List of usage examples for org.apache.hadoop.mapreduce Job setMapperClass
public void setMapperClass(Class<? extends Mapper> cls) throws IllegalStateException
From source file:com.cloudera.crunch.impl.mr.plan.JobPrototype.java
License:Open Source License
private CrunchJob build(Class<?> jarClass, Configuration conf) throws IOException { Job job = new Job(conf); conf = job.getConfiguration();/* w w w . j a v a2s.c om*/ job.setJarByClass(jarClass); Set<DoNode> outputNodes = Sets.newHashSet(); Set<Target> targets = targetsToNodePaths.keySet(); MSCROutputHandler outputHandler = new MSCROutputHandler(job, workingPath, group == null); for (Target target : targets) { DoNode node = null; for (NodePath nodePath : targetsToNodePaths.get(target)) { if (node == null) { PCollectionImpl collect = nodePath.tail(); node = DoNode.createOutputNode(target.toString(), collect.getPType()); outputHandler.configureNode(node, target); } outputNodes.add(walkPath(nodePath.descendingIterator(), node)); } } job.setMapperClass(CrunchMapper.class); List<DoNode> inputNodes; DoNode reduceNode = null; RTNodeSerializer serializer = new RTNodeSerializer(); if (group != null) { job.setReducerClass(CrunchReducer.class); List<DoNode> reduceNodes = Lists.newArrayList(outputNodes); reduceNode = reduceNodes.get(0); serializer.serialize(reduceNodes, conf, NodeContext.REDUCE); group.configureShuffle(job); DoNode mapOutputNode = group.getGroupingNode(); if (reduceNodes.size() == 1 && combineFnTable != null) { // Handle the combiner case DoNode mapSideCombineNode = combineFnTable.createDoNode(); mapSideCombineNode.addChild(mapOutputNode); mapOutputNode = mapSideCombineNode; } Set<DoNode> mapNodes = Sets.newHashSet(); for (NodePath nodePath : mapNodePaths) { // Advance these one step, since we've already configured // the grouping node, and the PGroupedTableImpl is the tail // of the NodePath. Iterator<PCollectionImpl> iter = nodePath.descendingIterator(); iter.next(); mapNodes.add(walkPath(iter, mapOutputNode)); } inputNodes = Lists.newArrayList(mapNodes); serializer.serialize(inputNodes, conf, NodeContext.MAP); } else { // No grouping job.setNumReduceTasks(0); inputNodes = Lists.newArrayList(outputNodes); serializer.serialize(inputNodes, conf, NodeContext.MAP); } if (inputNodes.size() == 1) { DoNode inputNode = inputNodes.get(0); inputNode.getSource().configureSource(job, -1); } else { for (int i = 0; i < inputNodes.size(); i++) { DoNode inputNode = inputNodes.get(i); inputNode.getSource().configureSource(job, i); } job.setInputFormatClass(CrunchInputFormat.class); } job.setJobName(createJobName(inputNodes, reduceNode)); return new CrunchJob(job, workingPath, outputHandler); }
From source file:com.cloudera.crunch.io.hbase.HBaseSourceTarget.java
License:Open Source License
@Override public void configureSource(Job job, int inputId) throws IOException { Configuration conf = job.getConfiguration(); job.setInputFormatClass(TableInputFormat.class); job.setMapperClass(CrunchMapper.class); HBaseConfiguration.addHbaseResources(conf); conf.set(TableInputFormat.INPUT_TABLE, table); conf.set(TableInputFormat.SCAN, convertScanToString(scan)); TableMapReduceUtil.addDependencyJars(job); }
From source file:com.cloudera.hbase.WordCount.java
License:Open Source License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: wordcount <in> <out>"); return 2; }//from w ww. j a va2 s . c o m Configuration conf = getConf(); Job job = new Job(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.avro.mapreduce.ColorCount.java
License:Apache License
/** * Run the MR2 color count with generic records, and return a map of favorite colors to * the number of users.//from w w w . ja va 2s .com */ public static java.util.Map<String, Integer> countColors() throws IOException, ClassNotFoundException, InterruptedException { String output = TestUtil.getTempDirectory(); Path outputPath = new Path(output); JobConf conf = new JobConf(ColorCount.class); conf.setInt("mapreduce.job.reduces", 1); Job job = Job.getInstance(conf); job.setJarByClass(ColorCount.class); job.setJobName("MR2 Color Count With Generic Records"); RecordServiceConfig.setInputTable(job.getConfiguration(), "rs", "users"); job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyInputFormat.class); FileOutputFormat.setOutputPath(job, outputPath); job.setMapperClass(Map.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(AvroKeyValueOutputFormat.class); job.setReducerClass(Reduce.class); AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING)); AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT)); job.waitForCompletion(false); // Read the result and return it. Since we set the number of reducers to 1, // there is always just one file containing the value. SeekableInput input = new FsInput(new Path(output + "/part-r-00000.avro"), conf); DatumReader<GenericRecord> reader = new GenericDatumReader<GenericRecord>(); FileReader<GenericRecord> fileReader = DataFileReader.openReader(input, reader); java.util.Map<String, Integer> colorMap = new HashMap<String, Integer>(); for (GenericRecord datum : fileReader) { colorMap.put(datum.get(0).toString(), Integer.parseInt(datum.get(1).toString())); } return colorMap; }
From source file:com.cloudera.recordservice.examples.mapreduce.MapReduceAgeCount.java
License:Apache License
public int run(String[] args) throws Exception { org.apache.log4j.BasicConfigurator.configure(); if (args.length != 2) { System.err.println("Usage: MapReduceAgeCount <input path> <output path>"); return -1; }/*from w w w .ja v a 2s.c om*/ Job job = Job.getInstance(getConf()); job.setJarByClass(MapReduceAgeCount.class); job.setJobName("Age Count"); // RECORDSERVICE: // To read from a table instead of a path, comment out // FileInputFormat.setInputPaths() and instead use: // FileInputFormat.setInputPaths(job, new Path(args[0])); RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); // RECORDSERVICE: // Use the RecordService version of the AvroKeyValueInputFormat job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyValueInputFormat.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(AgeCountMapper.class); // Set schema for input key and value. AvroJob.setInputKeySchema(job, UserKey.getClassSchema()); AvroJob.setInputValueSchema(job, UserValue.getClassSchema()); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(AvroKeyValueOutputFormat.class); job.setReducerClass(AgeCountReducer.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:com.cloudera.recordservice.examples.mapreduce.MapReduceColorCount.java
License:Apache License
@Override public int run(String[] args) throws Exception { org.apache.log4j.BasicConfigurator.configure(); if (args.length != 2) { System.err.println("Usage: MapReduceColorCount <input path> <output path>"); return -1; }//from w w w . j av a2s . c om Job job = Job.getInstance(getConf()); job.setJarByClass(MapReduceColorCount.class); job.setJobName("Color Count"); // RECORDSERVICE: // To read from a table instead of a path, comment out // FileInputFormat.setInputPaths() and instead use: //FileInputFormat.setInputPaths(job, new Path(args[0])); RecordServiceConfig.setInputTable(job.getConfiguration(), "rs", "users"); // RECORDSERVICE: // Use the RecordService version of the AvroKeyInputFormat job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyInputFormat.class); //job.setInputFormatClass(AvroKeyInputFormat.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); 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:com.cloudera.recordservice.examples.mapreduce.RecordCount.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: RecordCount <input_query> <output_path>"); System.exit(1);//from w ww .j a va2 s . c o m } String inputQuery = args[0]; String output = args[1]; Job job = Job.getInstance(getConf()); job.setJobName("recordcount"); job.setJarByClass(RecordCount.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setNumReduceTasks(1); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(LongWritable.class); RecordServiceConfig.setInputQuery(job.getConfiguration(), inputQuery); job.setInputFormatClass(RecordServiceInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileSystem fs = FileSystem.get(job.getConfiguration()); Path outputPath = new Path(output); if (fs.exists(outputPath)) fs.delete(outputPath, true); FileOutputFormat.setOutputPath(job, outputPath); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraChecksum.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; Job job = Job.getInstance(getConf()); if (args.length != 2 && args.length != 3) { usage();//from www. j a v a 2s . c o m return 2; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraSum"); job.setJarByClass(TeraChecksum.class); job.setMapperClass(ChecksumMapper.class); job.setReducerClass(ChecksumReducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Unsigned16.class); // force a single reducer job.setNumReduceTasks(1); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); } else { TeraInputFormat.setInputPaths(job, new Path(args[0])); job.setInputFormatClass(TeraInputFormat.class); } return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraGen.java
License:Apache License
/** * @param args the cli arguments/*from www . ja v a2 s .c om*/ */ @Override public int run(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Job job = Job.getInstance(getConf()); if (args.length != 2) { usage(); return 2; } setNumberOfRows(job, parseHumanLong(args[0])); Path outputDir = new Path(args[1]); if (outputDir.getFileSystem(getConf()).exists(outputDir)) { throw new IOException("Output directory " + outputDir + " already exists."); } FileOutputFormat.setOutputPath(job, outputDir); job.setJobName("TeraGen"); job.setJarByClass(TeraGen.class); job.setMapperClass(SortGenMapper.class); job.setNumReduceTasks(0); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(RangeInputFormat.class); job.setOutputFormatClass(TeraOutputFormat.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraValidate.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; if (args.length != 2 && args.length != 3) { usage();/*from w w w . java 2 s . com*/ return 1; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } Job job = Job.getInstance(getConf()); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraValidate"); job.setJarByClass(TeraValidate.class); job.setMapperClass(ValidateMapper.class); job.setReducerClass(ValidateReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // force a single reducer job.setNumReduceTasks(1); // force a single split FileInputFormat.setMinInputSplitSize(job, Long.MAX_VALUE); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); } else { TeraInputFormat.setInputPaths(job, new Path(args[0])); job.setInputFormatClass(TeraInputFormat.class); } return job.waitForCompletion(true) ? 0 : 1; }