List of usage examples for org.apache.hadoop.mapreduce Job setOutputKeyClass
public void setOutputKeyClass(Class<?> theClass) throws IllegalStateException
From source file:LinkedGraph.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2);// ww w.j a v a 2 s. c o m } Job job = new Job(conf, "Graph"); job.setJarByClass(LinkedGraph.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:MarkovStateTransitionModel.java
License:Apache License
@Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); String jobName = "Markov tate transition model"; job.setJobName(jobName);/*from w w w. j av a2s . c o m*/ job.setJarByClass(MarkovStateTransitionModel.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); Utility.setConfiguration(job.getConfiguration(), "avenir"); job.setMapperClass(MarkovStateTransitionModel.StateTransitionMapper.class); job.setReducerClass(MarkovStateTransitionModel.StateTransitionReducer.class); job.setCombinerClass(MarkovStateTransitionModel.StateTransitionCombiner.class); job.setMapOutputKeyClass(Tuple.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); job.setNumReduceTasks(job.getConfiguration().getInt("num.reducer", 1)); int status = job.waitForCompletion(true) ? 0 : 1; return status; }
From source file:DescSorter.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length < 2) { System.err.println("Usage: flights <in> <in> <out>"); System.exit(2);/*from w ww . j av a 2 s .c o m*/ } Job job = new Job(conf, "AvgDelays"); job.setJarByClass(DescSorter.class); job.setMapperClass(FlightMapper.class); job.setMapOutputKeyClass(CompositeKey.class); job.setMapOutputValueClass(IntWritable.class); job.setPartitionerClass(CompositeKeyPartitioner.class); job.setSortComparatorClass(SortComparator.class); job.setGroupingComparatorClass(GroupingComparator.class); job.setReducerClass(AvgDelayReducer.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(Text.class); for (int i = 0; i < otherArgs.length - 1; ++i) { FileInputFormat.addInputPath(job, new Path(otherArgs[i])); } FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:MaleUsersBelow7Years.java
public static void main(String args[]) throws Exception { Configuration configuration = new Configuration(); Job job = new Job(configuration, "CountMaleUsersLessThan7"); job.setJarByClass(MaleUsersBelow7Years.class); job.setMapperClass(Map.class); job.setReducerClass(Reducer.class); job.setCombinerClass(Reducer.class); //set output and input formats;mapper-input reducer-output job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); //path for input file FileOutputFormat.setOutputPath(job, new Path(args[1])); // Path for output file System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:PrimeDivisor.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2);/*from w ww. j a v a 2 s .c o m*/ } Job job = new Job(conf, "word count"); job.setJarByClass(PrimeDivisor.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:WordCount.java
License:Apache License
public int run(String[] args) throws Exception { ///start//from ww w.ja v a 2 s . c o m final long startTime = System.currentTimeMillis(); String outputReducerType = "filesystem"; if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) { String[] s = args[0].split("="); if (s != null && s.length == 2) outputReducerType = s[1]; } logger.info("output reducer type: " + outputReducerType); // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better ConfigHelper.setRangeBatchSize(getConf(), 99); for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) { String columnName = "userId"; Job job = new Job(getConf(), "wordcount"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); if (outputReducerType.equalsIgnoreCase("filesystem")) { job.setReducerClass(ReducerToFilesystem.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i)); } else { job.setReducerClass(ReducerToCassandra.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(ByteBuffer.class); job.setOutputValueClass(List.class); job.setOutputFormatClass(ColumnFamilyOutputFormat.class); ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY); job.getConfiguration().set(CONF_COLUMN_NAME, "sum"); } job.setInputFormatClass(ColumnFamilyInputFormat.class); ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160"); ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost"); ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner"); ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY); SlicePredicate predicate = new SlicePredicate() .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName))); ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate); // this will cause the predicate to be ignored in favor of scanning everything as a wide row //Son degisiklik // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true); //System.out.println("tessssssaaat"); ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost"); ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner"); job.waitForCompletion(true); } //print final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after System.out.println(); System.out.println("Job Finished in " + duration + " seconds"); System.out.println(); return 0; }
From source file:ComputeCooccurrenceMatrixPairs.java
License:Apache License
/** * Runs this tool./*from ww w. java 2s. c om*/ */ @SuppressWarnings({ "static-access" }) public int run(String[] args) throws Exception { Options options = new Options(); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT)); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("window size").create(WINDOW)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers") .create(NUM_REDUCERS)); CommandLine cmdline; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); return -1; } if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) { System.out.println("args: " + Arrays.toString(args)); HelpFormatter formatter = new HelpFormatter(); formatter.setWidth(120); formatter.printHelp(this.getClass().getName(), options); ToolRunner.printGenericCommandUsage(System.out); return -1; } String inputPath = cmdline.getOptionValue(INPUT); String outputPath = cmdline.getOptionValue(OUTPUT); int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1; int window = cmdline.hasOption(WINDOW) ? Integer.parseInt(cmdline.getOptionValue(WINDOW)) : 2; LOG.info("Tool: " + ComputeCooccurrenceMatrixPairs.class.getSimpleName()); LOG.info(" - input path: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - window: " + window); LOG.info(" - number of reducers: " + reduceTasks); Job job = Job.getInstance(getConf()); job.setJobName(ComputeCooccurrenceMatrixPairs.class.getSimpleName()); job.setJarByClass(ComputeCooccurrenceMatrixPairs.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(getConf()).delete(outputDir, true); job.getConfiguration().setInt("window", window); job.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setMapOutputKeyClass(PairOfStrings.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(PairOfStrings.class); job.setOutputValueClass(IntWritable.class); job.setMapperClass(MyMapper.class); job.setCombinerClass(MyReducer.class); job.setReducerClass(MyReducer.class); job.setPartitionerClass(MyPartitioner.class); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:Inlinks.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length < 2) { System.err.println("Usage: inlinks <in> [<in>...] <out>"); System.exit(2);// w w w .j a va2s . c o m } Job job = new Job(conf, "inlinks"); job.setJarByClass(Inlinks.class); job.setMapperClass(TokenizerMapper.class); //job.setCombinerClass(IdentityReducer.class); job.setReducerClass(IdentityReducer.class); job.setNumReduceTasks(10); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(IntWritable.class); for (int i = 0; i < otherArgs.length - 1; ++i) { FileInputFormat.addInputPath(job, new Path(otherArgs[i])); } FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:WordCount.java
License:Apache License
public int run(String[] args) throws Exception { ///start// w ww . j a va 2 s . com final long startTime = System.currentTimeMillis(); String outputReducerType = "filesystem"; if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) { String[] s = args[0].split("="); if (s != null && s.length == 2) outputReducerType = s[1]; } logger.info("output reducer type: " + outputReducerType); // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better ConfigHelper.setRangeBatchSize(getConf(), 99); for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) { String columnName = "userId"; Job job = new Job(getConf(), "wordcount"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); if (outputReducerType.equalsIgnoreCase("filesystem")) { job.setReducerClass(ReducerToFilesystem.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i)); } else { job.setReducerClass(ReducerToCassandra.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(ByteBuffer.class); job.setOutputValueClass(List.class); job.setOutputFormatClass(ColumnFamilyOutputFormat.class); ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY); job.getConfiguration().set(CONF_COLUMN_NAME, "sum"); } job.setInputFormatClass(ColumnFamilyInputFormat.class); ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160"); ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost"); ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner"); ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY); SlicePredicate predicate = new SlicePredicate() .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName))); ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate); // this will cause the predicate to be ignored in favor of scanning everything as a wide row //Son degisiklik // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true); //System.out.println("tessssssaaat"); ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost"); ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner"); job.waitForCompletion(true); } //print final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after System.out.println(); System.out.println("Job Finished in " + duration + " seconds"); System.out.println(); return 0; }
From source file:TopFiveAverageMoviesRatedByFemales.java
public static void main(String[] args) throws Exception { JobConf conf1 = new JobConf(); Job job1 = new Job(conf1, "TopFiveAverageMoviesRatedByFemales"); org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job1, new Path(args[0]), TextInputFormat.class, TopFiveAverageMoviesRatedByFemales.MapRatings.class); org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job1, new Path(args[1]), TextInputFormat.class, TopFiveAverageMoviesRatedByFemales.MapGender.class); job1.setReducerClass(TopFiveAverageMoviesRatedByFemales.ReduceToMovieIdAndRatings.class); job1.setMapOutputKeyClass(Text.class); job1.setMapOutputValueClass(Text.class); job1.setOutputKeyClass(Text.class); job1.setOutputValueClass(Text.class); job1.setJarByClass(TopFiveAverageMoviesRatedByFemales.class); job1.setOutputFormatClass(TextOutputFormat.class); FileOutputFormat.setOutputPath(job1, new Path(args[3])); boolean flag = job1.waitForCompletion(true); boolean flag1 = false; boolean flag2 = false; if (flag) {/*from www . j a v a 2 s .co m*/ JobConf conf2 = new JobConf(); Job job2 = new Job(conf2, "AverageCalculation"); //org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job2, new Path(args[2]), TextInputFormat.class, Map2_1.class); //org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job2, new Path(args[3]), TextInputFormat.class, Map2_2.class); job2.setMapperClass(MapAverage.class); job2.setReducerClass(ReduceAverage.class); job2.setMapOutputKeyClass(Text.class); job2.setMapOutputValueClass(Text.class); job2.setOutputKeyClass(Text.class); job2.setOutputValueClass(Text.class); job2.setJarByClass(TopFiveAverageMoviesRatedByFemales.class); job2.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job2, new Path(args[3])); FileOutputFormat.setOutputPath(job2, new Path(args[4])); flag1 = job2.waitForCompletion(true); } if (flag1) { JobConf conf3 = new JobConf(); Job job3 = new Job(conf3, "AverageCalculation"); org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job3, new Path(args[4]), TextInputFormat.class, MapAverageTop5.class); org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job3, new Path(args[2]), TextInputFormat.class, MapMovieName.class); //job3.setMapperClass(MapAverageTop5.class); job3.setReducerClass(ReduceAverageTop5.class); job3.setMapOutputKeyClass(Text.class); job3.setMapOutputValueClass(Text.class); job3.setOutputKeyClass(Text.class); job3.setOutputValueClass(Text.class); job3.setJarByClass(TopFiveAverageMoviesRatedByFemales.class); job3.setOutputFormatClass(TextOutputFormat.class); //FileInputFormat.addInputPath(job3, new Path(args[4])); FileOutputFormat.setOutputPath(job3, new Path(args[5])); flag2 = job3.waitForCompletion(true); } }