List of usage examples for org.apache.mahout.common HadoopUtil countRecords
public static long countRecords(Path path, PathType pt, PathFilter filter, Configuration conf) throws IOException
From source file:org.gpfvic.mahout.cf.taste.hadoop.item.RecommenderJob.java
License:Apache License
public int run(String[] args) throws Exception { addInputOption();//from w w w . ja v a 2 s . c om addOutputOption(); addOption("numRecommendations", "n", "Number of recommendations per user", String.valueOf(AggregateAndRecommendReducer.DEFAULT_NUM_RECOMMENDATIONS)); addOption("usersFile", null, "File of users to recommend for", null); addOption("itemsFile", null, "File of items to recommend for", null); addOption("filterFile", "f", "File containing comma-separated userID,itemID pairs. Used to exclude the item from " + "the recommendations for that user (optional)", null); addOption("userItemFile", "uif", "File containing comma-separated userID,itemID pairs (optional). " + "Used to include only these items into recommendations. " + "Cannot be used together with usersFile or itemsFile", null); addOption("booleanData", "b", "Treat input as without pref values", Boolean.FALSE.toString()); addOption("maxPrefsPerUser", "mxp", "Maximum number of preferences considered per user in final recommendation phase", String.valueOf(UserVectorSplitterMapper.DEFAULT_MAX_PREFS_PER_USER_CONSIDERED)); addOption("minPrefsPerUser", "mp", "ignore users with less preferences than this in the similarity computation " + "(default: " + DEFAULT_MIN_PREFS_PER_USER + ')', String.valueOf(DEFAULT_MIN_PREFS_PER_USER)); addOption("maxSimilaritiesPerItem", "m", "Maximum number of similarities considered per item ", String.valueOf(DEFAULT_MAX_SIMILARITIES_PER_ITEM)); addOption("maxPrefsInItemSimilarity", "mpiis", "max number of preferences to consider per user or item in the " + "item similarity computation phase, users or items with more preferences will be sampled down (default: " + DEFAULT_MAX_PREFS + ')', String.valueOf(DEFAULT_MAX_PREFS)); addOption("similarityClassname", "s", "Name of distributed similarity measures class to instantiate, " + "alternatively use one of the predefined similarities (" + VectorSimilarityMeasures.list() + ')', true); addOption("threshold", "tr", "discard item pairs with a similarity value below this", false); addOption("outputPathForSimilarityMatrix", "opfsm", "write the item similarity matrix to this path (optional)", false); addOption("randomSeed", null, "use this seed for sampling", false); addFlag("sequencefileOutput", null, "write the output into a SequenceFile instead of a text file"); Map<String, List<String>> parsedArgs = parseArguments(args); if (parsedArgs == null) { return -1; } Path outputPath = getOutputPath(); int numRecommendations = Integer.parseInt(getOption("numRecommendations")); String usersFile = getOption("usersFile"); String itemsFile = getOption("itemsFile"); String filterFile = getOption("filterFile"); String userItemFile = getOption("userItemFile"); boolean booleanData = Boolean.valueOf(getOption("booleanData")); int maxPrefsPerUser = Integer.parseInt(getOption("maxPrefsPerUser")); int minPrefsPerUser = Integer.parseInt(getOption("minPrefsPerUser")); int maxPrefsInItemSimilarity = Integer.parseInt(getOption("maxPrefsInItemSimilarity")); int maxSimilaritiesPerItem = Integer.parseInt(getOption("maxSimilaritiesPerItem")); String similarityClassname = getOption("similarityClassname"); double threshold = hasOption("threshold") ? Double.parseDouble(getOption("threshold")) : RowSimilarityJob.NO_THRESHOLD; long randomSeed = hasOption("randomSeed") ? Long.parseLong(getOption("randomSeed")) : RowSimilarityJob.NO_FIXED_RANDOM_SEED; Path prepPath = getTempPath(DEFAULT_PREPARE_PATH); Path similarityMatrixPath = getTempPath("similarityMatrix"); Path explicitFilterPath = getTempPath("explicitFilterPath"); Path partialMultiplyPath = getTempPath("partialMultiply"); AtomicInteger currentPhase = new AtomicInteger(); int numberOfUsers = -1; if (shouldRunNextPhase(parsedArgs, currentPhase)) { ToolRunner.run(getConf(), new PreparePreferenceMatrixJob(), new String[] { "--input", getInputPath().toString(), "--output", prepPath.toString(), "--minPrefsPerUser", String.valueOf(minPrefsPerUser), "--booleanData", String.valueOf(booleanData), "--tempDir", getTempPath().toString(), }); numberOfUsers = HadoopUtil.readInt(new Path(prepPath, PreparePreferenceMatrixJob.NUM_USERS), getConf()); } if (shouldRunNextPhase(parsedArgs, currentPhase)) { /* special behavior if phase 1 is skipped */ if (numberOfUsers == -1) { numberOfUsers = (int) HadoopUtil.countRecords( new Path(prepPath, PreparePreferenceMatrixJob.USER_VECTORS), PathType.LIST, null, getConf()); } //calculate the co-occurrence matrix ToolRunner.run(getConf(), new RowSimilarityJob(), new String[] { "--input", new Path(prepPath, PreparePreferenceMatrixJob.RATING_MATRIX).toString(), "--output", similarityMatrixPath.toString(), "--numberOfColumns", String.valueOf(numberOfUsers), "--similarityClassname", similarityClassname, "--maxObservationsPerRow", String.valueOf(maxPrefsInItemSimilarity), "--maxObservationsPerColumn", String.valueOf(maxPrefsInItemSimilarity), "--maxSimilaritiesPerRow", String.valueOf(maxSimilaritiesPerItem), "--excludeSelfSimilarity", String.valueOf(Boolean.TRUE), "--threshold", String.valueOf(threshold), "--randomSeed", String.valueOf(randomSeed), "--tempDir", getTempPath().toString(), }); // write out the similarity matrix if the user specified that behavior if (hasOption("outputPathForSimilarityMatrix")) { Path outputPathForSimilarityMatrix = new Path(getOption("outputPathForSimilarityMatrix")); Job outputSimilarityMatrix = prepareJob(similarityMatrixPath, outputPathForSimilarityMatrix, SequenceFileInputFormat.class, ItemSimilarityJob.MostSimilarItemPairsMapper.class, EntityEntityWritable.class, DoubleWritable.class, ItemSimilarityJob.MostSimilarItemPairsReducer.class, EntityEntityWritable.class, DoubleWritable.class, TextOutputFormat.class); Configuration mostSimilarItemsConf = outputSimilarityMatrix.getConfiguration(); mostSimilarItemsConf.set(ItemSimilarityJob.ITEM_ID_INDEX_PATH_STR, new Path(prepPath, PreparePreferenceMatrixJob.ITEMID_INDEX).toString()); mostSimilarItemsConf.setInt(ItemSimilarityJob.MAX_SIMILARITIES_PER_ITEM, maxSimilaritiesPerItem); outputSimilarityMatrix.waitForCompletion(true); } } //start the multiplication of the co-occurrence matrix by the user vectors if (shouldRunNextPhase(parsedArgs, currentPhase)) { Job partialMultiply = new Job(getConf(), "partialMultiply"); Configuration partialMultiplyConf = partialMultiply.getConfiguration(); MultipleInputs.addInputPath(partialMultiply, similarityMatrixPath, SequenceFileInputFormat.class, SimilarityMatrixRowWrapperMapper.class); MultipleInputs.addInputPath(partialMultiply, new Path(prepPath, PreparePreferenceMatrixJob.USER_VECTORS), SequenceFileInputFormat.class, UserVectorSplitterMapper.class); partialMultiply.setJarByClass(ToVectorAndPrefReducer.class); partialMultiply.setMapOutputKeyClass(VarIntWritable.class); partialMultiply.setMapOutputValueClass(VectorOrPrefWritable.class); partialMultiply.setReducerClass(ToVectorAndPrefReducer.class); partialMultiply.setOutputFormatClass(SequenceFileOutputFormat.class); partialMultiply.setOutputKeyClass(VarIntWritable.class); partialMultiply.setOutputValueClass(VectorAndPrefsWritable.class); partialMultiplyConf.setBoolean("mapred.compress.map.output", true); partialMultiplyConf.set("mapred.output.dir", partialMultiplyPath.toString()); if (usersFile != null) { partialMultiplyConf.set(UserVectorSplitterMapper.USERS_FILE, usersFile); } if (userItemFile != null) { partialMultiplyConf.set(IDReader.USER_ITEM_FILE, userItemFile); } partialMultiplyConf.setInt(UserVectorSplitterMapper.MAX_PREFS_PER_USER_CONSIDERED, maxPrefsPerUser); boolean succeeded = partialMultiply.waitForCompletion(true); if (!succeeded) { return -1; } } if (shouldRunNextPhase(parsedArgs, currentPhase)) { //filter out any users we don't care about /* convert the user/item pairs to filter if a filterfile has been specified */ if (filterFile != null) { Job itemFiltering = prepareJob(new Path(filterFile), explicitFilterPath, TextInputFormat.class, ItemFilterMapper.class, VarLongWritable.class, VarLongWritable.class, ItemFilterAsVectorAndPrefsReducer.class, VarIntWritable.class, VectorAndPrefsWritable.class, SequenceFileOutputFormat.class); boolean succeeded = itemFiltering.waitForCompletion(true); if (!succeeded) { return -1; } } String aggregateAndRecommendInput = partialMultiplyPath.toString(); if (filterFile != null) { aggregateAndRecommendInput += "," + explicitFilterPath; } Class<? extends OutputFormat> outputFormat = parsedArgs.containsKey("--sequencefileOutput") ? SequenceFileOutputFormat.class : TextOutputFormat.class; //extract out the recommendations Job aggregateAndRecommend = prepareJob(new Path(aggregateAndRecommendInput), outputPath, SequenceFileInputFormat.class, PartialMultiplyMapper.class, VarLongWritable.class, PrefAndSimilarityColumnWritable.class, AggregateAndRecommendReducer.class, VarLongWritable.class, RecommendedItemsWritable.class, outputFormat); Configuration aggregateAndRecommendConf = aggregateAndRecommend.getConfiguration(); if (itemsFile != null) { aggregateAndRecommendConf.set(AggregateAndRecommendReducer.ITEMS_FILE, itemsFile); } if (userItemFile != null) { aggregateAndRecommendConf.set(IDReader.USER_ITEM_FILE, userItemFile); } if (filterFile != null) { setS3SafeCombinedInputPath(aggregateAndRecommend, getTempPath(), partialMultiplyPath, explicitFilterPath); } setIOSort(aggregateAndRecommend); aggregateAndRecommendConf.set(AggregateAndRecommendReducer.ITEMID_INDEX_PATH, new Path(prepPath, PreparePreferenceMatrixJob.ITEMID_INDEX).toString()); aggregateAndRecommendConf.setInt(AggregateAndRecommendReducer.NUM_RECOMMENDATIONS, numRecommendations); aggregateAndRecommendConf.setBoolean(BOOLEAN_DATA, booleanData); boolean succeeded = aggregateAndRecommend.waitForCompletion(true); if (!succeeded) { return -1; } } return 0; }