List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass
public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException
From source file:com.github.sandgorgon.parmr.Main.java
License:Open Source License
@Override public int run(String[] args) throws Exception { if (args.length < 2) { System.err.println("Usage: parmr <input file> <output path>"); return -1; }/*from www. j a v a2 s . com*/ Configuration conf = super.getConf(); conf.set("mapreduce.job.queuename", "prod"); Job job = Job.getInstance(conf); job.setJobName(jobName); job.setJarByClass(Main.class); // Parquet Schema // Read from the input file itself the schema that we will be assuming Path infile = new Path(args[0]); List<Footer> footers = ParquetFileReader.readFooters(conf, infile.getFileSystem(conf).getFileStatus(infile), true); MessageType schema = footers.get(0).getParquetMetadata().getFileMetaData().getSchema(); // Avro Schema // Convert the Parquet schema to an Avro schema AvroSchemaConverter avroSchemaConverter = new AvroSchemaConverter(); Schema avroSchema = avroSchemaConverter.convert(schema); // Set the Mapper job.setMapperClass(UserMapper.class); // This works for predicate pushdown on record assembly read. AvroParquetInputFormat.setUnboundRecordFilter(job, UserRecordFilter.class); AvroParquetInputFormat.addInputPath(job, new Path(args[0])); AvroParquetInputFormat.setAvroReadSchema(job, avroSchema); job.setInputFormatClass(AvroParquetInputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); // If you needed to return an avro object from the mapper, refer to this... //job.setMapOutputValueClass(AvroValue.class); //AvroJob.setMapOutputValueSchema(job, avroSchema); // Reducer job.setReducerClass(UserReducer.class); // Output job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); // If we need to return an avro class again, refer to this... //job.setOutputFormatClass(AvroParquetOutputFormat.class); //AvroParquetOutputFormat.setOutputPath(job, new Path(args[1])); //AvroParquetOutputFormat.setSchema(job, avroSchema); //job.setOutputKeyClass(Void.class); //job.setOutputValueClass(GenericRecord.class); // Rough way of testing the projection side of things. AvroParquetInputFormat.setRequestedProjection(job, Schema.parse("{\"namespace\": \"com.github.sandgorgon.parmr.avro\",\n" + " \"type\": \"record\",\n" + " \"name\": \"User\",\n" + " \"fields\": [\n" + " {\"name\": \"name\", \"type\": \"string\"},\n" + " {\"name\": \"favorite_number\", \"type\": [\"int\", \"null\"]}\n" + // " {\"name\": \"favorite_color\", \"type\": [\"string\", \"null\"]}\n" + " ]\n" + "}\n" + "")); // Do the deed! int completion = job.waitForCompletion(true) ? 0 : 1; return completion; }
From source file:com.github.ygf.pagerank.InLinks.java
License:Apache License
private void computeInLinks(Configuration conf, Path linksFile, Path outputDir) throws Exception { // This job computes the number of in-links for every page. The // implementation is very similar to the classic word count example. Job job = Job.getInstance(conf, "InLinks:Computation"); job.setJarByClass(InLinks.class); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(InLinksMapper.class); job.setCombinerClass(InLinksReducer.class); job.setReducerClass(InLinksReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, linksFile); FileOutputFormat.setOutputPath(job, new Path(outputDir, "inlinks")); job.waitForCompletion(true);//from w w w . ja v a 2 s. c o m }
From source file:com.github.ygf.pagerank.InLinks.java
License:Apache License
private void summarizeResults(Configuration conf, Path outputDir) throws Exception { int topResults = Integer.parseInt(conf.get("inlinks.top_results")); Job job = Job.getInstance(conf, "InLinks:TopN"); job.setJarByClass(InLinks.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setMapperClass(InLinksTopNMapper.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(IntWritable.class); job.setReducerClass(InLinksTopNReducer.class); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(outputDir, "inlinks")); FileOutputFormat.setOutputPath(job, new Path(outputDir, "inlinks-top" + topResults)); job.setNumReduceTasks(1);/*from ww w . ja v a 2 s .co m*/ job.waitForCompletion(true); }
From source file:com.github.ygf.pagerank.PageRank.java
License:Apache License
private void createTransitionMatrix(Configuration conf, Path linksFile, Path outputDir) throws Exception { // This job reads the links-simple-sorted.txt input file and generates // the corresponding transition matrix. The matrix is divided into // square blocks and each block is represented by the nonzero entries. // See Section 5.2 (and 5.2.3 in particular) of Mining of Massive Datasets // (http://infolab.stanford.edu/~ullman/mmds.html) for details. // The output is written to the "M" subdir in the output dir. Job job = Job.getInstance(conf, "PageRank:Matrix"); job.setJarByClass(PageRank.class); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(PageRankMatrixMapper.class); job.getConfiguration().setBoolean("mapreduce.map.output.compress", true); job.getConfiguration().setClass("mapreduce.map.output.compress.codec", DefaultCodec.class, CompressionCodec.class); job.setMapOutputKeyClass(ShortArrayWritable.class); job.setMapOutputValueClass(ShortArrayWritable.class); job.setReducerClass(PageRankMatrixReducer.class); SequenceFileOutputFormat.setCompressOutput(job, true); SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK); SequenceFileOutputFormat.setOutputCompressorClass(job, DefaultCodec.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setOutputKeyClass(ShortArrayWritable.class); job.setOutputValueClass(MatrixBlockWritable.class); FileInputFormat.addInputPath(job, linksFile); FileOutputFormat.setOutputPath(job, new Path(outputDir, "M")); job.waitForCompletion(true);/*from ww w .j av a 2 s .com*/ }
From source file:com.github.ygf.pagerank.PageRank.java
License:Apache License
private void pageRankIteration(int iter, Configuration conf, Path outputDir) throws Exception { // This job performs an iteration of the power iteration method to // compute PageRank. The map task processes each block M_{i,j}, loads // the corresponding stripe j of the vector v_{k-1} and produces the // partial result of the stripe i of the vector v_k. The reduce task // sums all the partial results of v_k and adds the teleportation factor // (the combiner only sums all the partial results). See Section 5.2 // (and 5.2.3 in particular) of Mining of Massive Datasets // (http://infolab.stanford.edu/~ullman/mmds.html) for details. The // output is written in a "vk" subdir of the output dir, where k is the // iteration number. MapFileOutputFormat is used to keep an array of the // stripes of v. Job job = Job.getInstance(conf, "PageRank:Iteration"); job.setJarByClass(PageRank.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setMapperClass(PageRankIterationMapper.class); job.setMapOutputKeyClass(ShortWritable.class); job.setMapOutputValueClass(FloatArrayWritable.class); job.setCombinerClass(PageRankIterationCombiner.class); job.setReducerClass(PageRankIterationReducer.class); job.setOutputFormatClass(MapFileOutputFormat.class); job.setOutputKeyClass(ShortWritable.class); job.setOutputValueClass(FloatArrayWritable.class); FileInputFormat.addInputPath(job, new Path(outputDir, "M")); FileOutputFormat.setOutputPath(job, new Path(outputDir, "v" + iter)); job.waitForCompletion(true);/* w w w. j a v a 2 s .com*/ }
From source file:com.github.ygf.pagerank.PageRank.java
License:Apache License
private void summarizeResults(int iter, Configuration conf, Path outputDir) throws Exception { // This job creates a plain text file with the top N PageRanks and the // titles of the pages. Each map task emits the top N PageRanks it // receives, and the reduce task merges the partial results into the // global top N PageRanks. A single reducer is used in the job in order // to have access to all the individual top N PageRanks from the // mappers. The reducer looks up the titles in the index built by // TitleIndex. This job was designed considering that N is small. int topResults = Integer.parseInt(conf.get("pagerank.top_results")); Job job = Job.getInstance(conf, "PageRank:TopN"); job.setJarByClass(PageRank.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setMapperClass(PageRankTopNMapper.class); job.setMapOutputKeyClass(FloatWritable.class); job.setMapOutputValueClass(IntWritable.class); job.setReducerClass(PageRankTopNReducer.class); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(FloatWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(outputDir, "v" + iter)); FileOutputFormat.setOutputPath(job, new Path(outputDir, "v" + iter + "-top" + topResults)); job.setNumReduceTasks(1);//w w w . j a va 2 s . c o m job.waitForCompletion(true); }
From source file:com.github.ygf.pagerank.TitleIndex.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.out.println("Usage: TitleIndex <titles-sorted.txt> <output-dir>"); ToolRunner.printGenericCommandUsage(System.out); return 2; }//from w w w . ja v a2 s . c o m Path titlesFile = new Path(args[0]); Path outputDir = new Path(args[1]); Configuration conf = getConf(); // Do not create _SUCCESS files. MapFileOutputFormat.getReaders calls // try to read the _SUCCESS as another MapFile dir. conf.set("mapreduce.fileoutputcommitter.marksuccessfuljobs", "false"); // This job creates a MapFile of the titles indexed by the page id. // UnsplittableTextInputFormat is used to ensure that the same map task // gets all the lines in the titlesFile and it can count the line // numbers. The number of reduce tasks is set to 0. Job job = Job.getInstance(conf, "TitleIndex"); job.setJarByClass(InLinks.class); job.setInputFormatClass(UnsplittableTextInputFormat.class); job.setMapperClass(TitleIndexMapper.class); job.setOutputFormatClass(MapFileOutputFormat.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, titlesFile); FileOutputFormat.setOutputPath(job, outputDir); job.setNumReduceTasks(0); job.waitForCompletion(true); return 0; }
From source file:com.goldsaxfoundation.bigdata.Module5.SimpleMapReduce.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "wordcount"); job.setJarByClass(SimpleMapReduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true);/*from ww w . j av a 2 s.c o m*/ }
From source file:com.google.cloud.bigtable.mapreduce.Import.java
License:Open Source License
/** * Sets up the actual job./*from ww w . ja v a2 s. co m*/ * @param conf The current configuration. * @param args The command line parameters. * @return The newly created job. * @throws IOException When setting up the job fails. */ public static Job createSubmittableJob(Configuration conf, String[] args) throws IOException { TableName tableName = TableName.valueOf(args[0]); conf.set(TABLE_NAME, tableName.getNameAsString()); Path inputDir = new Path(args[1]); Job job = Job.getInstance(conf, conf.get(JOB_NAME_CONF_KEY, NAME + "_" + tableName)); job.setJarByClass(Importer.class); FileInputFormat.setInputPaths(job, inputDir); job.setInputFormatClass(SequenceFileInputFormat.class); String hfileOutPath = conf.get(BULK_OUTPUT_CONF_KEY); // make sure we get the filter in the jars try { Class<? extends Filter> filter = conf.getClass(FILTER_CLASS_CONF_KEY, null, Filter.class); if (filter != null) { TableMapReduceUtil.addDependencyJars(conf, filter); } } catch (Exception e) { throw new IOException(e); } if (hfileOutPath != null) { job.setMapperClass(KeyValueImporter.class); try (Connection conn = ConnectionFactory.createConnection(conf); Table table = conn.getTable(tableName); RegionLocator regionLocator = conn.getRegionLocator(tableName)) { job.setReducerClass(KeyValueSortReducer.class); Path outputDir = new Path(hfileOutPath); FileOutputFormat.setOutputPath(job, outputDir); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(KeyValue.class); HFileOutputFormat2.configureIncrementalLoad(job, table, regionLocator); TableMapReduceUtil.addDependencyJars(job.getConfiguration(), com.google.common.base.Preconditions.class); } } else { // No reducers. Just write straight to table. Call initTableReducerJob // because it sets up the TableOutputFormat. job.setMapperClass(Importer.class); TableMapReduceUtil.initTableReducerJob(tableName.getNameAsString(), null, job); job.setNumReduceTasks(0); } return job; }
From source file:com.gsinnovations.howdah.AbstractJob.java
License:Apache License
protected Job prepareJob(Path inputPath, Path outputPath, Class<? extends InputFormat> inputFormat, Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey, Class<? extends Writable> mapperValue, Class<? extends Reducer> reducer, Class<? extends Writable> reducerKey, Class<? extends Writable> reducerValue, Class<? extends OutputFormat> outputFormat) throws IOException { Job job = new Job(new Configuration(getConf())); Configuration jobConf = job.getConfiguration(); if (reducer.equals(Reducer.class)) { if (mapper.equals(Mapper.class)) { throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer"); }/* w w w . ja v a 2s . c om*/ job.setJarByClass(mapper); } else { job.setJarByClass(reducer); } job.setInputFormatClass(inputFormat); jobConf.set("mapred.input.dir", inputPath.toString()); job.setMapperClass(mapper); job.setMapOutputKeyClass(mapperKey); job.setMapOutputValueClass(mapperValue); jobConf.setBoolean("mapred.compress.map.output", true); job.setReducerClass(reducer); job.setOutputKeyClass(reducerKey); job.setOutputValueClass(reducerValue); job.setJobName(getCustomJobName(job, mapper, reducer)); job.setOutputFormatClass(outputFormat); jobConf.set("mapred.output.dir", outputPath.toString()); return job; }