List of usage examples for org.apache.hadoop.mapreduce Job setOutputValueClass
public void setOutputValueClass(Class<?> theClass) throws IllegalStateException
From source file:com.elex.dmp.vectorizer.DictionaryVectorizer.java
License:Apache License
/** * Count the frequencies of words in parallel using Map/Reduce. The input documents have to be in * {@link SequenceFile} format//from w ww . j a v a 2 s.co m */ private static void startWordCounting(Path input, Path output, Configuration baseConf, int minSupport) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(baseConf); // this conf parameter needs to be set enable serialisation of conf values conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); conf.setInt(MIN_SUPPORT, minSupport); Job job = new Job(conf); job.setJobName("DictionaryVectorizer::WordCount: input-folder: " + input); job.setJarByClass(DictionaryVectorizer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(TermCountMapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setCombinerClass(TermCountCombiner.class); job.setReducerClass(TermCountReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); HadoopUtil.delete(conf, output); boolean succeeded = job.waitForCompletion(true); if (!succeeded) throw new IllegalStateException("Job failed!"); }
From source file:com.elex.dmp.vectorizer.FixDictionaryVectorizer.java
License:Apache License
/** * Create a partial vector using a chunk of features from the input documents. The input documents has to be * in the {@link SequenceFile} format//w w w. ja va 2s . c o m * * @param input * input directory of the documents in {@link SequenceFile} format * @param baseConf * job configuration * @param maxNGramSize * maximum size of ngrams to generate * @param dictionaryFilePath * location of the chunk of features and the id's * @param output * output directory were the partial vectors have to be created * @param dimension * @param sequentialAccess * output vectors should be optimized for sequential access * @param namedVectors * output vectors should be named, retaining key (doc id) as a label * @param numReducers * the desired number of reducer tasks */ private static void makePartialVectors(Path input, Configuration baseConf, int maxNGramSize, Path dictionaryFilePath, Path output, int dimension, boolean sequentialAccess, boolean namedVectors, int numReducers) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(baseConf); // this conf parameter needs to be set enable serialisation of conf values conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); conf.setInt(PartialVectorMerger.DIMENSION, dimension); conf.setBoolean(PartialVectorMerger.SEQUENTIAL_ACCESS, sequentialAccess); conf.setBoolean(PartialVectorMerger.NAMED_VECTOR, namedVectors); conf.setInt(MAX_NGRAMS, maxNGramSize); DistributedCache.setCacheFiles(new URI[] { dictionaryFilePath.toUri() }, conf); Job job = new Job(conf); job.setJobName("DictionaryVectorizer::MakePartialVectors: input-folder: " + input + ", dictionary-file: " + dictionaryFilePath); job.setJarByClass(FixDictionaryVectorizer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(StringTuple.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(VectorWritable.class); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(Mapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setReducerClass(TFPartialVectorReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setNumReduceTasks(numReducers); HadoopUtil.delete(conf, output); boolean succeeded = job.waitForCompletion(true); if (!succeeded) throw new IllegalStateException("Job failed!"); }
From source file:com.elex.dmp.vectorizer.FixDictionaryVectorizer.java
License:Apache License
/** * Count the frequencies of words in parallel using Map/Reduce. The input documents have to be in * {@link SequenceFile} format/*from w w w . j av a 2 s . c o m*/ */ private static void startWordCounting(Path input, Path output, Configuration baseConf, int minSupport) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(baseConf); // this conf parameter needs to be set enable serialisation of conf values conf.set("io.serializations", "org.apache.hadoop.io.serializer.JavaSerialization," + "org.apache.hadoop.io.serializer.WritableSerialization"); conf.setInt(MIN_SUPPORT, minSupport); Job job = new Job(conf); job.setJobName("DictionaryVectorizer::WordCount: input-folder: " + input); job.setJarByClass(FixDictionaryVectorizer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); FileInputFormat.setInputPaths(job, input); FileOutputFormat.setOutputPath(job, output); job.setMapperClass(TermCountMapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setCombinerClass(TermCountCombiner.class); job.setReducerClass(TermCountReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); HadoopUtil.delete(conf, output); boolean succeeded = job.waitForCompletion(true); if (!succeeded) throw new IllegalStateException("Job failed!"); }
From source file:com.elixir.hadoop.Chromo.FragmentCoverage.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> [<in>...] <out>"); System.exit(2);/* w ww. ja va2 s. co m*/ } Job job = Job.getInstance(conf, "position"); job.setJarByClass(FragmentCoverage.class); job.setMapperClass(CoverageMapper.class); job.setCombinerClass(IntSumReducer.class); job.setNumReduceTasks(5); job.setMapOutputKeyClass(com.elixir.hadoop.Chromo.SecondrySort.IntPair.class); //job.setSpeculativeExecution(true); job.setPartitionerClass(ChromoPartitioner.class); job.setGroupingComparatorClass(com.elixir.hadoop.Chromo.SecondrySort.FirstGroupingComparator.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // job.setOutputFormatClass(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:com.elixir.hadoop.FragmentCoverage.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> [<in>...] <out>"); System.exit(2);/* w w w . ja va 2 s .c o m*/ } Job job = Job.getInstance(conf, "position"); job.setJarByClass(FragmentCoverage.class); job.setMapperClass(CoverageMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.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:com.elixir.hadoop.OddEven.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> [<in>...] <out>"); System.exit(2);//from w w w . java 2s . c o m } Job job = Job.getInstance(conf, "oddeven"); job.setJarByClass(OddEven.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.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:com.elixir.hadoop.Word.WordCount.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> [<in>...] <out>"); System.exit(2);//from ww w. jav a 2s. c om } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.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:com.elixir.hadoop.WordCount.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> [<in>...] <out>"); System.exit(2);//from w w w .ja v a 2s.c o m } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.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:com.ema.hadoop.bestclient.BestClient.java
public static void main(String[] args) throws Exception { if (args.length != 4) { System.err.println("Usage: BestClient <input path> <output path> <date start> <date end>"); System.exit(-1);//from ww w .j a va2 s. co m } Job job = Job.getInstance(); job.setJarByClass(BestClient.class); job.setJobName("Best client job"); JobConf jobConf = (JobConf) job.getConfiguration(); jobConf.setStrings("dates", args[2], args[3]); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(BCMapper.class); job.setReducerClass(BCReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.ema.hadoop.wordcount.WordCount.java
public static void main(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: WordCount <input path> <output path>"); System.exit(-1);//from w w w . j av a 2s .c o m } Job job = Job.getInstance(); job.setJarByClass(WordCount.class); job.setJobName("Word count job"); FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(WCMapper.class); job.setReducerClass(WCReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); System.exit(job.waitForCompletion(true) ? 0 : 1); }