List of usage examples for org.apache.hadoop.mapreduce Job setJarByClass
public void setJarByClass(Class<?> cls)
From source file:Assignment5_P3_PartitionPattern.Partition_IPAddress_By_MonthDriver.java
/** * @param args the command line arguments *//*from www.j ava2 s.c o m*/ public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "IP Address By Date"); job.setJarByClass(Partition_IPAddress_By_MonthDriver.class); job.setMapperClass(Partition_IPAddress_By_Month_Mapper.class); //job.setCombinerClass(Partition_IPAddress_By_Month_Reducer.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(Text.class); // partitioner class inclusion job.setPartitionerClass(Partition_IPAddress_By_Month_Partitioner.class); // set num of reduce tasks based on partition we need (here we need 12 cos total no.of months in a year) job.setNumReduceTasks(12); job.setReducerClass(Partition_IPAddress_By_Month_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.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:Assignment5_P4_BinningPattern.Binning_IPAddress_By_DayDriver.java
/** * @param args the command line arguments *//*from w w w . j a v a2s . c om*/ public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "IP Address By Hour"); job.setJarByClass(Binning_IPAddress_By_DayDriver.class); job.setMapperClass(Binning_IPAddress_By_Day_Mapper.class); job.setMapOutputKeyClass(NullWritable.class); job.setMapOutputValueClass(Text.class); MultipleOutputs.addNamedOutput(job, "textualBins", TextOutputFormat.class, NullWritable.class, Text.class); MultipleOutputs.addNamedOutput(job, "massaBins", TextOutputFormat.class, NullWritable.class, Text.class); MultipleOutputs.setCountersEnabled(job, true); // set num of reduce tasks to 0 job.setNumReduceTasks(0); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Assignment5_P6_StructureToHierarchyPattern.Structure_HierarchyDriver.java
/** * @param args the command line arguments *///from w w w .j a va2 s .c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Structure to Hierarchy"); job.setJarByClass(Structure_HierarchyDriver.class); // pass file 1 to this mapper in Text format MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, Structure_Hierarchy_Movie_Mapper.class); // pass file 2 to this mapper in Text format MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, Structure_Hierarchy_Tag_Mapper.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setReducerClass(Structure_Hierarchy_Reducer.class); FileOutputFormat.setOutputPath(job, new Path(args[2])); System.exit(job.waitForCompletion(true) ? 0 : 2); }
From source file:at.illecker.hama.rootbeer.examples.util.RandomGraphGenerator.java
License:Apache License
public static void main(String[] args) throws Exception { if (args.length != 4) { System.out.println(/*from ww w. ja v a 2s.co m*/ "USAGE: <Number of vertices> <Number of edges per vertex> <Number of partitions> <Outpath>"); return; } System.out.println(Arrays.toString(args)); Configuration conf = new Configuration(); conf.setInt("hama.num.vertices", Integer.parseInt(args[0])); conf.setInt("hama.num.partitions", Integer.parseInt(args[2])); conf.setInt("number.edges", Integer.parseInt(args[1])); Job job = new Job(conf); Path generated = new Path(new Path(args[3]).getParent(), "generated"); FileOutputFormat.setOutputPath(job, generated); FileSystem.get(conf).delete(generated, true); job.setJobName("RangeWriter"); job.setJarByClass(SortGenMapper.class); job.setMapperClass(SortGenMapper.class); job.setNumReduceTasks(0); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class); job.setInputFormatClass(RangeInputFormat.class); job.waitForCompletion(true); conf.setInt("max.id", Integer.valueOf(args[0])); job = new Job(conf); FileOutputFormat.setOutputPath(job, new Path(args[3])); FileSystem.get(conf).delete(new Path(args[3]), true); job.setJobName("Random Vertex Writer"); FileInputFormat.addInputPath(job, generated); job.setJarByClass(RandomMapper.class); job.setMapperClass(RandomMapper.class); job.setReducerClass(Reducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setNumReduceTasks(conf.getInt("hama.num.partitions", 2)); job.setPartitionerClass(HashPartitioner.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.waitForCompletion(true); }
From source file:AverageProj.AveragePrice.java
public int run(String[] args) throws Exception, ClassNotFoundException { Configuration conf = getConf(); Job job = new Job(conf, "Avg"); job.setJarByClass(AveragePrice.class); //final File f = new File(AveragePrice.class.getProtectionDomain().getCodeSource().getLocation().getPath()); Path in = new Path(args[0]); Path out = new Path(args[1]); FileInputFormat.setInputPaths(job, in); FileOutputFormat.setOutputPath(job, out); job.setMapperClass(AvMapper.class); job.setMapOutputKeyClass(YearPrice.class); job.setMapOutputValueClass(DoubleWritable.class); job.setGroupingComparatorClass(YearSymComparator.class); // job.setCombinerClass(AvReducer.class); job.setReducerClass(AvReducer.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(YearPrice.class); job.setOutputValueClass(DoubleWritable.class); job.setPartitionerClass(AvgPartitioner.class); job.setNumReduceTasks(7);/* w ww . j av a 2 s. c o m*/ System.exit(job.waitForCompletion(true) ? 0 : 1); return 0; }
From source file:averagerating_youtube.AverageRating_Youtube.java
/** * @param args the command line arguments *//*from w w w . ja v a2s . c o m*/ @Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); job.setJobName("AverageRating_Youtube"); job.setJarByClass(AverageRating_Youtube.class); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(AvgRating_CommCountMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(AverageRating_CommentCountTuple.class); job.setCombinerClass(AvgRating_CommCountCombiner.class); job.setReducerClass(AvgRating_CommCountReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(AverageRating_CommentCountTuple.class); boolean success = job.waitForCompletion(true); return success ? 0 : 1; }
From source file:avro.mr.MapReduceAvroWordCount.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: AvroWordCount <input path> <output path>"); return -1; }//from w w w. j a v a2 s. com Job job = Job.getInstance(getConf()); job.setJarByClass(MapReduceAvroWordCount.class); job.setJobName("wordcount"); // We call setOutputSchema first so we can override the configuration // parameters it sets AvroJob.setOutputKeySchema(job, Pair.getPairSchema(Schema.create(Type.STRING), Schema.create(Type.INT))); job.setOutputValueClass(NullWritable.class); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setInputFormatClass(TextInputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setSortComparatorClass(Text.Comparator.class); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true); return 0; }
From source file:avro.mr.MapReduceColorCount.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MapReduceColorCount <input path> <output path>"); return -1; }/*from w w w . jav a 2 s . co m*/ Job job = Job.getInstance(getConf()); job.setJarByClass(MapReduceColorCount.class); job.setJobName("Color Count"); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(AvroKeyInputFormat.class); job.setMapperClass(ColorCountMapper.class); AvroJob.setInputKeySchema(job, User.getClassSchema()); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(AvroKeyValueOutputFormat.class); job.setReducerClass(ColorCountReducer.class); AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING)); AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT)); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:avro.mr.MapReduceColorCountSeqFile.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MapReduceColorCount <input path> <output path>"); return -1; }// w w w . ja v a2s. c o m Job job = Job.getInstance(getConf()); job.setJarByClass(MapReduceColorCountSeqFile.class); job.setJobName("Color Count 2"); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(AvroSequenceFileInputFormat.class); AvroJob.setInputKeySchema(job, Schema.create(Schema.Type.LONG)); AvroJob.setInputValueSchema(job, User.getClassSchema()); job.setMapperClass(ColorCountMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(AvroSequenceFileOutputFormat.class); job.setReducerClass(ColorCountReducer.class); AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING)); AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT)); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:azkaban.jobtype.examples.java.WordCount2.java
License:Apache License
@Override public void run() throws Exception { logger.info(String.format("Starting %s", getClass().getSimpleName())); //getConf() and set Job job = createJob(MapperClass.class, ReducerClass.class); job.setJarByClass(WordCount2.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(inputPath)); super.run();// w w w . ja va2 s .co m }