List of usage examples for org.apache.hadoop.conf Configuration set
public void set(String name, String value)
value
of the name
property. From source file:com.cg.mapreduce.fpgrowth.mahout.fpm.PFPGrowth.java
License:Apache License
/** * Count the frequencies of various features in parallel using Map/Reduce *///from ww w . j a v a 2 s . c om public static void startParallelCounting(Parameters params, Configuration conf) throws IOException, InterruptedException, ClassNotFoundException { conf.set(PFP_PARAMETERS, params.toString()); conf.set("mapred.compress.map.output", "true"); conf.set("mapred.output.compression.type", "BLOCK"); String input = params.get(INPUT); Job job = new Job(conf, "Parallel Counting Driver running over input: " + input); job.setJarByClass(PFPGrowth.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.addInputPath(job, new Path(input)); Path outPath = new Path(params.get(OUTPUT), PARALLEL_COUNTING); FileOutputFormat.setOutputPath(job, outPath); HadoopUtil.delete(conf, outPath); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(ParallelCountingMapper.class); job.setCombinerClass(ParallelCountingReducer.class); job.setReducerClass(ParallelCountingReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); boolean succeeded = job.waitForCompletion(true); if (!succeeded) { throw new IllegalStateException("Job failed!"); } }
From source file:com.cg.mapreduce.fpgrowth.mahout.fpm.PFPGrowth.java
License:Apache License
/** * Run the Parallel FPGrowth Map/Reduce Job to calculate the Top K features of group dependent shards *//*from w w w . j av a 2 s . c om*/ public static void startParallelFPGrowth(Parameters params, Configuration conf) throws IOException, InterruptedException, ClassNotFoundException { conf.set(PFP_PARAMETERS, params.toString()); conf.set("mapred.compress.map.output", "true"); conf.set("mapred.output.compression.type", "BLOCK"); Path input = new Path(params.get(INPUT)); Job job = new Job(conf, "PFP Growth Driver running over input" + input); job.setJarByClass(PFPGrowth.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(TransactionTree.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(TopKStringPatterns.class); FileInputFormat.addInputPath(job, input); Path outPath = new Path(params.get(OUTPUT), FPGROWTH); FileOutputFormat.setOutputPath(job, outPath); HadoopUtil.delete(conf, outPath); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(ParallelFPGrowthMapper.class); job.setCombinerClass(ParallelFPGrowthCombiner.class); job.setReducerClass(ParallelFPGrowthReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); boolean succeeded = job.waitForCompletion(true); if (!succeeded) { throw new IllegalStateException("Job failed!"); } }
From source file:com.cg.mapreduce.myfpgrowth.PFPGrowth.java
License:Apache License
/** * @throws ClassNotFoundException /* w w w . j a v a 2s . c o m*/ * @throws InterruptedException * @throws IOException * @params * input, output locations, additional parameters like minSupport(3), maxHeapSize(50), numGroups(1000) * @conf * initial Hadoop configuration to use. * * */ public static void runPFPGrowth(Parameters params) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); startParallelCounting(params, conf); genGroupList(params, conf); startParallelFPGrowth(params, conf); }
From source file:com.cg.mapreduce.myfpgrowth.PFPGrowth.java
License:Apache License
/** * Count the frequencies of various features in parallel using Map/Reduce *//*from w w w . j av a 2 s . c o m*/ public static void startParallelCounting(Parameters params, Configuration conf) throws IOException, InterruptedException, ClassNotFoundException { conf.set(PFP_PARAMETERS, params.toString()); conf.set("mapred.compress.map.output", "true"); conf.set("mapred.output.compression.type", "BLOCK"); String input = params.get(INPUT); Job job = new Job(conf, "Parallel Counting Driver running over input: " + input); job.setJarByClass(PFPGrowth.class); // Job job = initJob(conf); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.addInputPath(job, new Path(input)); Path outPath = new Path(params.get(OUTPUT), PARALLEL_COUNTING); FileOutputFormat.setOutputPath(job, outPath); HadoopUtil.delete(conf, outPath); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(ParallelCountingMapper.class); job.setCombinerClass(ParallelCountingReducer.class); job.setReducerClass(ParallelCountingReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); boolean succeeded = job.waitForCompletion(true); if (!succeeded) { throw new IllegalStateException("Job failed!"); } }
From source file:com.cg.mapreduce.myfpgrowth.PFPGrowth.java
License:Apache License
/** * Run the Parallel FPGrowth Map/Reduce Job to calculate the Top K features of group dependent shards */// w w w. j a va 2 s.co m public static void startParallelFPGrowth(Parameters params, Configuration conf) throws IOException, InterruptedException, ClassNotFoundException { conf.set(PFP_PARAMETERS, params.toString()); conf.set("mapred.compress.map.output", "true"); conf.set("mapred.output.compression.type", "BLOCK"); Path input = new Path(params.get(INPUT)); Job job = new Job(conf, "PFP Growth Driver running over input" + input); job.setJarByClass(PFPGrowth.class); // Job job = initJob(conf); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(ArrayList.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.addInputPath(job, input); Path outPath = new Path(params.get(OUTPUT), FPGROWTH); FileOutputFormat.setOutputPath(job, outPath); HadoopUtil.delete(conf, outPath); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(ParallelFPGrowthMapper.class); //job.setCombinerClass(ParallelFPGrowthCombiner.class); job.setReducerClass(ParallelFPGrowthReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); boolean succeeded = job.waitForCompletion(true); if (!succeeded) { throw new IllegalStateException("Job failed!"); } }
From source file:com.cg.mapreduce.myfpgrowth.PFPGrowth.java
License:Apache License
private static Job initJob(Configuration conf) { conf.addResource(new Path("D:/program/hadoop-2.6.0/etc/hadoop/core-site.xml")); conf.addResource(new Path("D:/program/hadoop-2.6.0/etc/hadoop/hdfs-default.xml")); conf.addResource(new Path("D:/program/hadoop-2.6.0/etc/hadoop/hdfs-site.xml")); conf.addResource(new Path("D:/program/hadoop-2.6.0/etc/hadoop/yarn-default.xml")); conf.addResource(new Path("D:/program/hadoop-2.6.0/etc/hadoop/yarn-site.xml")); conf.addResource(new Path("D:/program/hadoop-2.6.0/etc/hadoop/mapred-site.xml")); conf.set("HADOOP_USER_NAME", "hadoop"); conf.set("mapred.reduce.tasks", "3"); Job job = null;//from w w w.j a v a 2 s . com try { File jarFile = EJob.createTempJar("bin"); EJob.addClasspath("D:/program/hadoop-2.6.0/etc/hadoop/"); ClassLoader classLoader = EJob.getClassLoader(); Thread.currentThread().setContextClassLoader(classLoader); job = new Job(conf, "PFP"); ((JobConf) job.getConfiguration()).setJar(jarFile.toString()); } catch (IOException e) { e.printStackTrace(); } return job; }
From source file:com.checkup.tez.test.DriverTest.java
public static Configuration getTezDecoratedConfiguration() { Configuration configuration = new Configuration(); configuration.set(MRConfig.FRAMEWORK_NAME, MRConfig.YARN_TEZ_FRAMEWORK_NAME); return configuration; }
From source file:com.chinamobile.bcbsp.bspcontroller.JobInProgress.java
License:Apache License
/** * clean checkpoint and delete the checkpoint information * @return chean result./*from www . j av a2 s . c om*/ */ private boolean cleanCheckpoint() { if (job.getCheckpointType().equals("HBase")) { String tableName = null; Configuration conf = HBaseConfiguration.create(); conf.set("hbase.zookeeper.property.clientPort", job.getConf().get(Constants.ZOOKEPER_CLIENT_PORT)); conf.set("hbase.zookeeper.quorum", "master"); conf.set("hbase.master", "master:60000"); HBaseAdmin admin; try { admin = new HBaseAdmin(conf); for (int i = 0; i < this.attemptIDList.size(); i++) { tableName = this.attemptIDList.get(i).toString(); if (admin.tableExists(tableName)) { admin.disableTable(tableName); admin.deleteTable(tableName); } } admin.close(); return true; } catch (MasterNotRunningException e) { LOG.error("Exception has happened and been catched!", e); e.printStackTrace(); } catch (ZooKeeperConnectionException e) { LOG.error("Exception has happened and been catched!", e); e.printStackTrace(); } catch (IOException e) { LOG.error("Exception has happened and been catched!", e); e.printStackTrace(); } return false; } else if (job.getCheckpointType().equals("HDFS")) { try { String uri = conf.get(Constants.BC_BSP_CHECKPOINT_WRITEPATH) + "/" + job.getJobID().toString() + "/"; // FileSystem fs = FileSystem.get(URI.create(uri), conf); BSPFileSystem bspfs = new BSPFileSystemImpl(URI.create(uri), conf); // if(fs.exists(new Path(uri))) { // fs.delete(new Path(uri), true); // } if (bspfs.exists(new BSPHdfsImpl().newPath(uri))) { bspfs.delete(new BSPHdfsImpl().newPath(uri), true); } return true; } catch (IOException e) { LOG.error("Exception has happened and been catched!", e); return false; } } return false; }
From source file:com.chinamobile.bcbsp.fault.storage.Checkpoint.java
License:Apache License
private void createTable(BSPJob job, StaffAttemptID staffId) { LOG.info("create hbase table"); Configuration conf = HBaseConfiguration.create(); // conf.addResource(new Path("/usr/local/termite/bc-bsp-1.0/conf/bcbsp-site.xml")); conf.set("hbase.zookeeper.property.clientPort", job.getConf().get(Constants.ZOOKEPER_CLIENT_PORT)); conf.set("hbase.zookeeper.quorum", "master"); conf.set("hbase.master", "master:60000"); String tableName = staffId.toString(); String columnFamilyName = "BorderNode"; try {//from ww w.ja v a 2 s .co m HBaseAdmin admin = new HBaseAdmin(conf); if (admin.tableExists(tableName)) { admin.disableTable(tableName); admin.deleteTable(tableName); } HTableDescriptor descriptor = new HTableDescriptor(tableName); descriptor.addFamily(new HColumnDescriptor(columnFamilyName)); admin.createTable(descriptor); admin.close(); } catch (MasterNotRunningException e1) { e1.printStackTrace(); } catch (ZooKeeperConnectionException e1) { e1.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } }
From source file:com.chinamobile.bcbsp.io.BSPFileInputFormat.java
License:Apache License
/** * Add a {@link Path} to the list of inputs for the BC_BSP job. * * @param job/*www. ja va 2 s. c om*/ * the current job BSPJob. * @param path * {@link Path} to be added to the list of inputs for the BC_BSP job. */ public static void addInputPath(BSPJob job, Path path) throws IOException { Configuration conf = job.getConf(); FileSystem fs = FileSystem.get(conf); path = path.makeQualified(fs); String dirStr = StringUtils.escapeString(path.toString()); String dirs = conf.get(Constants.USER_BC_BSP_JOB_INPUT_DIR); conf.set(Constants.USER_BC_BSP_JOB_INPUT_DIR, dirs == null ? dirStr : dirs + "," + dirStr); }