List of usage examples for org.apache.hadoop.mapred JobConf setMapOutputValueClass
public void setMapOutputValueClass(Class<?> theClass)
From source file:com.ibm.bi.dml.runtime.matrix.CSVReblockMR.java
License:Open Source License
private static JobReturn runCSVReblockJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String reblockInstructions, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos, Path counterFile, String[] smallestFiles) throws Exception { JobConf job; job = new JobConf(ReblockMR.class); job.setJobName("CSV-Reblock-MR"); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/* www . ja va 2 s.c o m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, false, ConvertTarget.CELL); job.setStrings(SMALLEST_FILE_NAME_PER_INPUT, smallestFiles); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setCSVReblockInstructions(job, reblockInstructions); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, null, reblockInstructions, null, otherInstructionsInReducer, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, null, reblockInstructions, null, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers int numRed = WriteCSVMR.determineNumReducers(rlens, clens, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), ret.numReducerGroups); job.setNumReduceTasks(numRed); // Print the complete instruction //if (LOG.isTraceEnabled()) // inst.printCompelteMRJobInstruction(stats); // Update resultDimsUnknown based on computed "stats" byte[] resultDimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { resultDimsUnknown[i] = (byte) 1; } else { resultDimsUnknown[i] = (byte) 0; } } //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true); // configure mapper and the mapper output key value pairs job.setMapperClass(CSVReblockMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); job.setMapOutputValueClass(BlockRow.class); //configure reducer job.setReducerClass(CSVReblockReducer.class); //turn off adaptivemr job.setBoolean("adaptivemr.map.enable", false); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); Path cachefile = new Path(counterFile, "part-00000"); DistributedCache.addCacheFile(cachefile.toUri(), job); DistributedCache.createSymlink(job); job.set(ROWID_FILE_NAME, cachefile.toString()); RunningJob runjob = JobClient.runJob(job); MapReduceTool.deleteFileIfExistOnHDFS(counterFile, job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); // System.out.println("result #"+resultIndexes[i]+" ===>\n"+stats[i]); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.DataGenMR.java
License:Open Source License
/** * <p>Starts a Rand MapReduce job which will produce one or more random objects.</p> * /*from www . j a v a2s .c o m*/ * @param numRows number of rows for each random object * @param numCols number of columns for each random object * @param blockRowSize number of rows in a block for each random object * @param blockColSize number of columns in a block for each random object * @param minValue minimum of the random values for each random object * @param maxValue maximum of the random values for each random object * @param sparsity sparsity for each random object * @param pdf probability density function for each random object * @param replication file replication * @param inputs input file for each random object * @param outputs output file for each random object * @param outputInfos output information for each random object * @param instructionsInMapper instruction for each random object * @param resultIndexes result indexes for each random object * @return matrix characteristics for each random object * @throws Exception if an error occurred in the MapReduce phase */ public static JobReturn runJob(MRJobInstruction inst, String[] dataGenInstructions, String instructionsInMapper, String aggInstructionsInReducer, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(DataGenMR.class); job.setJobName("DataGen-MR"); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, true); byte[] realIndexes = new byte[dataGenInstructions.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b; String[] inputs = new String[dataGenInstructions.length]; InputInfo[] inputInfos = new InputInfo[dataGenInstructions.length]; long[] rlens = new long[dataGenInstructions.length]; long[] clens = new long[dataGenInstructions.length]; int[] brlens = new int[dataGenInstructions.length]; int[] bclens = new int[dataGenInstructions.length]; FileSystem fs = FileSystem.get(job); String dataGenInsStr = ""; int numblocks = 0; int maxbrlen = -1, maxbclen = -1; double maxsparsity = -1; for (int i = 0; i < dataGenInstructions.length; i++) { dataGenInsStr = dataGenInsStr + Lop.INSTRUCTION_DELIMITOR + dataGenInstructions[i]; MRInstruction mrins = MRInstructionParser.parseSingleInstruction(dataGenInstructions[i]); MRINSTRUCTION_TYPE mrtype = mrins.getMRInstructionType(); DataGenMRInstruction genInst = (DataGenMRInstruction) mrins; rlens[i] = genInst.getRows(); clens[i] = genInst.getCols(); brlens[i] = genInst.getRowsInBlock(); bclens[i] = genInst.getColsInBlock(); maxbrlen = Math.max(maxbrlen, brlens[i]); maxbclen = Math.max(maxbclen, bclens[i]); if (mrtype == MRINSTRUCTION_TYPE.Rand) { RandInstruction randInst = (RandInstruction) mrins; inputs[i] = genInst.getBaseDir() + "tmp" + _seqRandInput.getNextID() + ".randinput"; maxsparsity = Math.max(maxsparsity, randInst.getSparsity()); FSDataOutputStream fsOut = fs.create(new Path(inputs[i])); PrintWriter pw = new PrintWriter(fsOut); //for obj reuse and preventing repeated buffer re-allocations StringBuilder sb = new StringBuilder(); //seed generation Well1024a bigrand = LibMatrixDatagen.setupSeedsForRand(randInst.getSeed()); long[] nnz = LibMatrixDatagen.computeNNZperBlock(rlens[i], clens[i], brlens[i], bclens[i], randInst.getSparsity()); int nnzIx = 0; for (long r = 0; r < rlens[i]; r += brlens[i]) { long curBlockRowSize = Math.min(brlens[i], (rlens[i] - r)); for (long c = 0; c < clens[i]; c += bclens[i]) { long curBlockColSize = Math.min(bclens[i], (clens[i] - c)); sb.append((r / brlens[i]) + 1); sb.append(','); sb.append((c / bclens[i]) + 1); sb.append(','); sb.append(curBlockRowSize); sb.append(','); sb.append(curBlockColSize); sb.append(','); sb.append(nnz[nnzIx++]); sb.append(','); sb.append(bigrand.nextLong()); pw.println(sb.toString()); sb.setLength(0); numblocks++; } } pw.close(); fsOut.close(); inputInfos[i] = InputInfo.TextCellInputInfo; } else if (mrtype == MRINSTRUCTION_TYPE.Seq) { SeqInstruction seqInst = (SeqInstruction) mrins; inputs[i] = genInst.getBaseDir() + System.currentTimeMillis() + ".seqinput"; maxsparsity = 1.0; //always dense double from = seqInst.fromValue; double to = seqInst.toValue; double incr = seqInst.incrValue; // Correctness checks on (from, to, incr) boolean neg = (from > to); if (incr == 0) throw new DMLRuntimeException("Invalid value for \"increment\" in seq()."); if (neg != (incr < 0)) throw new DMLRuntimeException("Wrong sign for the increment in a call to seq()"); // Compute the number of rows in the sequence long numrows = 1 + (long) Math.floor((to - from) / incr); if (rlens[i] > 0) { if (numrows != rlens[i]) throw new DMLRuntimeException( "Unexpected error while processing sequence instruction. Expected number of rows does not match given number: " + rlens[i] + " != " + numrows); } else { rlens[i] = numrows; } if (clens[i] > 0 && clens[i] != 1) throw new DMLRuntimeException( "Unexpected error while processing sequence instruction. Number of columns (" + clens[i] + ") must be equal to 1."); else clens[i] = 1; FSDataOutputStream fsOut = fs.create(new Path(inputs[i])); PrintWriter pw = new PrintWriter(fsOut); StringBuilder sb = new StringBuilder(); double temp = from; double block_from, block_to; for (long r = 0; r < rlens[i]; r += brlens[i]) { long curBlockRowSize = Math.min(brlens[i], (rlens[i] - r)); // block (bid_i,bid_j) generates a sequence from the interval [block_from, block_to] (inclusive of both end points of the interval) long bid_i = ((r / brlens[i]) + 1); long bid_j = 1; block_from = temp; block_to = temp + (curBlockRowSize - 1) * incr; temp = block_to + incr; // next block starts from here sb.append(bid_i); sb.append(','); sb.append(bid_j); sb.append(','); /* // Need not include block size while generating seq() sb.append(curBlockRowSize); sb.append(','); sb.append(1); sb.append(',');*/ sb.append(block_from); sb.append(','); sb.append(block_to); sb.append(','); sb.append(incr); pw.println(sb.toString()); //System.out.println("MapTask " + r + ": " + sb.toString()); sb.setLength(0); numblocks++; } pw.close(); fsOut.close(); inputInfos[i] = InputInfo.TextCellInputInfo; } else { throw new DMLRuntimeException("Unexpected Data Generation Instruction Type: " + mrtype); } } dataGenInsStr = dataGenInsStr.substring(1);//remove the first "," RunningJob runjob; MatrixCharacteristics[] stats; try { //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, false, ConvertTarget.BLOCK); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); MRJobConfiguration.setDimsUnknownFilePrefix(job, dimsUnknownFilePrefix); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up the rand Instructions MRJobConfiguration.setRandInstructions(job, dataGenInsStr); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setAggregateInstructions(job, aggInstructionsInReducer); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); //determine degree of parallelism (nmappers: 1<=n<=capacity) //TODO use maxsparsity whenever we have a way of generating sparse rand data int capacity = InfrastructureAnalyzer.getRemoteParallelMapTasks(); long dfsblocksize = InfrastructureAnalyzer.getHDFSBlockSize(); //correction max number of mappers on yarn clusters if (InfrastructureAnalyzer.isYarnEnabled()) capacity = (int) Math.max(capacity, YarnClusterAnalyzer.getNumCores()); int nmapers = Math .max(Math.min((int) (8 * maxbrlen * maxbclen * (long) numblocks / dfsblocksize), capacity), 1); job.setNumMapTasks(nmapers); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, dataGenInsStr, instructionsInMapper, null, aggInstructionsInReducer, otherInstructionsInReducer, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, dataGenInsStr, instructionsInMapper, null, aggInstructionsInReducer, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); stats = ret.stats; //set up the number of reducers MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); // print the complete MRJob instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); // Update resultDimsUnknown based on computed "stats" byte[] resultDimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { resultDimsUnknown[i] = (byte) 1; } else { resultDimsUnknown[i] = (byte) 0; } } boolean mayContainCtable = instructionsInMapper.contains("ctabletransform") || instructionsInMapper.contains("groupedagg"); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, mayContainCtable); // configure mapper and the mapper output key value pairs job.setMapperClass(DataGenMapper.class); if (numReducers == 0) { job.setMapOutputKeyClass(Writable.class); job.setMapOutputValueClass(Writable.class); } else { job.setMapOutputKeyClass(MatrixIndexes.class); job.setMapOutputValueClass(TaggedMatrixBlock.class); } //set up combiner if (numReducers != 0 && aggInstructionsInReducer != null && !aggInstructionsInReducer.isEmpty()) job.setCombinerClass(GMRCombiner.class); //configure reducer job.setReducerClass(GMRReducer.class); //job.setReducerClass(PassThroughReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile"; stats = MapReduceTool.processDimsFiles(dir, stats); MapReduceTool.deleteFileIfExistOnHDFS(dir); } finally { for (String input : inputs) MapReduceTool.deleteFileIfExistOnHDFS(new Path(input), job); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.GMR.java
License:Open Source License
/** * inBlockRepresentation: indicate whether to use block representation or cell representation * inputs: input matrices, the inputs are indexed by 0, 1, 2, .. based on the position in this string * inputInfos: the input format information for the input matrices * rlen: the number of rows for each matrix * clen: the number of columns for each matrix * brlen: the number of rows per block//from ww w .j a v a2s.co m * bclen: the number of columns per block * instructionsInMapper: in Mapper, the set of unary operations that need to be performed on each input matrix * aggInstructionsInReducer: in Reducer, right after sorting, the set of aggreagte operations that need * to be performed on each input matrix, * otherInstructionsInReducer: the mixed operations that need to be performed on matrices after the aggregate operations * numReducers: the number of reducers * replication: the replication factor for the output * resulltIndexes: the indexes of the result matrices that needs to be outputted. * outputs: the names for the output directories, one for each result index * outputInfos: output format information for the output matrices */ @SuppressWarnings({ "unchecked", "rawtypes" }) public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, boolean[] partitioned, PDataPartitionFormat[] pformats, int[] psizes, String recordReaderInstruction, String instructionsInMapper, String aggInstructionsInReducer, String otherInstructionsInReducer, int numReducers, int replication, boolean jvmReuse, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(GMR.class); job.setJobName("G-MR"); boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation); //added for handling recordreader instruction String[] realinputs = inputs; InputInfo[] realinputInfos = inputInfos; long[] realrlens = rlens; long[] realclens = clens; int[] realbrlens = brlens; int[] realbclens = bclens; byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b; if (recordReaderInstruction != null && !recordReaderInstruction.isEmpty()) { assert (inputs.length <= 2); PickByCountInstruction ins = (PickByCountInstruction) PickByCountInstruction .parseInstruction(recordReaderInstruction); PickFromCompactInputFormat.setKeyValueClasses(job, (Class<? extends WritableComparable>) inputInfos[ins.input1].inputKeyClass, inputInfos[ins.input1].inputValueClass); job.setInputFormat(PickFromCompactInputFormat.class); PickFromCompactInputFormat.setZeroValues(job, (NumItemsByEachReducerMetaData) inputInfos[ins.input1].metadata); if (ins.isValuePick) { double[] probs = MapReduceTool.readColumnVectorFromHDFS(inputs[ins.input2], inputInfos[ins.input2], rlens[ins.input2], clens[ins.input2], brlens[ins.input2], bclens[ins.input2]); PickFromCompactInputFormat.setPickRecordsInEachPartFile(job, (NumItemsByEachReducerMetaData) inputInfos[ins.input1].metadata, probs); realinputs = new String[inputs.length - 1]; realinputInfos = new InputInfo[inputs.length - 1]; realrlens = new long[inputs.length - 1]; realclens = new long[inputs.length - 1]; realbrlens = new int[inputs.length - 1]; realbclens = new int[inputs.length - 1]; realIndexes = new byte[inputs.length - 1]; byte realIndex = 0; for (byte i = 0; i < inputs.length; i++) { if (i == ins.input2) continue; realinputs[realIndex] = inputs[i]; realinputInfos[realIndex] = inputInfos[i]; if (i == ins.input1) { realrlens[realIndex] = rlens[ins.input2]; realclens[realIndex] = clens[ins.input2]; realbrlens[realIndex] = 1; realbclens[realIndex] = 1; realIndexes[realIndex] = ins.output; } else { realrlens[realIndex] = rlens[i]; realclens[realIndex] = clens[i]; realbrlens[realIndex] = brlens[i]; realbclens[realIndex] = bclens[i]; realIndexes[realIndex] = i; } realIndex++; } } else { //PickFromCompactInputFormat.setPickRecordsInEachPartFile(job, (NumItemsByEachReducerMetaData) inputInfos[ins.input1].metadata, ins.cst, 1-ins.cst); PickFromCompactInputFormat.setRangePickPartFiles(job, (NumItemsByEachReducerMetaData) inputInfos[ins.input1].metadata, ins.cst, 1 - ins.cst); realrlens[ins.input1] = UtilFunctions.getLengthForInterQuantile( (NumItemsByEachReducerMetaData) inputInfos[ins.input1].metadata, ins.cst); realclens[ins.input1] = clens[ins.input1]; realbrlens[ins.input1] = 1; realbclens[ins.input1] = 1; realIndexes[ins.input1] = ins.output; } } setupDistributedCache(job, instructionsInMapper, otherInstructionsInReducer, realinputs, realrlens, realclens); //set up the input files and their format information boolean[] distCacheOnly = getDistCacheOnlyInputs(realIndexes, recordReaderInstruction, instructionsInMapper, aggInstructionsInReducer, otherInstructionsInReducer); MRJobConfiguration.setUpMultipleInputs(job, realIndexes, realinputs, realinputInfos, realbrlens, realbclens, distCacheOnly, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL); MRJobConfiguration.setInputPartitioningInfo(job, pformats); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, realrlens, realclens); MRJobConfiguration.setDimsUnknownFilePrefix(job, dimsUnknownFilePrefix); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, realbrlens, realbclens); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setAggregateInstructions(job, aggInstructionsInReducer); //set up the instructions that will happen in the reducer, after the aggregation instructions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); //set up jvm reuse (incl. reuse of loaded dist cache matrices) if (jvmReuse) job.setNumTasksToExecutePerJvm(-1); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, otherInstructionsInReducer, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); // Update resultDimsUnknown based on computed "stats" byte[] dimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { dimsUnknown[i] = (byte) 1; } else { dimsUnknown[i] = (byte) 0; } } //MRJobConfiguration.updateResultDimsUnknown(job,resultDimsUnknown); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, dimsUnknown, outputs, outputInfos, inBlockRepresentation, true); // configure mapper and the mapper output key value pairs job.setMapperClass(GMRMapper.class); if (numReducers == 0) { job.setMapOutputKeyClass(Writable.class); job.setMapOutputValueClass(Writable.class); } else { job.setMapOutputKeyClass(MatrixIndexes.class); if (inBlockRepresentation) job.setMapOutputValueClass(TaggedMatrixBlock.class); else job.setMapOutputValueClass(TaggedMatrixPackedCell.class); } //set up combiner if (numReducers != 0 && aggInstructionsInReducer != null && !aggInstructionsInReducer.isEmpty()) { job.setCombinerClass(GMRCombiner.class); } //configure reducer job.setReducerClass(GMRReducer.class); //job.setReducerClass(PassThroughReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); //MatrixCharacteristics[] stats=new MatrixCharacteristics[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile"; stats = MapReduceTool.processDimsFiles(dir, stats); MapReduceTool.deleteFileIfExistOnHDFS(dir); return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.GroupedAggMR.java
License:Open Source License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String grpAggInstructions, String simpleReduceInstructions/*only scalar or reorg instructions allowed*/, int numReducers, int replication, byte[] resultIndexes, String dimsUnknownFilePrefix, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(GroupedAggMR.class); job.setJobName("GroupedAgg-MR"); //whether use block representation or cell representation //MRJobConfiguration.setMatrixValueClassForCM_N_COM(job, true); MRJobConfiguration.setMatrixValueClass(job, false); //added for handling recordreader instruction String[] realinputs = inputs; InputInfo[] realinputInfos = inputInfos; long[] realrlens = rlens; long[] realclens = clens; int[] realbrlens = brlens; int[] realbclens = bclens; byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/*from www . ja v a2 s. c o m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, realinputs, realinputInfos, realbrlens, realbclens, true, ConvertTarget.WEIGHTEDCELL); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, realrlens, realclens); MRJobConfiguration.setDimsUnknownFilePrefix(job, dimsUnknownFilePrefix); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, realbrlens, realbclens); //set up the grouped aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setGroupedAggInstructions(job, grpAggInstructions); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, simpleReduceInstructions); //set up the number of reducers MRJobConfiguration.setNumReducers(job, numReducers, numReducers); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up what matrices are needed to pass from the mapper to reducer MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, null, null, grpAggInstructions, resultIndexes); MatrixCharacteristics[] stats = new MatrixCharacteristics[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) stats[i] = new MatrixCharacteristics(); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); byte[] resultDimsUnknown = new byte[resultIndexes.length]; // Update resultDimsUnknown based on computed "stats" for (int i = 0; i < resultIndexes.length; i++) resultDimsUnknown[i] = (byte) 2; //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, false); // configure mapper and the mapper output key value pairs job.setMapperClass(GroupedAggMRMapper.class); job.setCombinerClass(GroupedAggMRCombiner.class); job.setMapOutputKeyClass(TaggedInt.class); job.setMapOutputValueClass(WeightedCell.class); //configure reducer job.setReducerClass(GroupedAggMRReducer.class); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); //execute job RunningJob runjob = JobClient.runJob(job); //get important output statistics Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i] = new MatrixCharacteristics(); stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } String dir = dimsUnknownFilePrefix + "/" + runjob.getID().toString() + "_dimsFile"; stats = MapReduceTool.processDimsFiles(dir, stats); MapReduceTool.deleteFileIfExistOnHDFS(dir); return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.MMCJMR.java
License:Open Source License
private static MatrixCharacteristics[] commonSetup(JobConf job, boolean inBlockRepresentation, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String instructionsInMapper, String aggInstructionsInReducer, String aggBinInstrction, int numReducers, int replication, byte resultDimsUnknown, String output, OutputInfo outputinfo) throws Exception { job.setJobName("MMCJ-MR"); if (numReducers <= 0) throw new Exception("MMCJ-MR has to have at least one reduce task!"); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/*from w w w. j av a2 s . c o m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setAggregateInstructions(job, aggInstructionsInReducer); //set up the aggregate binary operation for the mmcj job MRJobConfiguration.setAggregateBinaryInstructions(job, aggBinInstrction); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); byte[] resultIndexes = new byte[] { MRInstructionParser.parseSingleInstruction(aggBinInstrction).output }; byte[] resultDimsUnknown_Array = new byte[] { resultDimsUnknown }; // byte[] resultIndexes=new byte[]{AggregateBinaryInstruction.parseMRInstruction(aggBinInstrction).output}; //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrction, resultIndexes); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown_Array, new String[] { output }, new OutputInfo[] { outputinfo }, inBlockRepresentation); // configure mapper job.setMapperClass(MMCJMRMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); if (inBlockRepresentation) job.setMapOutputValueClass(MatrixBlock.class); else job.setMapOutputValueClass(MatrixCell.class); job.setOutputKeyComparatorClass(TaggedFirstSecondIndexes.Comparator.class); job.setPartitionerClass(TaggedFirstSecondIndexes.FirstIndexPartitioner.class); //configure combiner //TODO: cannot set up combiner, because it will destroy the stable numerical algorithms // for sum or for central moments //if(aggInstructionsInReducer!=null && !aggInstructionsInReducer.isEmpty()) // job.setCombinerClass(MMCJMRCombiner.class); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrction, null, resultIndexes, mapoutputIndexes, true); //set up the number of reducers if (AUTOMATIC_CONFIG_NUM_REDUCERS) { int numRed = determineNumReducers(rlens, clens, numReducers, ret.numReducerGroups); job.setNumReduceTasks(numRed); } else MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); //configure reducer // note: the alternative MMCJMRReducer is not maintained job.setReducerClass(MMCJMRReducerWithAggregator.class); return ret.stats; }
From source file:com.ibm.bi.dml.runtime.matrix.MMRJMR.java
License:Open Source License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String instructionsInMapper, String aggInstructionsInReducer, String aggBinInstrctions, String otherInstructionsInReducer, int numReducers, int replication, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(MMRJMR.class); job.setJobName("MMRJ-MR"); if (numReducers <= 0) throw new Exception("MMRJ-MR has to have at least one reduce task!"); // TODO: check w/ yuanyuan. This job always runs in blocked mode, and hence derivation is not necessary. boolean inBlockRepresentation = MRJobConfiguration.deriveRepresentation(inputInfos); //whether use block representation or cell representation MRJobConfiguration.setMatrixValueClass(job, inBlockRepresentation); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;//from w w w . j av a2 s .com //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, inBlockRepresentation ? ConvertTarget.BLOCK : ConvertTarget.CELL); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setAggregateInstructions(job, aggInstructionsInReducer); //set up the aggregate binary operation for the mmcj job MRJobConfiguration.setAggregateBinaryInstructions(job, aggBinInstrctions); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up map/reduce memory configurations (if in AM context) DMLConfig config = ConfigurationManager.getConfig(); DMLAppMasterUtils.setupMRJobRemoteMaxMemory(job, config); // byte[] resultIndexes=new byte[]{AggregateBinaryInstruction.parseMRInstruction(aggBinInstrction).output}; //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrctions, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, aggInstructionsInReducer, aggBinInstrctions, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers MRJobConfiguration.setNumReducers(job, ret.numReducerGroups, numReducers); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); byte[] dimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { dimsUnknown[i] = (byte) 1; } else { dimsUnknown[i] = (byte) 0; } } //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, dimsUnknown, outputs, outputInfos, inBlockRepresentation); // configure mapper job.setMapperClass(MMRJMRMapper.class); job.setMapOutputKeyClass(TripleIndexes.class); if (inBlockRepresentation) job.setMapOutputValueClass(TaggedMatrixBlock.class); else job.setMapOutputValueClass(TaggedMatrixCell.class); job.setOutputKeyComparatorClass(TripleIndexes.Comparator.class); job.setPartitionerClass(TripleIndexes.FirstTwoIndexesPartitioner.class); //configure combiner //TODO: cannot set up combiner, because it will destroy the stable numerical algorithms // for sum or for central moments // if(aggInstructionsInReducer!=null && !aggInstructionsInReducer.isEmpty()) // job.setCombinerClass(MMCJMRCombiner.class); //configure reducer job.setReducerClass(MMRJMRReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.ReblockMR.java
License:Open Source License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, long[] nnz, String instructionsInMapper, String reblockInstructions, String otherInstructionsInReducer, int numReducers, int replication, boolean jvmReuse, byte[] resultIndexes, String[] outputs, OutputInfo[] outputInfos) throws Exception { JobConf job = new JobConf(ReblockMR.class); job.setJobName("Reblock-MR"); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/* ww w . j a va2 s . co m*/ //set up the input files and their format information //(internally used input converters: text2bc for text, identity for binary inputs) MRJobConfiguration.setUpMultipleInputsReblock(job, realIndexes, inputs, inputInfos, brlens, bclens); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens, nnz); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); //set up unary instructions that will perform in the mapper MRJobConfiguration.setInstructionsInMapper(job, instructionsInMapper); //set up the aggregate instructions that will happen in the combiner and reducer MRJobConfiguration.setReblockInstructions(job, reblockInstructions); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInstructionsInReducer); //set up the replication factor for the results job.setInt("dfs.replication", replication); //disable automatic tasks timeouts and speculative task exec job.setInt("mapred.task.timeout", 0); job.setMapSpeculativeExecution(false); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //enable jvm reuse (based on SystemML configuration) if (jvmReuse) job.setNumTasksToExecutePerJvm(-1); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, instructionsInMapper, reblockInstructions, null, otherInstructionsInReducer, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, instructionsInMapper, reblockInstructions, null, null, otherInstructionsInReducer, resultIndexes, mapoutputIndexes, false); MatrixCharacteristics[] stats = ret.stats; //set up the number of reducers (according to output size) int numRed = determineNumReducers(rlens, clens, nnz, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), ret.numReducerGroups); job.setNumReduceTasks(numRed); //setup in-memory reduce buffers budget (reblock reducer dont need much memory) //job.set("mapred.job.reduce.input.buffer.percent", "0.70"); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); // Update resultDimsUnknown based on computed "stats" byte[] resultDimsUnknown = new byte[resultIndexes.length]; for (int i = 0; i < resultIndexes.length; i++) { if (stats[i].getRows() == -1 || stats[i].getCols() == -1) { resultDimsUnknown[i] = (byte) 1; } else { resultDimsUnknown[i] = (byte) 0; } } //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true); // configure mapper and the mapper output key value pairs job.setMapperClass(ReblockMapper.class); job.setMapOutputKeyClass(MatrixIndexes.class); //represent key offsets for block job.setMapOutputValueClass(TaggedAdaptivePartialBlock.class); //binary cell/block //configure reducer job.setReducerClass(ReblockReducer.class); // By default, the job executes in "cluster" mode. // Determine if we can optimize and run it in "local" mode. // at this point, both reblock_binary and reblock_text are similar MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); // System.out.println("result #"+resultIndexes[i]+" ===>\n"+stats[i]); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.matrix.SortMR.java
License:Open Source License
@SuppressWarnings({ "unchecked", "rawtypes" })
public static JobReturn runJob(MRJobInstruction inst, String input, InputInfo inputInfo, long rlen, long clen,
int brlen, int bclen, String combineInst, String sortInst, int numReducers, int replication,
String output, OutputInfo outputInfo, boolean valueIsWeight) throws Exception {
boolean sortIndexes = getSortInstructionType(sortInst) == SortKeys.OperationTypes.Indexes;
String tmpOutput = sortIndexes ? MRJobConfiguration.constructTempOutputFilename() : output;
JobConf job = new JobConf(SortMR.class);
job.setJobName("SortMR");
//setup partition file
String pfname = MRJobConfiguration.setUpSortPartitionFilename(job);
Path partitionFile = new Path(pfname);
URI partitionUri = new URI(partitionFile.toString());
//setup input/output paths
Path inputDir = new Path(input);
inputDir = inputDir.makeQualified(inputDir.getFileSystem(job));
SamplingSortMRInputFormat.setInputPaths(job, inputDir);
Path outpath = new Path(tmpOutput);
FileOutputFormat.setOutputPath(job, outpath);
MapReduceTool.deleteFileIfExistOnHDFS(outpath, job);
//set number of reducers (1 if local mode)
if (InfrastructureAnalyzer.isLocalMode(job))
job.setNumReduceTasks(1);//from ww w . j av a2s . c o m
else
MRJobConfiguration.setNumReducers(job, numReducers, numReducers);
//setup input/output format
job.setInputFormat(SamplingSortMRInputFormat.class);
SamplingSortMRInputFormat.setTargetKeyValueClasses(job,
(Class<? extends WritableComparable>) outputInfo.outputKeyClass, outputInfo.outputValueClass);
//setup instructions and meta information
if (combineInst != null && !combineInst.trim().isEmpty())
job.set(COMBINE_INSTRUCTION, combineInst);
job.set(SORT_INSTRUCTION, sortInst);
job.setBoolean(VALUE_IS_WEIGHT, valueIsWeight);
boolean desc = getSortInstructionDescending(sortInst);
job.setBoolean(SORT_DECREASING, desc);
MRJobConfiguration.setBlockSize(job, (byte) 0, brlen, bclen);
MRJobConfiguration.setInputInfo(job, (byte) 0, inputInfo, brlen, bclen, ConvertTarget.CELL);
int partitionWith0 = SamplingSortMRInputFormat.writePartitionFile(job, partitionFile);
//setup mapper/reducer/partitioner/output classes
if (getSortInstructionType(sortInst) == SortKeys.OperationTypes.Indexes) {
MRJobConfiguration.setInputInfo(job, (byte) 0, inputInfo, brlen, bclen, ConvertTarget.CELL);
job.setOutputFormat(OutputInfo.BinaryBlockOutputInfo.outputFormatClass);
job.setMapperClass(IndexSortMapper.class);
job.setReducerClass(IndexSortReducer.class);
job.setMapOutputKeyClass(!desc ? IndexSortComparable.class : IndexSortComparableDesc.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(MatrixIndexes.class);
job.setOutputValueClass(MatrixBlock.class);
} else { //default case: SORT w/wo weights
MRJobConfiguration.setInputInfo(job, (byte) 0, inputInfo, brlen, bclen, ConvertTarget.CELL);
job.setOutputFormat(CompactOutputFormat.class);
job.setMapperClass(ValueSortMapper.class);
job.setReducerClass(ValueSortReducer.class);
job.setOutputKeyClass(outputInfo.outputKeyClass); //double
job.setOutputValueClass(outputInfo.outputValueClass); //int
}
job.setPartitionerClass(TotalOrderPartitioner.class);
//setup distributed cache
DistributedCache.addCacheFile(partitionUri, job);
DistributedCache.createSymlink(job);
//setup replication factor
job.setInt("dfs.replication", replication);
MatrixCharacteristics[] s = new MatrixCharacteristics[1];
s[0] = new MatrixCharacteristics(rlen, clen, brlen, bclen);
// Print the complete instruction
if (LOG.isTraceEnabled())
inst.printCompleteMRJobInstruction(s);
//set unique working dir
MRJobConfiguration.setUniqueWorkingDir(job);
//run mr job
RunningJob runjob = JobClient.runJob(job);
Group group = runjob.getCounters().getGroup(NUM_VALUES_PREFIX);
numReducers = job.getNumReduceTasks();
//process final meta data
long[] counts = new long[numReducers];
long total = 0;
for (int i = 0; i < numReducers; i++) {
counts[i] = group.getCounter(Integer.toString(i));
total += counts[i];
}
//add missing 0s back to the results
long missing0s = 0;
if (total < rlen * clen) {
if (partitionWith0 < 0)
throw new RuntimeException("no partition contains 0, which is wrong!");
missing0s = rlen * clen - total;
counts[partitionWith0] += missing0s;
} else
partitionWith0 = -1;
if (sortIndexes) {
//run builtin job for shifting partially sorted blocks according to global offsets
//we do this in this custom form since it would not fit into the current structure
//of systemml to output two intermediates (partially sorted data, offsets) out of a
//single SortKeys lop
boolean success = runjob.isSuccessful();
if (success) {
success = runStitchupJob(tmpOutput, rlen, clen, brlen, bclen, counts, numReducers, replication,
output);
}
MapReduceTool.deleteFileIfExistOnHDFS(tmpOutput);
MapReduceTool.deleteFileIfExistOnHDFS(pfname);
return new JobReturn(s[0], OutputInfo.BinaryBlockOutputInfo, success);
} else {
MapReduceTool.deleteFileIfExistOnHDFS(pfname);
return new JobReturn(s[0], counts, partitionWith0, missing0s, runjob.isSuccessful());
}
}
From source file:com.ibm.bi.dml.runtime.matrix.WriteCSVMR.java
License:Open Source License
public static JobReturn runJob(MRJobInstruction inst, String[] inputs, InputInfo[] inputInfos, long[] rlens, long[] clens, int[] brlens, int[] bclens, String csvWriteInstructions, int numReducers, int replication, byte[] resultIndexes, String[] outputs) throws Exception { JobConf job = new JobConf(WriteCSVMR.class); job.setJobName("WriteCSV-MR"); byte[] realIndexes = new byte[inputs.length]; for (byte b = 0; b < realIndexes.length; b++) realIndexes[b] = b;/*from w ww . j av a 2s.co m*/ //set up the input files and their format information MRJobConfiguration.setUpMultipleInputs(job, realIndexes, inputs, inputInfos, brlens, bclens, true, ConvertTarget.CSVWRITE); //set up the dimensions of input matrices MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); //set up the block size MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); MRJobConfiguration.setCSVWriteInstructions(job, csvWriteInstructions); //set up the replication factor for the results job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); long maxRlen = 0; for (long rlen : rlens) if (rlen > maxRlen) maxRlen = rlen; //set up the number of reducers (according to output size) int numRed = determineNumReducers(rlens, clens, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), (int) maxRlen); job.setNumReduceTasks(numRed); byte[] resultDimsUnknown = new byte[resultIndexes.length]; MatrixCharacteristics[] stats = new MatrixCharacteristics[resultIndexes.length]; OutputInfo[] outputInfos = new OutputInfo[outputs.length]; HashMap<Byte, Integer> indexmap = new HashMap<Byte, Integer>(); for (int i = 0; i < stats.length; i++) { indexmap.put(resultIndexes[i], i); resultDimsUnknown[i] = (byte) 0; stats[i] = new MatrixCharacteristics(); outputInfos[i] = OutputInfo.CSVOutputInfo; } CSVWriteInstruction[] ins = MRInstructionParser.parseCSVWriteInstructions(csvWriteInstructions); for (CSVWriteInstruction in : ins) stats[indexmap.get(in.output)].set(rlens[in.input], clens[in.input], -1, -1); // Print the complete instruction if (LOG.isTraceEnabled()) inst.printCompleteMRJobInstruction(stats); //set up what matrices are needed to pass from the mapper to reducer MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, "", "", csvWriteInstructions, resultIndexes); //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, resultIndexes, resultDimsUnknown, outputs, outputInfos, true, true); // configure mapper and the mapper output key value pairs job.setMapperClass(CSVWriteMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); job.setMapOutputValueClass(MatrixBlock.class); //configure reducer job.setReducerClass(CSVWriteReducer.class); job.setOutputKeyComparatorClass(TaggedFirstSecondIndexes.Comparator.class); job.setPartitionerClass(TaggedFirstSecondIndexes.FirstIndexRangePartitioner.class); //job.setOutputFormat(UnPaddedOutputFormat.class); MatrixCharacteristics[] inputStats = new MatrixCharacteristics[inputs.length]; for (int i = 0; i < inputs.length; i++) { inputStats[i] = new MatrixCharacteristics(rlens[i], clens[i], brlens[i], bclens[i]); } //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); RunningJob runjob = JobClient.runJob(job); /* Process different counters */ Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { // number of non-zeros stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(stats, outputInfos, runjob.isSuccessful()); }
From source file:com.ibm.bi.dml.runtime.transform.ApplyTfBBMR.java
License:Open Source License
public static JobReturn runJob(String inputPath, String rblkInst, String otherInst, String specPath, String mapsPath, String tmpPath, String outputPath, String partOffsetsFile, CSVFileFormatProperties inputDataProperties, long numRows, long numColsBefore, long numColsAfter, int replication, String headerLine) throws Exception { CSVReblockInstruction rblk = (CSVReblockInstruction) InstructionParser.parseSingleInstruction(rblkInst); long[] rlens = new long[] { numRows }; long[] clens = new long[] { numColsAfter }; int[] brlens = new int[] { rblk.brlen }; int[] bclens = new int[] { rblk.bclen }; byte[] realIndexes = new byte[] { rblk.input }; byte[] resultIndexes = new byte[] { rblk.output }; JobConf job = new JobConf(ApplyTfBBMR.class); job.setJobName("ApplyTfBB"); /* Setup MapReduce Job */ job.setJarByClass(ApplyTfBBMR.class); // set relevant classes job.setMapperClass(ApplyTfBBMapper.class); MRJobConfiguration.setUpMultipleInputs(job, realIndexes, new String[] { inputPath }, new InputInfo[] { InputInfo.CSVInputInfo }, brlens, bclens, false, ConvertTarget.CELL); MRJobConfiguration.setMatricesDimensions(job, realIndexes, rlens, clens); MRJobConfiguration.setBlocksSizes(job, realIndexes, brlens, bclens); MRJobConfiguration.setCSVReblockInstructions(job, rblkInst); //set up the instructions that will happen in the reducer, after the aggregation instrucions MRJobConfiguration.setInstructionsInReducer(job, otherInst); job.setInt("dfs.replication", replication); //set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); //set up what matrices are needed to pass from the mapper to reducer HashSet<Byte> mapoutputIndexes = MRJobConfiguration.setUpOutputIndexesForMapper(job, realIndexes, null, rblkInst, null, otherInst, resultIndexes); MatrixChar_N_ReducerGroups ret = MRJobConfiguration.computeMatrixCharacteristics(job, realIndexes, null, rblkInst, null, null, null, resultIndexes, mapoutputIndexes, false); //set up the number of reducers int numRed = WriteCSVMR.determineNumReducers(rlens, clens, ConfigurationManager.getConfig().getIntValue(DMLConfig.NUM_REDUCERS), ret.numReducerGroups); job.setNumReduceTasks(numRed);/*from w ww . j a v a2s . c om*/ //set up the multiple output files, and their format information MRJobConfiguration.setUpMultipleOutputs(job, new byte[] { rblk.output }, new byte[] { 0 }, new String[] { outputPath }, new OutputInfo[] { OutputInfo.BinaryBlockOutputInfo }, true, false); // configure mapper and the mapper output key value pairs job.setMapperClass(ApplyTfBBMapper.class); job.setMapOutputKeyClass(TaggedFirstSecondIndexes.class); job.setMapOutputValueClass(BlockRow.class); //configure reducer job.setReducerClass(CSVReblockReducer.class); //turn off adaptivemr job.setBoolean("adaptivemr.map.enable", false); //set unique working dir MRJobConfiguration.setUniqueWorkingDir(job); // Add transformation metadata file as well as partOffsetsFile to Distributed cache DistributedCache.addCacheFile((new Path(mapsPath)).toUri(), job); DistributedCache.createSymlink(job); Path cachefile = new Path(new Path(partOffsetsFile), "part-00000"); DistributedCache.addCacheFile(cachefile.toUri(), job); DistributedCache.createSymlink(job); job.set(MRJobConfiguration.TF_HAS_HEADER, Boolean.toString(inputDataProperties.hasHeader())); job.set(MRJobConfiguration.TF_DELIM, inputDataProperties.getDelim()); if (inputDataProperties.getNAStrings() != null) // Adding "dummy" string to handle the case of na_strings = "" job.set(MRJobConfiguration.TF_NA_STRINGS, TfUtils.prepNAStrings(inputDataProperties.getNAStrings())); job.set(MRJobConfiguration.TF_SPEC_FILE, specPath); job.set(MRJobConfiguration.TF_SMALLEST_FILE, CSVReblockMR.findSmallestFile(job, inputPath)); job.set(MRJobConfiguration.OUTPUT_MATRICES_DIRS_CONFIG, outputPath); job.setLong(MRJobConfiguration.TF_NUM_COLS, numColsBefore); job.set(MRJobConfiguration.TF_TXMTD_PATH, mapsPath); job.set(MRJobConfiguration.TF_HEADER, headerLine); job.set(CSVReblockMR.ROWID_FILE_NAME, cachefile.toString()); job.set(MRJobConfiguration.TF_TMP_LOC, tmpPath); RunningJob runjob = JobClient.runJob(job); MapReduceTool.deleteFileIfExistOnHDFS(cachefile, job); Group group = runjob.getCounters().getGroup(MRJobConfiguration.NUM_NONZERO_CELLS); for (int i = 0; i < resultIndexes.length; i++) { ret.stats[i].setNonZeros(group.getCounter(Integer.toString(i))); } return new JobReturn(ret.stats, runjob.isSuccessful()); }