setSortComparatorClass(LongWritable.DecreasingComparator.class); sortingJob.setMapOutputKeyClass(LongWritable.class); sortingJob.setMapOutputValueClass(Text.class); FileInputFormat.addInputPath(sortingJob, new Path("/root/temporary")); FileOutputFormat.setOutputPath(sortingJob, new Path(args[2])); sortingJob.setNumReduceTasks(1); sortingJob.waitForCompletion(true); }
From source file:adts.PrepareInput.java
License:Open Source License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "PrepareInput"); job.setJarByClass(PrepareInput.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(1); job.waitForCompletion(true);/* w ww . j a v a 2 s. co m*/ }
From source file:AllLab_Skeleton.Lab2.Lab2SecondarySort.java
/** * @param args the command line arguments *//* ww w . ja v a 2 s.co m*/ public static void main(String[] args) { try { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "SecondarySort"); job.setJarByClass(Lab2SecondarySort.class); job.setMapperClass(Lab2Mapper.class); job.setMapOutputKeyClass(CompositeKeyWritable.class); job.setMapOutputValueClass(NullWritable.class); job.setPartitionerClass(Lab2Partitioner.class); job.setGroupingComparatorClass(Lab2GroupComparator.class); job.setReducerClass(Lab2Reducer.class); job.setOutputKeyClass(CompositeKeyWritable.class); job.setOutputValueClass(NullWritable.class); job.setNumReduceTasks(8); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } catch (IOException | InterruptedException | ClassNotFoundException ex) { System.out.println("Erorr Message" + ex.getMessage()); } }
From source file:AllLab_Skeleton.Lab6.BloomFilterBhavesh.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Bloom Filter"); job.setJarByClass(BloomFilterBhavesh.class); job.setMapperClass(BloomFilterMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class); job.setNumReduceTasks(0); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); boolean success = job.waitForCompletion(true); System.out.println(success);/*from w ww . jav a2 s . c o m*/ }
From source file:AllLab_Skeleton.Lab6.BloomFilterUsingDistributedCache.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Bloom Filter"); job.setJarByClass(BloomFilterUsingDistributedCache.class); job.setMapperClass(BloomFilterMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class); //adding the file in the cache having the Person class records //job.addCacheFile(new Path("localhost:9000/bhavesh/LabAssignment/CacheInput/cache.txt").toUri()); DistributedCache.addCacheFile(new URI(args[2]), job.getConfiguration()); job.setNumReduceTasks(0); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true);// w ww.j a va 2 s .c om }
From source file:Analysis.A2_Top_20_Most_Popular_Artists.Top_20_Most_Popular_Artist_Driver.java
/** * @param args the command line arguments */// w w w .j av a 2 s . c o m public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Top 20 most popular artist "); job.setJarByClass(Top_20_Most_Popular_Artist_Driver.class); job.setMapperClass(Top_20_Most_Popular_Artist_Mapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setNumReduceTasks(1); job.setCombinerClass(Top_20_Most_Popular_Artist_Combiner.class); job.setReducerClass(Top_20_Most_Popular_Artist_Reducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A5_Min_Max_Median_Age_Top_Countries.Min_Max_Age_By_Country_Driver.java
/** * @param args the command line arguments *//* w ww . j a v a 2 s . c o m*/ public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Min, Max, Average, Median age of users by country"); job.setJarByClass(Min_Max_Age_By_Country_Driver.class); job.setMapperClass(Min_Max_Age_By_Country_Mapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setReducerClass(Min_Max_Age_By_Country_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setNumReduceTasks(1); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }