List of usage examples for org.apache.hadoop.mapred JobConf set
public void set(String name, String value)
value of the name property. From source file:com.linkedin.mapred.AvroUtils.java
License:Open Source License
public static void addAvroCacheFilesAndSetTheProperty(JobConf conf, Path inputPath, String property) throws Exception { addAvroCacheFiles(conf, inputPath);//from w ww. j av a 2 s . c om conf.set(property, inputPath.toString()); }
From source file:com.linkedin.mlease.regression.jobs.ItemModelTest.java
License:Open Source License
@Override public void run() throws Exception { JobConfig props = super.getJobConfig(); List<String> lambdastr = props.getStringList(LAMBDA, ","); String outBasePath = props.getString(OUTPUT_BASE_PATH); for (String lambda : lambdastr) { String outPath = outBasePath + "/lambda-" + lambda; props.put("output.path", outPath); JobConf conf = createJobConf(PerItemTestMapper.class, PerItemTestReducer.class); AvroUtils.addAvroCacheFilesAndSetTheProperty(conf, new Path(props.get(MODEL_PATH)), MODEL_PATH); conf.set(ITEM_KEY, props.getString(ITEM_KEY)); conf.setFloat(LAMBDA, Float.parseFloat(lambda)); conf.setBoolean(BINARY_FEATURE, props.getBoolean(BINARY_FEATURE, false)); conf.setPartitionerClass(PerItemTestPartitioner.class); conf.setInt(NUM_REDUCERS, conf.getNumReduceTasks()); AvroUtils.runAvroJob(conf);/*w w w. ja v a 2 s.c om*/ } }
From source file:com.linkedin.mlease.regression.jobs.ItemModelTrain.java
License:Open Source License
@Override public void run() throws Exception { JobConfig props = super.getJobConfig(); _logger.info("Start training per-key naive logistic regression model..."); String outBasePath = props.getString(OUTPUT_MODEL_PATH); String outpath = outBasePath + "/models"; props.put("output.path", outpath); JobConf conf = createJobConf(ItemModelTrainMapper.class, ItemModelTrainReducer.class, Pair.getPairSchema(Schema.create(Type.STRING), RegressionPrepareOutput.SCHEMA$), LinearModelWithVarAvro.SCHEMA$); // set up conf String interceptPriorMeanMap = props.getString(INTERCEPT_PRIOR_MEAN_MAP, ""); if (!interceptPriorMeanMap.equals("")) { AvroUtils.addAvroCacheFilesAndSetTheProperty(conf, new Path(interceptPriorMeanMap), INTERCEPT_PRIOR_MEAN_MAP); }//from ww w. j ava2s .c om String lambdaMap = props.getString(LAMBDA_MAP, ""); if (!lambdaMap.equals("")) { AvroUtils.addAvroCacheFilesAndSetTheProperty(conf, new Path(lambdaMap), LAMBDA_MAP); } conf.setFloat(INTERCEPT_DEFAULT_PRIOR_MEAN, (float) props.getDouble(INTERCEPT_DEFAULT_PRIOR_MEAN, 0)); conf.set(INTERCEPT_LAMBDAS, props.get(INTERCEPT_LAMBDAS)); conf.set(DEFAULT_LAMBDAS, props.get(DEFAULT_LAMBDAS)); conf.setLong(REPORT_FREQUENCY, props.getLong(REPORT_FREQUENCY, 1000000)); conf.setFloat(LIBLINEAR_EPSILON, (float) props.getDouble(LIBLINEAR_EPSILON, 0.001f)); conf.setBoolean(COMPUTE_VAR, props.getBoolean(COMPUTE_VAR, false)); conf.setBoolean(BINARY_FEATURE, props.getBoolean(BINARY_FEATURE, false)); conf.setBoolean(SHORT_FEATURE_INDEX, props.getBoolean(SHORT_FEATURE_INDEX, false)); // run job AvroUtils.runAvroJob(conf); boolean removeTmpDir = props.getBoolean(REMOVE_TMP_DIR, true); if (removeTmpDir) { FileSystem fs = FileSystem.get(conf); fs.delete(new Path(outBasePath + "/tmp-data"), true); } }
From source file:com.linkedin.mlease.regression.jobs.RegressionAdmmTrain.java
License:Open Source License
@Override public void run() throws Exception { _logger.info("Now running Regression Train using ADMM..."); JobConfig props = super.getJobConfig(); String outBasePath = props.getString(OUTPUT_BASE_PATH); JobConf conf = super.createJobConf(); // Various configs int nblocks = props.getInt(NUM_BLOCKS); int niter = props.getInt(NUM_ITERS, 10); //Aggressive decay of liblinear_epsilon boolean aggressiveLiblinearEpsilonDecay = props.getBoolean(AGGRESSIVE_LIBLINEAR_EPSILON_DECAY, false); // Getting the value of the regularizer L1/L2 int reg = props.getInt(REGULARIZER); if ((reg != 1) && (reg != 2)) { throw new IOException("Only L1 and L2 regularization supported!"); }// w w w. j av a 2 s. c o m int numClickReplicates = props.getInt(NUM_CLICK_REPLICATES, 1); boolean ignoreValue = props.getBoolean(BINARY_FEATURE, false); float initializeBoostRate = props.getFloat(INITIALIZE_BOOST_RATE, 0); float rhoAdaptCoefficient = props.getFloat(RHO_ADAPT_COEFFICIENT, 0); // handling lambda and rho // initialize z and u and compute z-u and write to hadoop Map<String, LinearModel> z = new HashMap<String, LinearModel>(); // lambda -> List<String> lambdastr = props.getStringList(LAMBDA, ","); List<String> rhostr = props.getStringList(RHO, null, ","); if (rhostr != null) { if (rhostr.size() != lambdastr.size()) throw new IOException( "The number of rho's should be exactly the same as the number of lambda's. OR: don't claim rho!"); } Map<Float, Float> lambdaRho = new HashMap<Float, Float>(); for (int j = 0; j < lambdastr.size(); j++) { float lambda = Float.parseFloat(lambdastr.get(j)); float rho; if (rhostr != null) { rho = Float.parseFloat(rhostr.get(j)); } else { if (lambda <= 100) { rho = 1; } else { rho = 10; } } lambdaRho.put(lambda, rho); z.put(String.valueOf(lambda), new LinearModel()); } // Get specific lambda treatment for some features String lambdaMapPath = props.getString(LAMBDA_MAP, ""); Map<String, Float> lambdaMap = new HashMap<String, Float>(); if (!lambdaMapPath.equals("")) { AvroHdfsFileReader reader = new AvroHdfsFileReader(conf); ReadLambdaMapConsumer consumer = new ReadLambdaMapConsumer(); reader.build(lambdaMapPath, consumer); consumer.done(); lambdaMap = consumer.get(); } _logger.info("Lambda Map has size = " + String.valueOf(lambdaMap.size())); // Write lambda_rho mapping into file String rhoPath = outBasePath + "/lambda-rho/part-r-00000.avro"; writeLambdaRho(conf, rhoPath, lambdaRho); // test-loglik computation boolean testLoglikPerIter = props.getBoolean(TEST_LOGLIK_PER_ITER, false); DataFileWriter<GenericRecord> testRecordWriter = null; // test if the test file exists String testPath = props.getString(TEST_PATH, ""); testLoglikPerIter = Util.checkPath(testPath); if (testLoglikPerIter) { List<Path> testPathList = AvroUtils.enumerateFiles(conf, new Path(testPath)); if (testPathList.size() > 0) { testPath = testPathList.get(0).toString(); _logger.info("Sample test path = " + testPath); AvroHdfsFileWriter<GenericRecord> writer = new AvroHdfsFileWriter<GenericRecord>(conf, outBasePath + "/sample-test-loglik/write-test-00000.avro", SampleTestLoglik.SCHEMA$); testRecordWriter = writer.get(); } } if (testRecordWriter == null) { testLoglikPerIter = false; _logger.info( "test.loglik.per.iter=false or test path doesn't exist or is empty! So we will not output test loglik per iteration."); } else { testRecordWriter.close(); } MutableFloat bestTestLoglik = new MutableFloat(-9999999); //Initialize z by mean model if (initializeBoostRate > 0 && reg == 2) { _logger.info("Now start mean model initializing......"); // Different paths for L1 vs L2 set from job file String initalModelPath; initalModelPath = outBasePath + "/initialModel"; Path initalModelPathFromNaiveTrain = new Path(outBasePath, "models"); JobConfig propsIni = JobConfig.clone(props); if (!propsIni.containsKey(LIBLINEAR_EPSILON)) { propsIni.put(LIBLINEAR_EPSILON, 0.01); } propsIni.put(RegressionNaiveTrain.HEAVY_PER_ITEM_TRAIN, "true"); propsIni.put(LAMBDA_MAP, lambdaMapPath); propsIni.put(REMOVE_TMP_DIR, "false"); // run job RegressionNaiveTrain initializationJob = new RegressionNaiveTrain( super.getJobId() + "_ADMMInitialization", propsIni); initializationJob.run(); FileSystem fs = initalModelPathFromNaiveTrain.getFileSystem(conf); if (fs.exists(new Path(initalModelPath))) { fs.delete(new Path(initalModelPath), true); } fs.rename(initalModelPathFromNaiveTrain, new Path(initalModelPath)); // set up lambda Set<Float> lambdaSet = new HashSet<Float>(); for (String l : lambdastr) { lambdaSet.add(Float.parseFloat(l)); } // Compute Mean model as initial model z = LinearModelUtils.meanModel(conf, initalModelPath, nblocks, lambdaSet.size(), true); if (testLoglikPerIter) { updateLogLikBestModel(conf, 0, z, testPath, ignoreValue, bestTestLoglik, outBasePath, numClickReplicates); } } double mindiff = 99999999; float liblinearEpsilon = 0.01f; int i; for (i = 1; i <= niter; i++) { _logger.info("Now starting iteration " + String.valueOf(i)); // set up configuration props.put(AbstractAvroJob.OUTPUT_PATH, outBasePath + "/iter-" + String.valueOf(i)); conf = createJobConf(AdmmMapper.class, AdmmReducer.class, Pair.getPairSchema(Schema.create(Type.INT), RegressionPrepareOutput.SCHEMA$), RegressionTrainOutput.SCHEMA$); conf.setPartitionerClass(AdmmPartitioner.class); //AvroUtils.setSpecificReducerInput(conf, true); conf.setInt(NUM_BLOCKS, nblocks); //Added for L1/L2 conf.setInt(REGULARIZER, reg); conf.setLong(REPORT_FREQUENCY, props.getLong(REPORT_FREQUENCY, 1000000)); //boolean ignoreValue = props.getBoolean(BINARY_FEATURE, false); conf.setBoolean(BINARY_FEATURE, ignoreValue); conf.setBoolean(SHORT_FEATURE_INDEX, props.getBoolean(SHORT_FEATURE_INDEX, false)); boolean penalizeIntercept = props.getBoolean(PENALIZE_INTERCEPT, false); String interceptKey = props.getString(INTERCEPT_KEY, LibLinearDataset.INTERCEPT_NAME); conf.set(INTERCEPT_KEY, interceptKey); //int schemaType = props.getInt(SCHEMA_TYPE, 1); // compute and store u into file // u = uplusx - z String uPath = outBasePath + "/iter-" + String.valueOf(i) + "/u/part-r-00000.avro"; if (i == 1) { LinearModelUtils.writeLinearModel(conf, uPath, new HashMap<String, LinearModel>()); if (initializeBoostRate > 0 && reg == 2) { conf.setFloat(RHO_ADAPT_RATE, initializeBoostRate); } } else { String uplusxPath = outBasePath + "/iter-" + String.valueOf(i - 1) + "/model"; computeU(conf, uPath, uplusxPath, z); if (rhoAdaptCoefficient > 0) { float curRhoAdaptRate = (float) Math.exp(-(i - 1) * rhoAdaptCoefficient); conf.setFloat(RHO_ADAPT_RATE, curRhoAdaptRate); } } // write z into file String zPath = outBasePath + "/iter-" + String.valueOf(i) + "/init-value/part-r-00000.avro"; LinearModelUtils.writeLinearModel(conf, zPath, z); // run job String outpath = outBasePath + "/iter-" + String.valueOf(i) + "/model"; conf.set(U_PATH, uPath); conf.set(INIT_VALUE_PATH, zPath); conf.set(LAMBDA_RHO_MAP, rhoPath); if (i > 1 && mindiff < 0.001 && !aggressiveLiblinearEpsilonDecay) // need to get a more accurate estimate from liblinear { liblinearEpsilon = liblinearEpsilon / 10; } else if (aggressiveLiblinearEpsilonDecay && i > 5) { liblinearEpsilon = liblinearEpsilon / 10; } conf.setFloat(LIBLINEAR_EPSILON, liblinearEpsilon); //Added for logging aggressive decay _logger.info("Liblinear Epsilon for iter = " + String.valueOf(i) + " is: " + String.valueOf(liblinearEpsilon)); _logger.info("aggressiveLiblinearEpsilonDecay=" + aggressiveLiblinearEpsilonDecay); AvroOutputFormat.setOutputPath(conf, new Path(outpath)); AvroUtils.addAvroCacheFiles(conf, new Path(uPath)); AvroUtils.addAvroCacheFiles(conf, new Path(zPath)); AvroUtils.addAvroCacheFiles(conf, new Path(rhoPath)); conf.setNumReduceTasks(nblocks * lambdastr.size()); AvroJob.setInputSchema(conf, RegressionPrepareOutput.SCHEMA$); AvroUtils.runAvroJob(conf); // Load the result from the last iteration // compute z and u given x Map<String, LinearModel> xbar = LinearModelUtils.meanModel(conf, outpath, nblocks, lambdaRho.size(), true); Map<String, LinearModel> ubar = LinearModelUtils.meanModel(conf, uPath, nblocks, lambdaRho.size(), false); Map<String, LinearModel> lastz = new HashMap<String, LinearModel>(); for (String k : z.keySet()) { lastz.put(k, z.get(k).copy()); } for (String lambda : xbar.keySet()) { LinearModel thisz = z.get(lambda); thisz.clear(); float l = Float.parseFloat(lambda); float r = lambdaRho.get(l); double weight; //L2 regularization if (reg == 2) { _logger.info("Running code for regularizer = " + String.valueOf(reg)); weight = nblocks * r / (l + nblocks * r); Map<String, Double> weightmap = new HashMap<String, Double>(); for (String k : lambdaMap.keySet()) { weightmap.put(k, nblocks * r / (lambdaMap.get(k) + nblocks * r + 0.0)); } thisz.linearCombine(1.0, weight, xbar.get(lambda), weightmap); if (!ubar.isEmpty()) { thisz.linearCombine(1.0, weight, ubar.get(lambda), weightmap); } if (!penalizeIntercept) { if (ubar.isEmpty()) { thisz.setIntercept(xbar.get(lambda).getIntercept()); } else { thisz.setIntercept(xbar.get(lambda).getIntercept() + ubar.get(lambda).getIntercept()); } } z.put(lambda, thisz); } else { // L1 regularization _logger.info("Running code for regularizer = " + String.valueOf(reg)); weight = l / (r * nblocks + 0.0); Map<String, Double> weightmap = new HashMap<String, Double>(); for (String k : lambdaMap.keySet()) { weightmap.put(k, lambdaMap.get(k) / (r * nblocks + 0.0)); } // LinearModel thisz = new LinearModel(); thisz.linearCombine(1.0, 1.0, xbar.get(lambda)); if (!ubar.isEmpty()) { thisz.linearCombine(1.0, 1.0, ubar.get(lambda)); } // Iterative Thresholding Map<String, Double> thisCoefficients = thisz.getCoefficients(); for (String k : thisCoefficients.keySet()) { double val = thisCoefficients.get(k); if (val > weight) { thisCoefficients.put(k, val - weight); } else if (val < -weight) { thisCoefficients.put(k, val + weight); } } thisz.setCoefficients(thisCoefficients); if (!penalizeIntercept) { if (ubar.isEmpty()) { thisz.setIntercept(xbar.get(lambda).getIntercept()); } else { thisz.setIntercept(xbar.get(lambda).getIntercept() + ubar.get(lambda).getIntercept()); } } z.put(lambda, thisz); } } xbar.clear(); ubar.clear(); // Output max difference between last z and this z mindiff = 99999999; double maxdiff = 0; for (String k : z.keySet()) { LinearModel tmp = lastz.get(k); if (tmp == null) tmp = new LinearModel(); tmp.linearCombine(1, -1, z.get(k)); double diff = tmp.maxAbsValue(); _logger.info( "For lambda=" + k + ": Max Difference between last z and this z = " + String.valueOf(diff)); tmp.clear(); if (mindiff > diff) mindiff = diff; if (maxdiff < diff) maxdiff = diff; } double epsilon = props.getDouble(EPSILON, 0.0001); // remove tmp files? if (props.getBoolean(REMOVE_TMP_DIR, false) && i >= 2) { FileSystem fs = FileSystem.get(conf); fs.delete(new Path(outBasePath + "/iter-" + String.valueOf(i - 1)), true); } // Output testloglik and update best model if (testLoglikPerIter) { updateLogLikBestModel(conf, i, z, testPath, ignoreValue, bestTestLoglik, outBasePath, numClickReplicates); } if (maxdiff < epsilon && liblinearEpsilon <= 0.00001) { break; } } // write z into file String zPath = outBasePath + "/final-model/part-r-00000.avro"; LinearModelUtils.writeLinearModel(conf, zPath, z); // remove tmp files? if (props.getBoolean(REMOVE_TMP_DIR, false)) { FileSystem fs = FileSystem.get(conf); Path initalModelPath = new Path(outBasePath + "/initialModel"); if (fs.exists(initalModelPath)) { fs.delete(initalModelPath, true); } for (int j = i - 2; j <= i; j++) { Path deletepath = new Path(outBasePath + "/iter-" + String.valueOf(j)); if (fs.exists(deletepath)) { fs.delete(deletepath, true); } } fs.delete(new Path(outBasePath + "/tmp-data"), true); } }
From source file:com.linkedin.mlease.regression.jobs.RegressionNaiveTrain.java
License:Open Source License
@Override public void run() throws Exception { JobConfig props = super.getJobConfig(); String outBasePath = props.getString(OUTPUT_BASE_PATH); boolean heavyPerItemTrain = props.getBoolean(HEAVY_PER_ITEM_TRAIN, false); String partitionIdPath = ""; if (heavyPerItemTrain) { partitionIdPath = outBasePath + "/partitionIds"; props.put(AbstractAvroJob.OUTPUT_PATH, partitionIdPath); JobConf conf = createJobConf(PartitionIdAssignerMapper.class, PartitionIdAssignerReducer.class, PartitionIdAssignerCombiner.class, Pair.getPairSchema(Schema.create(Type.STRING), Schema.create(Type.INT)), Pair.getPairSchema(Schema.create(Type.STRING), Schema.create(Type.INT))); conf.set(LAMBDA, props.getString(LAMBDA)); AvroJob.setInputSchema(conf, RegressionPrepareOutput.SCHEMA$); conf.setNumReduceTasks(1);/*from ww w.j a v a 2 s . c om*/ AvroUtils.runAvroJob(conf); } _logger.info("Start training per-key naive logistic regression model..."); String outpath = outBasePath + "/models"; props.put(AbstractAvroJob.OUTPUT_PATH, outpath); JobConf conf = createJobConf(NaiveMapper.class, NaiveReducer.class, Pair.getPairSchema(Schema.create(Type.STRING), RegressionPrepareOutput.SCHEMA$), LinearModelAvro.SCHEMA$); // set up conf boolean computeModelMean = props.getBoolean(COMPUTE_MODEL_MEAN, true); int nblocks = -1; if (computeModelMean) { nblocks = props.getInt(NUM_BLOCKS); conf.setInt(NUM_BLOCKS, nblocks); } List<String> lambdastr = props.getStringList(LAMBDA, ","); conf.set(LAMBDA, props.getString(LAMBDA)); conf.setFloat(PRIOR_MEAN, props.getFloat(PRIOR_MEAN, 0.0)); conf.setBoolean(PENALIZE_INTERCEPT, props.getBoolean(PENALIZE_INTERCEPT, false)); conf.setBoolean(HAS_INTERCEPT, props.getBoolean(HAS_INTERCEPT, true)); conf.set(INTERCEPT_KEY, props.getString(INTERCEPT_KEY, LIBLINEAR_INTERCEPT_KEY)); conf.setLong(REPORT_FREQUENCY, props.getLong(REPORT_FREQUENCY, 1000000)); boolean removeTmpDir = props.getBoolean(REMOVE_TMP_DIR, true); conf.setFloat(LIBLINEAR_EPSILON, props.getFloat(LIBLINEAR_EPSILON, 0.001f)); String lambdaMap = props.getString(LAMBDA_MAP, ""); conf.set(LAMBDA_MAP, lambdaMap); if (!lambdaMap.equals("")) { AvroUtils.addAvroCacheFiles(conf, new Path(lambdaMap)); } conf.setBoolean(BINARY_FEATURE, props.getBoolean(BINARY_FEATURE, false)); conf.setBoolean(SHORT_FEATURE_INDEX, props.getBoolean(SHORT_FEATURE_INDEX, false)); // set up lambda Set<Float> lambdaSet = new HashSet<Float>(); for (String l : lambdastr) { lambdaSet.add(Float.parseFloat(l)); } conf.setInt(DATA_SIZE_THRESHOLD, props.getInt(DATA_SIZE_THRESHOLD, 0)); // set up partition id if (heavyPerItemTrain && !partitionIdPath.equals("")) { conf.set(PARTITION_ID_PATH, partitionIdPath); AvroHdfsFileReader reader = new AvroHdfsFileReader(conf); ReadPartitionIdAssignmentConsumer consumer = new ReadPartitionIdAssignmentConsumer(); reader.build(partitionIdPath, consumer); Map<String, Integer> partitionIdMap = consumer.get(); int maxPartitionId = 0; for (int v : partitionIdMap.values()) { if (v > maxPartitionId) { maxPartitionId = v; } } AvroUtils.addAvroCacheFiles(conf, new Path(partitionIdPath)); conf.setNumReduceTasks(maxPartitionId + 1); conf.setPartitionerClass(NaivePartitioner.class); } // run job AvroJob.setInputSchema(conf, RegressionPrepareOutput.SCHEMA$); AvroUtils.runAvroJob(conf); // Compute Mean if (computeModelMean) { Map<String, LinearModel> betabar = LinearModelUtils.meanModel(conf, outpath, nblocks, lambdaSet.size(), true); // Output the mean for each lambda // write z into file String finalOutPath = outBasePath + "/final-model/part-r-00000.avro"; LinearModelUtils.writeLinearModel(conf, finalOutPath, betabar); } // remove tmp dir if (removeTmpDir) { FileSystem fs = FileSystem.get(conf); fs.delete(new Path(outBasePath + "/tmp-data"), true); } }
From source file:com.linkedin.mlease.regression.jobs.RegressionPrepare.java
License:Open Source License
@Override public void run() throws Exception { JobConfig config = super.getJobConfig(); JobConf conf = super.createJobConf(RegressionPrepareMapper.class, RegressionPrepareOutput.SCHEMA$); String mapKey = config.getString(MAP_KEY, ""); conf.set(MAP_KEY, mapKey); conf.setInt(NUM_CLICK_REPLICATES, config.getInt(NUM_CLICK_REPLICATES, 1)); conf.setBoolean(IGNORE_FEATURE_VALUE, config.getBoolean(IGNORE_FEATURE_VALUE, false)); int nblocks = config.getInt(NUM_BLOCKS, 0); conf.setInt(NUM_BLOCKS, nblocks);/*from ww w . j ava 2s . c o m*/ _logger.info("Running the preparation job of admm with map.key = " + mapKey + " and num.blocks=" + nblocks); AvroUtils.runAvroJob(conf); }
From source file:com.linkedin.mlease.regression.jobs.RegressionTest.java
License:Open Source License
@Override public void run() throws Exception { JobConfig props = super.getJobConfig(); JobConf conf = super.createJobConf(); if (!props.getString("input.paths").equals("")) { // set up configuration _logger.info("Now starting test..."); List<String> lambdastr = props.getStringList(LAMBDA, ","); String outBasePath = props.getString(OUTPUT_BASE_PATH); for (String lambda : lambdastr) { String outPath = outBasePath + "/lambda-" + lambda; props.put(AbstractAvroJob.OUTPUT_PATH, outPath); conf = createJobConf(AdmmTestMapper.class, AdmmTestReducer.class); AvroOutputFormat.setOutputPath(conf, new Path(outPath)); String modelPath = props.getString(MODEL_BASE_PATH); modelPath = modelPath + "/final-model"; AvroUtils.addAvroCacheFiles(conf, new Path(modelPath)); conf.set(MODEL_PATH, modelPath); conf.setFloat(LAMBDA, Float.parseFloat(lambda)); conf.setBoolean(BINARY_FEATURE, props.getBoolean(BINARY_FEATURE, false)); AvroJob.setInputSchema(conf, AvroUtils.getAvroInputSchema(conf)); AvroUtils.runAvroJob(conf);//w w w. j a va 2 s .c o m } // also do full prediction on best-model if it exists FileSystem fs = FileSystem.get(conf); String modelPath = props.getString(MODEL_BASE_PATH) + "/best-model"; if (fs.exists(new Path(modelPath))) { String outPath = outBasePath + "/best-model"; props.put(AbstractAvroJob.OUTPUT_PATH, outPath); conf = createJobConf(AdmmTestMapper.class, AdmmTestReducer.class); AvroOutputFormat.setOutputPath(conf, new Path(outPath)); AvroUtils.addAvroCacheFiles(conf, new Path(modelPath)); conf.set(MODEL_PATH, modelPath); conf.setFloat(LAMBDA, -1); conf.setBoolean(BINARY_FEATURE, props.getBoolean(BINARY_FEATURE, false)); AvroJob.setInputSchema(conf, AvroUtils.getAvroInputSchema(conf)); AvroUtils.runAvroJob(conf); } } else { _logger.info("test.input.paths is empty! So no test will be done!"); } }
From source file:com.liveramp.cascading_ext.bloom.BloomAssemblyStrategy.java
License:Apache License
private void prepareBloomFilterBuilder(FlowStep<JobConf> currentStep) { JobConf currentStepConf = currentStep.getConfig(); currentStepConf.set("mapred.reduce.tasks", Integer.toString(BloomProps.getNumSplits(currentStepConf))); currentStepConf.set("io.sort.record.percent", Double.toString(BloomProps.getIOSortPercent(currentStepConf))); }
From source file:com.liveramp.cascading_ext.bloom.BloomAssemblyStrategy.java
License:Apache License
/** * Merges bloom filter parts created across multiple splits of the keys and put the result in the distributed cache. *///from w w w .j a v a2 s . c o m private void buildBloomfilter(String bloomID, FlowStep<JobConf> currentStep, List<FlowStep<JobConf>> predecessorSteps) { try { JobConf currentStepConf = currentStep.getConfig(); currentStepConf.set("io.sort.mb", Integer.toString(BloomProps.getBufferSize(currentStepConf))); currentStepConf.set("mapred.job.reuse.jvm.num.tasks", "-1"); String requiredBloomPath = currentStepConf.get(BloomProps.REQUIRED_BLOOM_FILTER_PATH); for (FlowStep<JobConf> step : predecessorSteps) { JobConf prevStepConf = step.getConfig(); String targetBloomID = prevStepConf.get(BloomProps.TARGET_BLOOM_FILTER_ID); if (bloomID.equals(targetBloomID)) { LOG.info("Found step generating required bloom filter: " + targetBloomID); // Extract the counters from the previous job to approximate the average key/tuple size FlowStepStats stats = ((BaseFlowStep) step).getFlowStepStats(); // Collect some of the stats gathered. This will help configure the bloom filter long numSampled = Counters.get(stats, CreateBloomFilter.StatsCounters.TOTAL_SAMPLED_TUPLES); long keySizeSum = Counters.get(stats, CreateBloomFilter.StatsCounters.KEY_SIZE_SUM); long matchSizeSum = Counters.get(stats, CreateBloomFilter.StatsCounters.TUPLE_SIZE_SUM); int avgKeySize = 0; int avgMatchSize = 0; if (numSampled != 0) { avgKeySize = (int) (keySizeSum / numSampled); avgMatchSize = (int) (matchSizeSum / numSampled); } LOG.info("Avg key size ~= " + avgKeySize); LOG.info("Avg match size ~= " + avgMatchSize); for (Map.Entry<String, String> entry : BloomUtil .getPropertiesForBloomFilter(avgMatchSize, avgKeySize).entrySet()) { currentStepConf.set(entry.getKey(), entry.getValue()); } // Put merged result in distributed cache LOG.info("Adding dist cache properties to config:"); for (Map.Entry<String, String> prop : BloomUtil.getPropertiesForDistCache(requiredBloomPath) .entrySet()) { LOG.info(prop.getKey() + " = " + prop.getValue()); String previousProperty = currentStepConf.get(prop.getKey()); if (previousProperty != null) { LOG.info("found already existing value for key: " + prop.getKey() + ", found " + previousProperty + ". Appending."); currentStepConf.set(prop.getKey(), previousProperty + "," + prop.getValue()); } else { currentStepConf.set(prop.getKey(), prop.getValue()); } } BloomUtil.writeFilterToHdfs(prevStepConf, requiredBloomPath); } } } catch (Exception e) { throw new RuntimeException("Failed to create bloom filter!", e); } }
From source file:com.liveramp.hank.cascading.DomainBuilderTap.java
License:Apache License
public void sinkConfInit(FlowProcess<JobConf> process, JobConf conf) { super.sinkConfInit(process, conf); // Output Format conf.setOutputFormat(this.outputFormatClass); // Output Committer conf.setOutputCommitter(DomainBuilderOutputCommitter.class); // Set this tap's Domain name locally in the conf if (conf.get(DomainBuilderAbstractOutputFormat.CONF_PARAM_HANK_DOMAIN_NAME) != null) { throw new RuntimeException("Trying to set domain name configuration parameter to " + domainName + " but it was previously set to " + conf.get(DomainBuilderAbstractOutputFormat.CONF_PARAM_HANK_DOMAIN_NAME)); } else {//from www. j a v a 2 s. com conf.set(DomainBuilderAbstractOutputFormat.CONF_PARAM_HANK_DOMAIN_NAME, domainName); } }