List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass
public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException
From source file:ca.uwaterloo.iss4e.hadoop.pointperrow.CosineMain.java
License:Open Source License
public int run(String[] args) throws IOException { Configuration conf = getConf(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: ca.uwaterloo.iss4e.hadoop.pointperrow.ConsineMain <input> <output>"); System.exit(2);//ww w . j a v a 2 s . co m } Job job1 = new Job(conf, "ConsineMain"); job1.setJarByClass(CosineMain.class); job1.setMapperClass(AggregateReadingsMapper.class); job1.setMapOutputKeyClass(LongWritable.class); job1.setMapOutputValueClass(DoubleWritable.class); job1.setReducerClass(AggregateReadingsReducer.class); job1.setOutputKeyClass(LongWritable.class); job1.setOutputValueClass(Text.class); FileInputFormat.setInputDirRecursive(job1, true); FileInputFormat.setInputPaths(job1, new Path(otherArgs[0])); int lastIdx = otherArgs[0].lastIndexOf("/"); String tempOutput = otherArgs[0].substring(0, lastIdx) + "/temp"; FileOutputFormat.setOutputPath(job1, new Path(tempOutput)); System.out.println("\nStarting Job-1 ..."); final long startTime = System.currentTimeMillis(); try { final long startTimeJob1 = System.currentTimeMillis(); if (!job1.waitForCompletion(true)) { System.out.println("Job-1 failed."); } else { System.out.println("Duration of Job1 " + ((System.currentTimeMillis() - startTimeJob1) / 1000.0) + " seconds."); final Job job2 = new Job(conf, "ConsineMain Aggregate"); job2.setJarByClass(CosineMain.class); job2.setInputFormatClass(CartesianInputFormat.class); CartesianInputFormat.setLeftInputInfo(job2, TextInputFormat.class, tempOutput); CartesianInputFormat.setRightInputInfo(job2, TextInputFormat.class, tempOutput); FileOutputFormat.setOutputPath(job2, new Path(otherArgs[1])); job2.setMapperClass(CartesianProductMapper.class); job2.setMapOutputKeyClass(DoubleWritable.class); job2.setMapOutputValueClass(Text.class); job2.setSortComparatorClass(DescendingKeyComparator.class); job2.setReducerClass(CartesianProductReducer.class); job2.setOutputKeyClass(Text.class); job2.setOutputValueClass(DoubleWritable.class); job2.setNumReduceTasks(10); final long startTimeJob2 = System.currentTimeMillis(); System.out.println("\nStarting Job-2 ..."); if (!job2.waitForCompletion(true)) { System.out.println("Job-2 failed."); } else { System.out.println("Duration of Job2: " + ((System.currentTimeMillis() - startTimeJob2) / 1000.0) + " seconds."); } } FileSystem fs = FileSystem.get(conf); fs.delete(new Path(tempOutput), true); } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Total Duration: " + duration + " seconds."); } return 0; }
From source file:ca.uwaterloo.iss4e.hadoop.pointperrow.CosineMain.java
License:Open Source License
public int run1(String[] args) throws IOException { if (args.length != 3) { System.err.println("Usage: java " + getClass().getName() + " <inputDir> <outDir> <ntasks>"); ToolRunner.printGenericCommandUsage(System.err); return -1; }// w w w . j a v a 2 s . c o m Configuration conf = getConf(); final Job job2 = new Job(conf, "ConsineMain cartesian product"); job2.setJarByClass(CosineMain.class); job2.setInputFormatClass(CartesianInputFormat.class); CartesianInputFormat.setLeftInputInfo(job2, TextInputFormat.class, args[0]); CartesianInputFormat.setRightInputInfo(job2, TextInputFormat.class, args[0]); FileOutputFormat.setOutputPath(job2, new Path(args[1])); job2.setMapperClass(CartesianProductMapper.class); job2.setMapOutputKeyClass(DoubleWritable.class); job2.setMapOutputValueClass(Text.class); job2.setSortComparatorClass(DescendingKeyComparator.class); job2.setReducerClass(CartesianProductReducer.class); job2.setOutputKeyClass(Text.class); job2.setOutputValueClass(DoubleWritable.class); job2.setNumReduceTasks(Integer.parseInt(args[2])); System.out.println("\nStarting Job-2 ..."); final long startTime = System.currentTimeMillis(); try { if (!job2.waitForCompletion(true)) { System.out.println("Job-2 failed."); System.exit(1); } } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Duration is " + duration + " seconds."); } return 0; }
From source file:cascading.flow.hadoop.MapReduceFlowPlatformTest.java
License:Open Source License
@Test public void testCascade() throws IOException { getPlatform().copyFromLocal(inputFileApache); // Setup two standard cascading flows that will generate the input for the first MapReduceFlow Tap source1 = new Hfs(new TextLine(new Fields("offset", "line")), remove(inputFileApache, false)); String sinkPath4 = getOutputPath("flow4"); Tap sink1 = new Hfs(new TextLine(new Fields("offset", "line")), remove(sinkPath4, true), SinkMode.REPLACE); Flow firstFlow = getPlatform().getFlowConnector(getProperties()).connect(source1, sink1, new Pipe("first-flow")); String sinkPath5 = getOutputPath("flow5"); Tap sink2 = new Hfs(new TextLine(new Fields("offset", "line")), remove(sinkPath5, true), SinkMode.REPLACE); Flow secondFlow = getPlatform().getFlowConnector(getProperties()).connect(sink1, sink2, new Pipe("second-flow")); JobConf defaultConf = HadoopPlanner.createJobConf(getProperties()); JobConf firstConf = new JobConf(defaultConf); firstConf.setJobName("first-mr"); firstConf.setOutputKeyClass(LongWritable.class); firstConf.setOutputValueClass(Text.class); firstConf.setMapperClass(IdentityMapper.class); firstConf.setReducerClass(IdentityReducer.class); firstConf.setInputFormat(TextInputFormat.class); firstConf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(firstConf, new Path(remove(sinkPath5, true))); String sinkPath1 = getOutputPath("flow1"); FileOutputFormat.setOutputPath(firstConf, new Path(remove(sinkPath1, true))); Flow firstMR = new MapReduceFlow(firstConf, true); JobConf secondConf = new JobConf(defaultConf); secondConf.setJobName("second-mr"); secondConf.setOutputKeyClass(LongWritable.class); secondConf.setOutputValueClass(Text.class); secondConf.setMapperClass(IdentityMapper.class); secondConf.setReducerClass(IdentityReducer.class); secondConf.setInputFormat(TextInputFormat.class); secondConf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(secondConf, new Path(remove(sinkPath1, true))); String sinkPath2 = getOutputPath("flow2"); FileOutputFormat.setOutputPath(secondConf, new Path(remove(sinkPath2, true))); Flow secondMR = new MapReduceFlow(secondConf, true); Job job = new Job(defaultConf); job.setJobName("third-mr"); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); job.setMapperClass(org.apache.hadoop.mapreduce.Mapper.class); job.setReducerClass(org.apache.hadoop.mapreduce.Reducer.class); job.setInputFormatClass(org.apache.hadoop.mapreduce.lib.input.TextInputFormat.class); job.setOutputFormatClass(org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.class); job.getConfiguration().set("mapred.mapper.new-api", "true"); job.getConfiguration().set("mapred.reducer.new-api", "true"); org.apache.hadoop.mapreduce.lib.input.FileInputFormat.addInputPath(job, new Path(remove(sinkPath2, true))); String sinkPath3 = getOutputPath("flow3"); org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.setOutputPath(job, new Path(remove(sinkPath3, true))); Flow thirdMR = new MapReduceFlow(new JobConf(job.getConfiguration()), true); CascadeConnector cascadeConnector = new CascadeConnector(); // pass out of order Cascade cascade = cascadeConnector.connect(firstFlow, secondFlow, thirdMR, firstMR, secondMR); cascade.complete();/* ww w .ja v a 2s . c o m*/ validateLength(new Hfs(new TextLine(), sinkPath3).openForRead(new HadoopFlowProcess(defaultConf)), 10); }
From source file:cassandra_mapreduce.MapReduceCassandraDB.java
License:GNU General Public License
public int run(String[] args) throws Exception { String columnName = "value"; getConf().set(CONF_COLUMN_NAME, columnName); getConf().set("mapred.job.tracker", args[0] + ":8021"); Job job = new Job(getConf(), "Phase1"); job.setJarByClass(MapReduceCassandraDB.class); job.setMapperClass(TokenizerMapper.class); job.setReducerClass(ReducerToCassandra.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(ByteBuffer.class); job.setOutputValueClass(List.class); job.setInputFormatClass(ColumnFamilyInputFormat.class); job.setOutputFormatClass(ColumnFamilyOutputFormat.class); ConfigHelper.setRangeBatchSize(job.getConfiguration(), 800); ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY); ConfigHelper.setRpcPort(job.getConfiguration(), "9160"); ConfigHelper.setInitialAddress(job.getConfiguration(), args[0]); ConfigHelper.setPartitioner(job.getConfiguration(), "org.apache.cassandra.dht.RandomPartitioner"); ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY); SlicePredicate predicate = new SlicePredicate() .setColumn_names(Arrays.asList(ByteBuffer.wrap(columnName.getBytes()))); ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate); job.waitForCompletion(true);/*w ww . ja v a 2 s . c o m*/ //Phase 2 Job job2 = new Job(getConf(), "Phase2"); job2.setJarByClass(MapReduceCassandraDB.class); job2.setMapperClass(Mapper2.class); job2.setReducerClass(Reducer2.class); job2.setMapOutputKeyClass(Text.class); job2.setMapOutputValueClass(IntWritable.class); job2.setOutputKeyClass(ByteBuffer.class); job2.setOutputValueClass(List.class); job2.setInputFormatClass(ColumnFamilyInputFormat.class); job2.setOutputFormatClass(ColumnFamilyOutputFormat.class); ConfigHelper.setOutputColumnFamily(job2.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY2); ConfigHelper.setRpcPort(job2.getConfiguration(), "9160"); ConfigHelper.setInitialAddress(job2.getConfiguration(), args[0]); ConfigHelper.setPartitioner(job2.getConfiguration(), "org.apache.cassandra.dht.RandomPartitioner"); ConfigHelper.setInputColumnFamily(job2.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY); SlicePredicate predicate2 = new SlicePredicate() .setColumn_names(Arrays.asList(ByteBuffer.wrap(columnName.getBytes()))); ConfigHelper.setInputSlicePredicate(job2.getConfiguration(), predicate2); job2.waitForCompletion(true); // job.setCombinerClass(IntSumReducer.class); // job.setReducerClass(IntSumReducer.class); // job.setOutputKeyClass(Text.class); // job.setOutputValueClass(Text.class); // // job.setInputFormatClass(ColumnFamilyInputFormat.class); // FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX)); // // ConfigHelper.setRpcPort(job.getConfiguration(), "9160"); // ConfigHelper.setInitialAddress(job.getConfiguration(), args[0]); // ConfigHelper.setPartitioner(job.getConfiguration(), "org.apache.cassandra.dht.RandomPartitioner"); // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY); // SlicePredicate predicate = new SlicePredicate().setColumn_names(Arrays.asList(ByteBuffer.wrap(columnName.getBytes()))); // ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate); // // job.waitForCompletion(true); return 0; }
From source file:cc.slda.AnnotateDocuments.java
License:Apache License
/** * Runs this tool.//from www. j a v a2s . co m */ @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("number of reducers") .create(NUM_REDUCERS)); options.addOption(OptionBuilder.withArgName(PCUTOFF).hasArg() .withDescription("probability of topic assignment").create(PCUTOFF)); options.addOption(OptionBuilder.withArgName(INDEX).hasArg() .withDescription("path to data directory containing term and title indices").create(INDEX)); 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) || !cmdline.hasOption(INDEX)) { 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 indexPath = cmdline.getOptionValue(INDEX); String inputPath = cmdline.getOptionValue(INPUT); String outputPath = cmdline.getOptionValue(OUTPUT); int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1; float cutoff = 0.9f; if (cmdline.hasOption(PCUTOFF)) { cutoff = Float.parseFloat(cmdline.getOptionValue(PCUTOFF)); } LOG.info("Tool: " + AnnotateDocuments.class.getSimpleName()); LOG.info(" - indices path: " + indexPath); LOG.info(" - input path: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - number of reducers: " + reduceTasks); LOG.info(" - log(probCutoff): " + Math.log(cutoff)); Configuration conf = getConf(); FileSystem fs = FileSystem.get(conf); Job job = Job.getInstance(conf); job.setJobName(AnnotateDocuments.class.getSimpleName()); job.setJarByClass(AnnotateDocuments.class); String termIndex = indexPath + Path.SEPARATOR + TERM; String titleIndex = indexPath + Path.SEPARATOR + TITLE; Path termIndexPath = new Path(termIndex); Path titleIndexPath = new Path(titleIndex); Preconditions.checkArgument(fs.exists(termIndexPath), "Missing term index files... " + termIndexPath); DistributedCache.addCacheFile(termIndexPath.toUri(), job.getConfiguration()); Preconditions.checkArgument(fs.exists(titleIndexPath), "Missing title index files... " + titleIndexPath); DistributedCache.addCacheFile(titleIndexPath.toUri(), job.getConfiguration()); job.setNumReduceTasks(reduceTasks); conf.setFloat(PCUTOFF, cutoff); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(HMapSIW.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(HMapSIW.class); job.setMapperClass(MyMapper.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:cgl.hadoop.apps.runner.DataAnalysis.java
License:Open Source License
/** * Launch the MapReduce computation./*from www . j av a2 s.com*/ * This method first, remove any previous working directories and create a new one * Then the data (file names) is copied to this new directory and launch the * MapReduce (map-only though) computation. * @param numMapTasks - Number of map tasks. * @param numReduceTasks - Number of reduce tasks =0. * @param programDir - The directory where the Cap3 program is. * @param execName - Name of the executable. * @param dataDir - Directory where the data is located. * @param outputDir - Output directory to place the output. * @param cmdArgs - These are the command line arguments to the Cap3 program. * @throws Exception - Throws any exception occurs in this program. */ void launch(int numReduceTasks, String programDir, String execName, String workingDir, String databaseArchive, String databaseName, String dataDir, String outputDir, String cmdArgs) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, execName); // First get the file system handler, delete any previous files, add the // files and write the data to it, then pass its name as a parameter to // job Path hdMainDir = new Path(outputDir); FileSystem fs = FileSystem.get(conf); fs.delete(hdMainDir, true); Path hdOutDir = new Path(hdMainDir, "out"); // Starting the data analysis. Configuration jc = job.getConfiguration(); jc.set(WORKING_DIR, workingDir); jc.set(EXECUTABLE, execName); jc.set(PROGRAM_DIR, programDir); // this the name of the executable archive jc.set(DB_ARCHIVE, databaseArchive); jc.set(DB_NAME, databaseName); jc.set(PARAMETERS, cmdArgs); jc.set(OUTPUT_DIR, outputDir); // using distributed cache // flush it //DistributedCache.releaseCache(new URI(programDir), jc); //DistributedCache.releaseCache(new URI(databaseArchive), jc); //DistributedCache.purgeCache(jc); // reput the data into cache long startTime = System.currentTimeMillis(); //DistributedCache.addCacheArchive(new URI(databaseArchive), jc); DistributedCache.addCacheArchive(new URI(programDir), jc); System.out.println( "Add Distributed Cache in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); FileInputFormat.setInputPaths(job, dataDir); FileOutputFormat.setOutputPath(job, hdOutDir); job.setJarByClass(DataAnalysis.class); job.setMapperClass(RunnerMap.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(DataFileInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setNumReduceTasks(numReduceTasks); startTime = System.currentTimeMillis(); int exitStatus = job.waitForCompletion(true) ? 0 : 1; System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); //clean the cache System.exit(exitStatus); }
From source file:chaohBIM.BIMGetIndex.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 w w. j ava2s .c om } Job job = new Job(conf, "getTfidf"); job.setJarByClass(BIMGetIndex.class); job.setMapperClass(tfidfMapper.class); job.setCombinerClass(tfidfCombiner.class); job.setReducerClass(tfidfdReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(ZipFileInputFormat.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:chaohParse.huangWordCount.java
License:Open Source 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 w w. ja v a 2 s .c o m*/ } Job job = new Job(conf, "word count"); job.setJarByClass(huangWordCount.class); job.setMapperClass(WordMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setCombinerClass(WordCombiner.class); job.setReducerClass(WordReducer.class); job.setInputFormatClass(ZipFileInputFormat.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:chaohParse.searchWord.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 w w . ja v a 2s. c om*/ } Job job = new Job(conf, "word count"); job.setJarByClass(wordcount.class); job.setMapperClass(TokenizerMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Integer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(FileInputFormat.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:chaohParse.uniword.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 va 2s . c om } Job job = new Job(conf, "word count"); job.setJarByClass(uniword.class); job.setMapperClass(TokenizerMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); //job.setCombinerClass(myUniwordCombiner.class); job.setReducerClass(myUniwordReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(ZipFileInputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }