List of usage examples for java.util HashMap get
public V get(Object key)
From source file:com.example.bigtable.simplecli.HBaseCLI.java
/** * The main method for the CLI. This method takes the command line * arguments and runs the appropriate commands. *///ww w . j a va 2 s. c o m public static void main(String[] args) { // We use Apache commons-cli to check for a help option. Options options = new Options(); Option help = new Option("help", "print this message"); options.addOption(help); // create the parser CommandLineParser parser = new BasicParser(); CommandLine line = null; try { // parse the command line arguments line = parser.parse(options, args); } catch (ParseException exp) { // oops, something went wrong System.err.println(exp.getMessage()); usage(); System.exit(1); } // Create a list of commands that are supported. Each // command defines a run method and some methods for // printing help. // See the definition of each command below. HashMap<String, Command> commands = new HashMap<String, Command>(); commands.put("create", new CreateCommand("create")); commands.put("scan", new ScanCommand("scan")); commands.put("get", new GetCommand("get")); commands.put("put", new PutCommand("put")); commands.put("list", new ListCommand("list")); Command command = null; List<String> argsList = Arrays.asList(args); if (argsList.size() > 0) { command = commands.get(argsList.get(0)); } // Check for the help option and if it's there // display the appropriate help. if (line.hasOption("help")) { // If there is a command listed (e.g. create -help) // then show the help for that command if (command == null) { help(commands.values()); } else { help(command); } System.exit(0); } else if (command == null) { // No valid command was given so print the usage. usage(); System.exit(0); } try { Connection connection = ConnectionFactory.createConnection(); try { try { // Run the command with the arguments after the command name. command.run(connection, argsList.subList(1, argsList.size())); } catch (InvalidArgsException e) { System.out.println("ERROR: Invalid arguments"); usage(command); System.exit(0); } } finally { // Make sure the connection is closed even if // an exception occurs. connection.close(); } } catch (IOException e) { e.printStackTrace(); } }
From source file:ch.epfl.lsir.xin.test.SVDPPTest.java
/** * @param args/* w w w . ja v a 2 s. c om*/ */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub PrintWriter logger = new PrintWriter(".//results//SVDPP"); PropertiesConfiguration config = new PropertiesConfiguration(); config.setFile(new File("conf//SVDPlusPlus.properties")); try { config.load(); } catch (ConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Read rating data..."); logger.flush(); DataLoaderFile loader = new DataLoaderFile(".//data//MoveLens100k.txt"); loader.readSimple(); DataSetNumeric dataset = loader.getDataset(); System.out.println("Number of ratings: " + dataset.getRatings().size() + " Number of users: " + dataset.getUserIDs().size() + " Number of items: " + dataset.getItemIDs().size()); logger.println("Number of ratings: " + dataset.getRatings().size() + ", Number of users: " + dataset.getUserIDs().size() + ", Number of items: " + dataset.getItemIDs().size()); logger.flush(); double totalMAE = 0; double totalRMSE = 0; double totalPrecision = 0; double totalRecall = 0; double totalMAP = 0; double totalNDCG = 0; double totalMRR = 0; double totalAUC = 0; int F = 5; logger.println(F + "- folder cross validation."); logger.flush(); ArrayList<ArrayList<NumericRating>> folders = new ArrayList<ArrayList<NumericRating>>(); for (int i = 0; i < F; i++) { folders.add(new ArrayList<NumericRating>()); } while (dataset.getRatings().size() > 0) { int index = new Random().nextInt(dataset.getRatings().size()); int r = new Random().nextInt(F); folders.get(r).add(dataset.getRatings().get(index)); dataset.getRatings().remove(index); } for (int folder = 1; folder <= F; folder++) { System.out.println("Folder: " + folder); logger.println("Folder: " + folder); logger.flush(); ArrayList<NumericRating> trainRatings = new ArrayList<NumericRating>(); ArrayList<NumericRating> testRatings = new ArrayList<NumericRating>(); for (int i = 0; i < folders.size(); i++) { if (i == folder - 1)//test data { testRatings.addAll(folders.get(i)); } else {//training data trainRatings.addAll(folders.get(i)); } } //create rating matrix HashMap<String, Integer> userIDIndexMapping = new HashMap<String, Integer>(); HashMap<String, Integer> itemIDIndexMapping = new HashMap<String, Integer>(); for (int i = 0; i < dataset.getUserIDs().size(); i++) { userIDIndexMapping.put(dataset.getUserIDs().get(i), i); } for (int i = 0; i < dataset.getItemIDs().size(); i++) { itemIDIndexMapping.put(dataset.getItemIDs().get(i), i); } RatingMatrix trainRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < trainRatings.size(); i++) { trainRatingMatrix.set(userIDIndexMapping.get(trainRatings.get(i).getUserID()), itemIDIndexMapping.get(trainRatings.get(i).getItemID()), trainRatings.get(i).getValue()); } RatingMatrix testRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < testRatings.size(); i++) { if (testRatings.get(i).getValue() < 5) continue; testRatingMatrix.set(userIDIndexMapping.get(testRatings.get(i).getUserID()), itemIDIndexMapping.get(testRatings.get(i).getItemID()), testRatings.get(i).getValue()); } System.out.println("Training: " + trainRatingMatrix.getTotalRatingNumber() + " vs Test: " + testRatingMatrix.getTotalRatingNumber()); logger.println("Initialize a SVD++ recommendation model."); logger.flush(); SVDPlusPlus algo = new SVDPlusPlus(trainRatingMatrix, false, ".//localModels//" + config.getString("NAME")); algo.setLogger(logger); algo.build(); algo.saveModel(".//localModels//" + config.getString("NAME")); logger.println("Save the model."); logger.flush(); //rating prediction accuracy double RMSE = 0; double MAE = 0; double precision = 0; double recall = 0; double map = 0; double ndcg = 0; double mrr = 0; double auc = 0; int count = 0; for (int i = 0; i < testRatings.size(); i++) { NumericRating rating = testRatings.get(i); double prediction = algo.predict(userIDIndexMapping.get(rating.getUserID()), itemIDIndexMapping.get(rating.getItemID()), false); if (prediction > algo.getMaxRating()) prediction = algo.getMaxRating(); if (prediction < algo.getMinRating()) prediction = algo.getMinRating(); if (Double.isNaN(prediction)) { System.out.println("no prediction"); continue; } MAE = MAE + Math.abs(rating.getValue() - prediction); RMSE = RMSE + Math.pow((rating.getValue() - prediction), 2); count++; } MAE = MAE / count; RMSE = Math.sqrt(RMSE / count); totalMAE = totalMAE + MAE; totalRMSE = totalRMSE + RMSE; System.out.println("Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Folder --- MAE: " + MAE + " RMSE: " + RMSE); //ranking accuracy if (algo.getTopN() > 0) { HashMap<Integer, ArrayList<ResultUnit>> results = new HashMap<Integer, ArrayList<ResultUnit>>(); for (int i = 0; i < trainRatingMatrix.getRow(); i++) { ArrayList<ResultUnit> rec = algo.getRecommendationList(i); if (rec == null) continue; int total = testRatingMatrix.getUserRatingNumber(i); if (total == 0)//this user is ignored continue; results.put(i, rec); } RankResultGenerator generator = new RankResultGenerator(results, algo.getTopN(), testRatingMatrix); precision = generator.getPrecisionN(); totalPrecision = totalPrecision + precision; recall = generator.getRecallN(); totalRecall = totalRecall + recall; map = generator.getMAPN(); totalMAP = totalMAP + map; ndcg = generator.getNDCGN(); totalNDCG = totalNDCG + ndcg; mrr = generator.getMRRN(); totalMRR = totalMRR + mrr; auc = generator.getAUC(); totalAUC = totalAUC + auc; System.out.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); logger.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); } logger.flush(); } System.out.println("MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F); System.out.println("Precision@N: " + totalPrecision / F); System.out.println("Recall@N: " + totalRecall / F); System.out.println("MAP@N: " + totalMAP / F); System.out.println("MRR@N: " + totalMRR / F); System.out.println("NDCG@N: " + totalNDCG / F); System.out.println("AUC@N: " + totalAUC / F); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + "\n" + "MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F + "\n" + "Precision@N: " + totalPrecision / F + "\n" + "Recall@N: " + totalRecall / F + "\n" + "MAP@N: " + totalMAP / F + "\n" + "MRR@N: " + totalMRR / F + "\n" + "NDCG@N: " + totalNDCG / F + "\n" + "AUC@N: " + totalAUC / F); logger.flush(); logger.close(); }
From source file:ch.epfl.lsir.xin.test.ItemBasedCFTest.java
/** * @param args/*from ww w. j a v a2s .c o m*/ */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub PrintWriter logger = new PrintWriter(".//results//ItemBasedCF"); PropertiesConfiguration config = new PropertiesConfiguration(); config.setFile(new File(".//conf//ItemBasedCF.properties")); try { config.load(); } catch (ConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Read rating data..."); DataLoaderFile loader = new DataLoaderFile(".//data//MoveLens100k.txt"); loader.readSimple(); DataSetNumeric dataset = loader.getDataset(); System.out.println("Number of ratings: " + dataset.getRatings().size() + " Number of users: " + dataset.getUserIDs().size() + " Number of items: " + dataset.getItemIDs().size()); logger.println("Number of ratings: " + dataset.getRatings().size() + ", Number of users: " + dataset.getUserIDs().size() + ", Number of items: " + dataset.getItemIDs().size()); logger.flush(); double totalMAE = 0; double totalRMSE = 0; double totalPrecision = 0; double totalRecall = 0; double totalMAP = 0; double totalNDCG = 0; double totalMRR = 0; double totalAUC = 0; int F = 5; logger.println(F + "- folder cross validation."); ArrayList<ArrayList<NumericRating>> folders = new ArrayList<ArrayList<NumericRating>>(); for (int i = 0; i < F; i++) { folders.add(new ArrayList<NumericRating>()); } while (dataset.getRatings().size() > 0) { int index = new Random().nextInt(dataset.getRatings().size()); int r = new Random().nextInt(F); folders.get(r).add(dataset.getRatings().get(index)); dataset.getRatings().remove(index); } for (int folder = 1; folder <= F; folder++) { logger.println("Folder: " + folder); System.out.println("Folder: " + folder); ArrayList<NumericRating> trainRatings = new ArrayList<NumericRating>(); ArrayList<NumericRating> testRatings = new ArrayList<NumericRating>(); for (int i = 0; i < folders.size(); i++) { if (i == folder - 1)//test data { testRatings.addAll(folders.get(i)); } else {//training data trainRatings.addAll(folders.get(i)); } } //create rating matrix HashMap<String, Integer> userIDIndexMapping = new HashMap<String, Integer>(); HashMap<String, Integer> itemIDIndexMapping = new HashMap<String, Integer>(); for (int i = 0; i < dataset.getUserIDs().size(); i++) { userIDIndexMapping.put(dataset.getUserIDs().get(i), i); } for (int i = 0; i < dataset.getItemIDs().size(); i++) { itemIDIndexMapping.put(dataset.getItemIDs().get(i), i); } RatingMatrix trainRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < trainRatings.size(); i++) { trainRatingMatrix.set(userIDIndexMapping.get(trainRatings.get(i).getUserID()), itemIDIndexMapping.get(trainRatings.get(i).getItemID()), trainRatings.get(i).getValue()); } trainRatingMatrix.calculateGlobalAverage(); trainRatingMatrix.calculateItemsMean(); RatingMatrix testRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < testRatings.size(); i++) { testRatingMatrix.set(userIDIndexMapping.get(testRatings.get(i).getUserID()), itemIDIndexMapping.get(testRatings.get(i).getItemID()), testRatings.get(i).getValue()); } System.out.println("Training: " + trainRatingMatrix.getTotalRatingNumber() + " vs Test: " + testRatingMatrix.getTotalRatingNumber()); logger.println("Initialize a item based collaborative filtering recommendation model."); ItemBasedCF algo = new ItemBasedCF(trainRatingMatrix); algo.setLogger(logger); algo.build();//if read local model, no need to build the model algo.saveModel(".//localModels//" + config.getString("NAME")); logger.println("Save the model."); logger.flush(); //rating prediction accuracy double RMSE = 0; double MAE = 0; double precision = 0; double recall = 0; double map = 0; double ndcg = 0; double mrr = 0; double auc = 0; int count = 0; for (int i = 0; i < testRatings.size(); i++) { NumericRating rating = testRatings.get(i); double prediction = algo.predict(userIDIndexMapping.get(rating.getUserID()), itemIDIndexMapping.get(rating.getItemID()), false); if (prediction > algo.getMaxRating()) prediction = algo.getMaxRating(); if (prediction < algo.getMinRating()) prediction = algo.getMinRating(); if (Double.isNaN(prediction)) { System.out.println("no prediction"); continue; } MAE = MAE + Math.abs(rating.getValue() - prediction); RMSE = RMSE + Math.pow((rating.getValue() - prediction), 2); count++; } MAE = MAE / count; RMSE = Math.sqrt(RMSE / count); totalMAE = totalMAE + MAE; totalRMSE = totalRMSE + RMSE; System.out.println("Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Folder --- MAE: " + MAE + " RMSE: " + RMSE); //ranking accuracy if (algo.getTopN() > 0) { HashMap<Integer, ArrayList<ResultUnit>> results = new HashMap<Integer, ArrayList<ResultUnit>>(); for (int i = 0; i < trainRatingMatrix.getRow(); i++) { // ArrayList<ResultUnit> rec = algo.getRecommendationList(i); // results.put(i, rec); ArrayList<ResultUnit> rec = algo.getRecommendationList(i); if (rec == null) continue; int total = testRatingMatrix.getUserRatingNumber(i); if (total == 0)//this user is ignored continue; results.put(i, rec); } RankResultGenerator generator = new RankResultGenerator(results, algo.getTopN(), testRatingMatrix, trainRatingMatrix); precision = generator.getPrecisionN(); totalPrecision = totalPrecision + precision; recall = generator.getRecallN(); totalRecall = totalRecall + recall; map = generator.getMAPN(); totalMAP = totalMAP + map; ndcg = generator.getNDCGN(); totalNDCG = totalNDCG + ndcg; mrr = generator.getMRRN(); totalMRR = totalMRR + mrr; auc = generator.getAUC(); totalAUC = totalAUC + auc; System.out.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); logger.append("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc + "\n"); } } System.out.println("MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F); System.out.println("Precision@N: " + totalPrecision / F); System.out.println("Recall@N: " + totalRecall / F); System.out.println("MAP@N: " + totalMAP / F); System.out.println("MRR@N: " + totalMRR / F); System.out.println("NDCG@N: " + totalNDCG / F); System.out.println("AUC@N: " + totalAUC / F); System.out.println("similarity: " + config.getString("SIMILARITY")); //MAE: 0.7227232762922241 RMSE: 0.9225576790122603 (MovieLens 100K, shrinkage 2500, neighbor size 40, PCC) //MAE: 0.7250636319353241 RMSE: 0.9242305485411567 (MovieLens 100K, shrinkage 25, neighbor size 40, PCC) //MAE: 0.7477213243604459 RMSE: 0.9512195004171138 (MovieLens 100K, shrinkage 2500, neighbor size 40, COSINE) logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + "\n" + "MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F + "\n" + "Precision@N: " + totalPrecision / F + "\n" + "Recall@N: " + totalRecall / F + "\n" + "MAP@N: " + totalMAP / F + "\n" + "MRR@N: " + totalMRR / F + "\n" + "NDCG@N: " + totalNDCG / F + "\n" + "AUC@N: " + totalAUC / F); logger.flush(); logger.close(); }
From source file:com.oltpbenchmark.multitenancy.MuTeBench.java
/** * @param args//from w w w . j a va 2s. c o m * @throws Exception */ public static void main(String[] args) throws Exception { String duration = null; String scenarioFile = null; // ------------------------------------------------------------------- // INITIALIZE LOGGING // ------------------------------------------------------------------- String log4jPath = System.getProperty("log4j.configuration"); if (log4jPath != null) { org.apache.log4j.PropertyConfigurator.configure(log4jPath); } else { throw new RuntimeException("Missing log4j.properties file"); } // ------------------------------------------------------------------- // PARSE COMMAND LINE PARAMETERS // ------------------------------------------------------------------- CommandLineParser parser = new PosixParser(); XMLConfiguration pluginConfig = null; try { pluginConfig = new XMLConfiguration("config/plugin.xml"); } catch (ConfigurationException e1) { LOG.info("Plugin configuration file config/plugin.xml is missing"); e1.printStackTrace(); } pluginConfig.setExpressionEngine(new XPathExpressionEngine()); Options options = new Options(); options.addOption("s", "scenario", true, "[required] Workload scenario file"); options.addOption("a", "analysis-buckets", true, "sampling buckets for result aggregation"); options.addOption("r", "runtime", true, "maximum runtime (no events will be started after finishing runtime)"); options.addOption("v", "verbose", false, "Display Messages"); options.addOption("g", "gui", false, "Show controlling GUI"); options.addOption("h", "help", false, "Print this help"); options.addOption("o", "output", true, "Output file (default System.out)"); options.addOption("b", "baseline", true, "Output files of previous baseline run"); options.addOption(null, "histograms", false, "Print txn histograms"); options.addOption("d", "dialects-export", true, "Export benchmark SQL to a dialects file"); // parse the command line arguments CommandLine argsLine = parser.parse(options, args); if (argsLine.hasOption("h")) { printUsage(options); return; } else if (!argsLine.hasOption("scenario")) { INIT_LOG.fatal("Missing scenario description file"); System.exit(-1); } else scenarioFile = argsLine.getOptionValue("scenario"); if (argsLine.hasOption("r")) duration = argsLine.getOptionValue("r"); if (argsLine.hasOption("runtime")) duration = argsLine.getOptionValue("runtime"); // ------------------------------------------------------------------- // CREATE TENANT SCHEDULE // ------------------------------------------------------------------- INIT_LOG.info("Create schedule"); Schedule schedule = new Schedule(duration, scenarioFile); HashMap<Integer, ScheduleEvents> tenantEvents = schedule.getTenantEvents(); ArrayList<Integer> tenantList = schedule.getTenantList(); List<BenchmarkModule> benchList = new ArrayList<BenchmarkModule>(); for (int tenInd = 0; tenInd < tenantList.size(); tenInd++) { int tenantID = tenantList.get(tenInd); for (int tenEvent = 0; tenEvent < tenantEvents.get(tenantID).size(); tenEvent++) { BenchmarkSettings benchmarkSettings = (BenchmarkSettings) tenantEvents.get(tenantID) .getBenchmarkSettings(tenEvent); // update benchmark Settings benchmarkSettings.setTenantID(tenantID); // ------------------------------------------------------------------- // GET PLUGIN LIST // ------------------------------------------------------------------- String plugins = benchmarkSettings.getBenchmark(); String[] pluginList = plugins.split(","); String configFile = benchmarkSettings.getConfigFile(); XMLConfiguration xmlConfig = new XMLConfiguration(configFile); xmlConfig.setExpressionEngine(new XPathExpressionEngine()); int lastTxnId = 0; for (String plugin : pluginList) { // ---------------------------------------------------------------- // WORKLOAD CONFIGURATION // ---------------------------------------------------------------- String pluginTest = ""; pluginTest = "[@bench='" + plugin + "']"; WorkloadConfiguration wrkld = new WorkloadConfiguration(); wrkld.setTenantId(tenantID); wrkld.setBenchmarkName(setTenantIDinString(plugin, tenantID)); wrkld.setXmlConfig(xmlConfig); wrkld.setDBType(DatabaseType.get(setTenantIDinString(xmlConfig.getString("dbtype"), tenantID))); wrkld.setDBDriver(setTenantIDinString(xmlConfig.getString("driver"), tenantID)); wrkld.setDBConnection(setTenantIDinString(xmlConfig.getString("DBUrl"), tenantID)); wrkld.setDBName(setTenantIDinString(xmlConfig.getString("DBName"), tenantID)); wrkld.setDBUsername(setTenantIDinString(xmlConfig.getString("username"), tenantID)); wrkld.setDBPassword(setTenantIDinString(xmlConfig.getString("password"), tenantID)); String terminalString = setTenantIDinString(xmlConfig.getString("terminals[not(@bench)]", "0"), tenantID); int terminals = Integer.parseInt(xmlConfig.getString("terminals" + pluginTest, terminalString)); wrkld.setTerminals(terminals); int taSize = Integer.parseInt(xmlConfig.getString("taSize", "1")); if (taSize < 0) INIT_LOG.fatal("taSize must not be negative!"); wrkld.setTaSize(taSize); wrkld.setProprietaryTaSyntax(xmlConfig.getBoolean("proprietaryTaSyntax", false)); wrkld.setIsolationMode(setTenantIDinString( xmlConfig.getString("isolation", "TRANSACTION_SERIALIZABLE"), tenantID)); wrkld.setScaleFactor(Double .parseDouble(setTenantIDinString(xmlConfig.getString("scalefactor", "1.0"), tenantID))); wrkld.setRecordAbortMessages(xmlConfig.getBoolean("recordabortmessages", false)); int size = xmlConfig.configurationsAt("/works/work").size(); for (int i = 1; i < size + 1; i++) { SubnodeConfiguration work = xmlConfig.configurationAt("works/work[" + i + "]"); List<String> weight_strings; // use a workaround if there multiple workloads or // single // attributed workload if (pluginList.length > 1 || work.containsKey("weights[@bench]")) { weight_strings = get_weights(plugin, work); } else { weight_strings = work.getList("weights[not(@bench)]"); } int rate = 1; boolean rateLimited = true; boolean disabled = false; // can be "disabled", "unlimited" or a number String rate_string; rate_string = setTenantIDinString(work.getString("rate[not(@bench)]", ""), tenantID); rate_string = setTenantIDinString(work.getString("rate" + pluginTest, rate_string), tenantID); if (rate_string.equals(RATE_DISABLED)) { disabled = true; } else if (rate_string.equals(RATE_UNLIMITED)) { rateLimited = false; } else if (rate_string.isEmpty()) { LOG.fatal(String.format( "Tenant " + tenantID + ": Please specify the rate for phase %d and workload %s", i, plugin)); System.exit(-1); } else { try { rate = Integer.parseInt(rate_string); if (rate < 1) { LOG.fatal("Tenant " + tenantID + ": Rate limit must be at least 1. Use unlimited or disabled values instead."); System.exit(-1); } } catch (NumberFormatException e) { LOG.fatal(String.format( "Tenant " + tenantID + ": Rate string must be '%s', '%s' or a number", RATE_DISABLED, RATE_UNLIMITED)); System.exit(-1); } } Phase.Arrival arrival = Phase.Arrival.REGULAR; String arrive = setTenantIDinString(work.getString("@arrival", "regular"), tenantID); if (arrive.toUpperCase().equals("POISSON")) arrival = Phase.Arrival.POISSON; int activeTerminals; activeTerminals = Integer.parseInt(setTenantIDinString( work.getString("active_terminals[not(@bench)]", String.valueOf(terminals)), tenantID)); activeTerminals = Integer.parseInt(setTenantIDinString( work.getString("active_terminals" + pluginTest, String.valueOf(activeTerminals)), tenantID)); if (activeTerminals > terminals) { LOG.fatal("Tenant " + tenantID + ": Configuration error in work " + i + ": number of active terminals" + "" + "is bigger than the total number of terminals"); System.exit(-1); } wrkld.addWork(Integer.parseInt(setTenantIDinString(work.getString("/time"), tenantID)), rate, weight_strings, rateLimited, disabled, activeTerminals, arrival); } // FOR int numTxnTypes = xmlConfig .configurationsAt("transactiontypes" + pluginTest + "/transactiontype").size(); if (numTxnTypes == 0 && pluginList.length == 1) { // if it is a single workload run, <transactiontypes /> // w/o attribute is used pluginTest = "[not(@bench)]"; numTxnTypes = xmlConfig .configurationsAt("transactiontypes" + pluginTest + "/transactiontype").size(); } wrkld.setNumTxnTypes(numTxnTypes); // CHECKING INPUT PHASES int j = 0; for (Phase p : wrkld.getAllPhases()) { j++; if (p.getWeightCount() != wrkld.getNumTxnTypes()) { LOG.fatal(String.format("Tenant " + tenantID + ": Configuration files is inconsistent, phase %d contains %d weights but you defined %d transaction types", j, p.getWeightCount(), wrkld.getNumTxnTypes())); System.exit(-1); } } // FOR // Generate the dialect map wrkld.init(); assert (wrkld.getNumTxnTypes() >= 0); assert (xmlConfig != null); // ---------------------------------------------------------------- // BENCHMARK MODULE // ---------------------------------------------------------------- String classname = pluginConfig.getString("/plugin[@name='" + plugin + "']"); if (classname == null) { throw new ParseException("Plugin " + plugin + " is undefined in config/plugin.xml"); } BenchmarkModule bench = ClassUtil.newInstance(classname, new Object[] { wrkld }, new Class<?>[] { WorkloadConfiguration.class }); assert (benchList.get(0) != null); Map<String, Object> initDebug = new ListOrderedMap<String, Object>(); initDebug.put("Benchmark", String.format("%s {%s}", plugin.toUpperCase(), classname)); initDebug.put("Configuration", configFile); initDebug.put("Type", wrkld.getDBType()); initDebug.put("Driver", wrkld.getDBDriver()); initDebug.put("URL", wrkld.getDBConnection()); initDebug.put("Isolation", setTenantIDinString( xmlConfig.getString("isolation", "TRANSACTION_SERIALIZABLE [DEFAULT]"), tenantID)); initDebug.put("Scale Factor", wrkld.getScaleFactor()); INIT_LOG.info(SINGLE_LINE + "\n\n" + StringUtil.formatMaps(initDebug)); INIT_LOG.info(SINGLE_LINE); // Load TransactionTypes List<TransactionType> ttypes = new ArrayList<TransactionType>(); // Always add an INVALID type for Carlo ttypes.add(TransactionType.INVALID); int txnIdOffset = lastTxnId; for (int i = 1; i < wrkld.getNumTxnTypes() + 1; i++) { String key = "transactiontypes" + pluginTest + "/transactiontype[" + i + "]"; String txnName = setTenantIDinString(xmlConfig.getString(key + "/name"), tenantID); int txnId = i + 1; if (xmlConfig.containsKey(key + "/id")) { txnId = Integer .parseInt(setTenantIDinString(xmlConfig.getString(key + "/id"), tenantID)); } ttypes.add(bench.initTransactionType(txnName, txnId + txnIdOffset)); lastTxnId = i; } // FOR TransactionTypes tt = new TransactionTypes(ttypes); wrkld.setTransTypes(tt); if (benchmarkSettings.getBenchmarkSlaFile() != null) wrkld.setSlaFromFile(benchmarkSettings.getBenchmarkSlaFile()); LOG.debug("Tenant " + tenantID + ": Using the following transaction types: " + tt); bench.setTenantOffset(tenantEvents.get(tenantID).getTime(tenEvent)); bench.setTenantID(tenantID); bench.setBenchmarkSettings(benchmarkSettings); benchList.add(bench); } } } // create result collector ResultCollector rCollector = new ResultCollector(tenantList); // execute benchmarks in parallel ArrayList<Thread> benchThreads = new ArrayList<Thread>(); for (BenchmarkModule benchmark : benchList) { BenchmarkExecutor benchThread = new BenchmarkExecutor(benchmark, argsLine); Thread t = new Thread(benchThread); t.start(); benchThreads.add(t); benchmark.getWorkloadConfiguration().setrCollector(rCollector); } // waiting for completion of all benchmarks for (Thread t : benchThreads) { t.join(); } // print statistics int analysisBuckets = -1; if (argsLine.hasOption("analysis-buckets")) analysisBuckets = Integer.parseInt(argsLine.getOptionValue("analysis-buckets")); String output = null; if (argsLine.hasOption("o")) output = argsLine.getOptionValue("o"); String baseline = null; if (argsLine.hasOption("b")) baseline = argsLine.getOptionValue("b"); rCollector.printStatistics(output, analysisBuckets, argsLine.hasOption("histograms"), baseline); // create GUI if (argsLine.hasOption("g") && (!rCollector.getAllResults().isEmpty())) { try { Gui gui = new Gui(Integer.parseInt(argsLine.getOptionValue("analysis-buckets", "10")), rCollector, output); } catch (Exception e) { e.printStackTrace(); } } }
From source file:ch.epfl.lsir.xin.test.BiasedMFTest.java
/** * @param args/*from www.j a v a 2s. com*/ */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub PrintWriter logger = new PrintWriter(".//results//BiasedMF"); PropertiesConfiguration config = new PropertiesConfiguration(); config.setFile(new File("conf//biasedMF.properties")); try { config.load(); } catch (ConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Read rating data..."); logger.flush(); DataLoaderFile loader = new DataLoaderFile(".//data//MoveLens100k.txt"); loader.readSimple(); DataSetNumeric dataset = loader.getDataset(); System.out.println("Number of ratings: " + dataset.getRatings().size() + " Number of users: " + dataset.getUserIDs().size() + " Number of items: " + dataset.getItemIDs().size()); logger.println("Number of ratings: " + dataset.getRatings().size() + ", Number of users: " + dataset.getUserIDs().size() + ", Number of items: " + dataset.getItemIDs().size()); logger.flush(); double totalMAE = 0; double totalRMSE = 0; double totalPrecision = 0; double totalRecall = 0; double totalMAP = 0; double totalNDCG = 0; double totalMRR = 0; double totalAUC = 0; int F = 5; logger.println(F + "- folder cross validation."); logger.flush(); ArrayList<ArrayList<NumericRating>> folders = new ArrayList<ArrayList<NumericRating>>(); for (int i = 0; i < F; i++) { folders.add(new ArrayList<NumericRating>()); } while (dataset.getRatings().size() > 0) { int index = new Random().nextInt(dataset.getRatings().size()); int r = new Random().nextInt(F); folders.get(r).add(dataset.getRatings().get(index)); dataset.getRatings().remove(index); } for (int folder = 1; folder <= F; folder++) { System.out.println("Folder: " + folder); logger.println("Folder: " + folder); logger.flush(); ArrayList<NumericRating> trainRatings = new ArrayList<NumericRating>(); ArrayList<NumericRating> testRatings = new ArrayList<NumericRating>(); for (int i = 0; i < folders.size(); i++) { if (i == folder - 1)//test data { testRatings.addAll(folders.get(i)); } else {//training data trainRatings.addAll(folders.get(i)); } } //create rating matrix HashMap<String, Integer> userIDIndexMapping = new HashMap<String, Integer>(); HashMap<String, Integer> itemIDIndexMapping = new HashMap<String, Integer>(); for (int i = 0; i < dataset.getUserIDs().size(); i++) { userIDIndexMapping.put(dataset.getUserIDs().get(i), i); } for (int i = 0; i < dataset.getItemIDs().size(); i++) { itemIDIndexMapping.put(dataset.getItemIDs().get(i), i); } RatingMatrix trainRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < trainRatings.size(); i++) { trainRatingMatrix.set(userIDIndexMapping.get(trainRatings.get(i).getUserID()), itemIDIndexMapping.get(trainRatings.get(i).getItemID()), trainRatings.get(i).getValue()); } RatingMatrix testRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < testRatings.size(); i++) { // if( testRatings.get(i).getValue() < 5 ) // continue; testRatingMatrix.set(userIDIndexMapping.get(testRatings.get(i).getUserID()), itemIDIndexMapping.get(testRatings.get(i).getItemID()), testRatings.get(i).getValue()); } System.out.println("Training: " + trainRatingMatrix.getTotalRatingNumber() + " vs Test: " + testRatingMatrix.getTotalRatingNumber()); logger.println("Initialize a biased matrix factorization recommendation model."); logger.flush(); BiasedMF algo = new BiasedMF(trainRatingMatrix, false, ".//localModels//" + config.getString("NAME")); algo.setLogger(logger); algo.build(); algo.saveModel(".//localModels//" + config.getString("NAME")); logger.println("Save the model."); logger.flush(); //rating prediction accuracy double RMSE = 0; double MAE = 0; double precision = 0; double recall = 0; double map = 0; double ndcg = 0; double mrr = 0; double auc = 0; int count = 0; for (int i = 0; i < testRatings.size(); i++) { NumericRating rating = testRatings.get(i); double prediction = algo.predict(userIDIndexMapping.get(rating.getUserID()), itemIDIndexMapping.get(rating.getItemID()), false); if (prediction > algo.getMaxRating()) prediction = algo.getMaxRating(); if (prediction < algo.getMinRating()) prediction = algo.getMinRating(); if (Double.isNaN(prediction)) { System.out.println("no prediction"); continue; } MAE = MAE + Math.abs(rating.getValue() - prediction); RMSE = RMSE + Math.pow((rating.getValue() - prediction), 2); count++; } MAE = MAE / count; RMSE = Math.sqrt(RMSE / count); totalMAE = totalMAE + MAE; totalRMSE = totalRMSE + RMSE; System.out.println("Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Folder --- MAE: " + MAE + " RMSE: " + RMSE); //ranking accuracy if (algo.getTopN() > 0) { HashMap<Integer, ArrayList<ResultUnit>> results = new HashMap<Integer, ArrayList<ResultUnit>>(); for (int i = 0; i < trainRatingMatrix.getRow(); i++) { ArrayList<ResultUnit> rec = algo.getRecommendationList(i); if (rec == null) continue; int total = testRatingMatrix.getUserRatingNumber(i); if (total == 0)//this user is ignored continue; results.put(i, rec); } RankResultGenerator generator = new RankResultGenerator(results, algo.getTopN(), testRatingMatrix, trainRatingMatrix); precision = generator.getPrecisionN(); totalPrecision = totalPrecision + precision; recall = generator.getRecallN(); totalRecall = totalRecall + recall; map = generator.getMAPN(); totalMAP = totalMAP + map; ndcg = generator.getNDCGN(); totalNDCG = totalNDCG + ndcg; mrr = generator.getMRRN(); totalMRR = totalMRR + mrr; auc = generator.getAUC(); totalAUC = totalAUC + auc; System.out.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); logger.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); } logger.flush(); } System.out.println("MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F); System.out.println("Precision@N: " + totalPrecision / F); System.out.println("Recall@N: " + totalRecall / F); System.out.println("MAP@N: " + totalMAP / F); System.out.println("MRR@N: " + totalMRR / F); System.out.println("NDCG@N: " + totalNDCG / F); System.out.println("AUC@N: " + totalAUC / F); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + "\n" + "MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F + "\n" + "Precision@N: " + totalPrecision / F + "\n" + "Recall@N: " + totalRecall / F + "\n" + "MAP@N: " + totalMAP / F + "\n" + "MRR@N: " + totalMRR / F + "\n" + "NDCG@N: " + totalNDCG / F + "\n" + "AUC@N: " + totalAUC / F); logger.flush(); logger.close(); }
From source file:ch.epfl.lsir.xin.test.UserBasedCFTest.java
/** * @param args//w w w . j a v a2s .c om */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub PrintWriter logger = new PrintWriter(".//results//UserBasedCF"); PropertiesConfiguration config = new PropertiesConfiguration(); config.setFile(new File(".//conf//UserBasedCF.properties")); try { config.load(); } catch (ConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Read rating data..."); DataLoaderFile loader = new DataLoaderFile(".//data//MoveLens100k.txt"); loader.readSimple(); DataSetNumeric dataset = loader.getDataset(); System.out.println("Number of ratings: " + dataset.getRatings().size() + " Number of users: " + dataset.getUserIDs().size() + " Number of items: " + dataset.getItemIDs().size()); logger.println("Number of ratings: " + dataset.getRatings().size() + ", Number of users: " + dataset.getUserIDs().size() + ", Number of items: " + dataset.getItemIDs().size()); logger.flush(); double totalMAE = 0; double totalRMSE = 0; double totalPrecision = 0; double totalRecall = 0; double totalMAP = 0; double totalNDCG = 0; double totalMRR = 0; double totalAUC = 0; int F = 5; logger.println(F + "- folder cross validation."); ArrayList<ArrayList<NumericRating>> folders = new ArrayList<ArrayList<NumericRating>>(); for (int i = 0; i < F; i++) { folders.add(new ArrayList<NumericRating>()); } while (dataset.getRatings().size() > 0) { int index = new Random().nextInt(dataset.getRatings().size()); int r = new Random().nextInt(F); folders.get(r).add(dataset.getRatings().get(index)); dataset.getRatings().remove(index); } for (int folder = 1; folder <= F; folder++) { logger.println("Folder: " + folder); System.out.println("Folder: " + folder); ArrayList<NumericRating> trainRatings = new ArrayList<NumericRating>(); ArrayList<NumericRating> testRatings = new ArrayList<NumericRating>(); for (int i = 0; i < folders.size(); i++) { if (i == folder - 1)//test data { testRatings.addAll(folders.get(i)); } else {//training data trainRatings.addAll(folders.get(i)); } } //create rating matrix HashMap<String, Integer> userIDIndexMapping = new HashMap<String, Integer>(); HashMap<String, Integer> itemIDIndexMapping = new HashMap<String, Integer>(); for (int i = 0; i < dataset.getUserIDs().size(); i++) { userIDIndexMapping.put(dataset.getUserIDs().get(i), i); } for (int i = 0; i < dataset.getItemIDs().size(); i++) { itemIDIndexMapping.put(dataset.getItemIDs().get(i), i); } RatingMatrix trainRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < trainRatings.size(); i++) { trainRatingMatrix.set(userIDIndexMapping.get(trainRatings.get(i).getUserID()), itemIDIndexMapping.get(trainRatings.get(i).getItemID()), trainRatings.get(i).getValue()); } trainRatingMatrix.calculateGlobalAverage(); trainRatingMatrix.calculateUsersMean(); RatingMatrix testRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < testRatings.size(); i++) { // if( testRatings.get(i).getValue() < 5 ) // continue; testRatingMatrix.set(userIDIndexMapping.get(testRatings.get(i).getUserID()), itemIDIndexMapping.get(testRatings.get(i).getItemID()), testRatings.get(i).getValue()); } logger.println("Initialize a user based collaborative filtering recommendation model."); UserBasedCF algo = new UserBasedCF(trainRatingMatrix, false, ".//localModels//" + config.getString("NAME")); algo.setLogger(logger); algo.build();//if read local model, no need to build the model algo.saveModel(".//localModels//" + config.getString("NAME")); logger.println("Save the model."); System.out.println(trainRatings.size() + " vs. " + testRatings.size()); logger.flush(); //rating prediction accuracy double RMSE = 0; double MAE = 0; double precision = 0; double recall = 0; double map = 0; double ndcg = 0; double mrr = 0; double auc = 0; int count = 0; for (int i = 0; i < testRatings.size(); i++) { NumericRating rating = testRatings.get(i); double prediction = algo.predict(userIDIndexMapping.get(rating.getUserID()), itemIDIndexMapping.get(rating.getItemID()), false); if (Double.isNaN(prediction)) { System.out.println("no prediction"); continue; } if (prediction > algo.getMaxRating()) prediction = algo.getMaxRating(); if (prediction < algo.getMinRating()) prediction = algo.getMinRating(); MAE = MAE + Math.abs(rating.getValue() - prediction); RMSE = RMSE + Math.pow((rating.getValue() - prediction), 2); count++; } MAE = MAE / count; RMSE = Math.sqrt(RMSE / count); totalMAE = totalMAE + MAE; totalRMSE = totalRMSE + RMSE; System.out.println("Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.flush(); //ranking accuracy if (algo.getTopN() > 0) { HashMap<Integer, ArrayList<ResultUnit>> results = new HashMap<Integer, ArrayList<ResultUnit>>(); for (int i = 0; i < testRatingMatrix.getRow(); i++) { ArrayList<ResultUnit> rec = algo.getRecommendationList(i); if (rec == null) continue; int total = testRatingMatrix.getUserRatingNumber(i); if (total == 0)//this user is ignored continue; results.put(i, rec); // for( Map.Entry<Integer, Double> entry : testRatingMatrix.getRatingMatrix().get(i).entrySet() ) // { // System.out.print( entry.getKey() + "(" + entry.getValue() + ") , "); // } // System.out.println(); // for( int j = 0 ; j < rec.size() ; j++ ) // { // System.out.print(rec.get(j).getItemIndex() + "(" + rec.get(j).getPrediciton() + // ") , "); // } // System.out.println("**********"); } RankResultGenerator generator = new RankResultGenerator(results, algo.getTopN(), testRatingMatrix, trainRatingMatrix); precision = generator.getPrecisionN(); totalPrecision = totalPrecision + precision; recall = generator.getRecallN(); totalRecall = totalRecall + recall; map = generator.getMAPN(); totalMAP = totalMAP + map; ndcg = generator.getNDCGN(); totalNDCG = totalNDCG + ndcg; mrr = generator.getMRRN(); totalMRR = totalMRR + mrr; auc = generator.getAUC(); totalAUC = totalAUC + auc; System.out.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); logger.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); } } System.out.println("MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F); System.out.println("Precision@N: " + totalPrecision / F); System.out.println("Recall@N: " + totalRecall / F); System.out.println("MAP@N: " + totalMAP / F); System.out.println("MRR@N: " + totalMRR / F); System.out.println("NDCG@N: " + totalNDCG / F); System.out.println("AUC@N: " + totalAUC / F); // MovieLens100k //MAE: 0.7343907480119425 RMSE: 0.9405808357192891 (MovieLens 100K, shrinkage 25, neighbor size 60, PCC) //MAE: 0.7522376630596646 RMSE: 0.9520931265724659 (MovieLens 100K, no shrinkage , neighbor size 40, COSINE) logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + "\n" + "MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F + "\n" + "Precision@N: " + totalPrecision / F + "\n" + "Recall@N: " + totalRecall / F + "\n" + "MAP@N: " + totalMAP / F + "\n" + "MRR@N: " + totalMRR / F + "\n" + "NDCG@N: " + totalNDCG / F + "\n" + "AUC@N: " + totalAUC / F); logger.flush(); logger.close(); }
From source file:ch.epfl.lsir.xin.test.MFTest.java
/** * @param args//from ww w .j av a2 s. c o m */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub PrintWriter logger = new PrintWriter(".//results//MF"); PropertiesConfiguration config = new PropertiesConfiguration(); config.setFile(new File("conf//MF.properties")); try { config.load(); } catch (ConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Read rating data..."); logger.flush(); DataLoaderFile loader = new DataLoaderFile(".//data//MoveLens100k.txt"); loader.readSimple(); DataSetNumeric dataset = loader.getDataset(); System.out.println("Number of ratings: " + dataset.getRatings().size() + " Number of users: " + dataset.getUserIDs().size() + " Number of items: " + dataset.getItemIDs().size()); logger.println("Number of ratings: " + dataset.getRatings().size() + ", Number of users: " + dataset.getUserIDs().size() + ", Number of items: " + dataset.getItemIDs().size()); logger.flush(); double totalMAE = 0; double totalRMSE = 0; double totalPrecision = 0; double totalRecall = 0; double totalMAP = 0; double totalNDCG = 0; double totalMRR = 0; double totalAUC = 0; int F = 5; logger.println(F + "- folder cross validation."); logger.flush(); ArrayList<ArrayList<NumericRating>> folders = new ArrayList<ArrayList<NumericRating>>(); for (int i = 0; i < F; i++) { folders.add(new ArrayList<NumericRating>()); } while (dataset.getRatings().size() > 0) { int index = new Random().nextInt(dataset.getRatings().size()); int r = new Random().nextInt(F); folders.get(r).add(dataset.getRatings().get(index)); dataset.getRatings().remove(index); } for (int folder = 1; folder <= F; folder++) { System.out.println("Folder: " + folder); logger.println("Folder: " + folder); logger.flush(); ArrayList<NumericRating> trainRatings = new ArrayList<NumericRating>(); ArrayList<NumericRating> testRatings = new ArrayList<NumericRating>(); for (int i = 0; i < folders.size(); i++) { if (i == folder - 1)//test data { testRatings.addAll(folders.get(i)); } else {//training data trainRatings.addAll(folders.get(i)); } } //create rating matrix HashMap<String, Integer> userIDIndexMapping = new HashMap<String, Integer>(); HashMap<String, Integer> itemIDIndexMapping = new HashMap<String, Integer>(); for (int i = 0; i < dataset.getUserIDs().size(); i++) { userIDIndexMapping.put(dataset.getUserIDs().get(i), i); } for (int i = 0; i < dataset.getItemIDs().size(); i++) { itemIDIndexMapping.put(dataset.getItemIDs().get(i), i); } RatingMatrix trainRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < trainRatings.size(); i++) { trainRatingMatrix.set(userIDIndexMapping.get(trainRatings.get(i).getUserID()), itemIDIndexMapping.get(trainRatings.get(i).getItemID()), trainRatings.get(i).getValue()); } RatingMatrix testRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < testRatings.size(); i++) { // if( testRatings.get(i).getValue() < 5 ) // continue; testRatingMatrix.set(userIDIndexMapping.get(testRatings.get(i).getUserID()), itemIDIndexMapping.get(testRatings.get(i).getItemID()), testRatings.get(i).getValue()); } System.out.println("Training: " + trainRatingMatrix.getTotalRatingNumber() + " vs Test: " + testRatingMatrix.getTotalRatingNumber()); logger.println("Initialize a matrix factorization based recommendation model."); logger.flush(); MatrixFactorization algo = new MatrixFactorization(trainRatingMatrix, false, ".//localModels//" + config.getString("NAME")); algo.setLogger(logger); algo.build(); algo.saveModel(".//localModels//" + config.getString("NAME")); logger.println("Save the model."); logger.flush(); //rating prediction accuracy double RMSE = 0; double MAE = 0; double precision = 0; double recall = 0; double map = 0; double ndcg = 0; double mrr = 0; double auc = 0; int count = 0; for (int i = 0; i < testRatings.size(); i++) { NumericRating rating = testRatings.get(i); double prediction = algo.predict(userIDIndexMapping.get(rating.getUserID()), itemIDIndexMapping.get(rating.getItemID()), false); if (prediction > algo.getMaxRating()) prediction = algo.getMaxRating(); if (prediction < algo.getMinRating()) prediction = algo.getMinRating(); if (Double.isNaN(prediction)) { System.out.println("no prediction"); continue; } MAE = MAE + Math.abs(rating.getValue() - prediction); RMSE = RMSE + Math.pow((rating.getValue() - prediction), 2); count++; } MAE = MAE / count; RMSE = Math.sqrt(RMSE / count); totalMAE = totalMAE + MAE; totalRMSE = totalRMSE + RMSE; System.out.println("Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Folder --- MAE: " + MAE + " RMSE: " + RMSE); //ranking accuracy if (algo.getTopN() > 0) { HashMap<Integer, ArrayList<ResultUnit>> results = new HashMap<Integer, ArrayList<ResultUnit>>(); for (int i = 0; i < trainRatingMatrix.getRow(); i++) { ArrayList<ResultUnit> rec = algo.getRecommendationList(i); if (rec == null) continue; int total = testRatingMatrix.getUserRatingNumber(i); if (total == 0)//this user is ignored continue; results.put(i, rec); // for( Map.Entry<Integer, Double> entry : testRatingMatrix.getRatingMatrix().get(i).entrySet() ) // { // System.out.print( entry.getKey() + "(" + entry.getValue() + ") , "); // } // System.out.println(); // for( int j = 0 ; j < rec.size() ; j++ ) // { // System.out.print(rec.get(j).getItemIndex() + "(" + rec.get(j).getPrediciton() + // ") , "); // } // System.out.println("**********"); } RankResultGenerator generator = new RankResultGenerator(results, algo.getTopN(), testRatingMatrix, trainRatingMatrix); precision = generator.getPrecisionN(); totalPrecision = totalPrecision + precision; recall = generator.getRecallN(); totalRecall = totalRecall + recall; map = generator.getMAPN(); totalMAP = totalMAP + map; ndcg = generator.getNDCGN(); totalNDCG = totalNDCG + ndcg; mrr = generator.getMRRN(); totalMRR = totalMRR + mrr; auc = generator.getAUC(); totalAUC = totalAUC + auc; System.out.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); logger.println("Folder --- precision: " + precision + " recall: " + recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " MAE: " + MAE + " RMSE: " + RMSE); logger.flush(); } System.out.println("MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F); System.out.println("Precision@N: " + totalPrecision / F); System.out.println("Recall@N: " + totalRecall / F); System.out.println("MAP@N: " + totalMAP / F); System.out.println("MRR@N: " + totalMRR / F); System.out.println("NDCG@N: " + totalNDCG / F); System.out.println("AUC@N: " + totalAUC / F); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + "\n" + "MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F + "\n" + "Precision@N: " + totalPrecision / F + "\n" + "Recall@N: " + totalRecall / F + "\n" + "MAP@N: " + totalMAP / F + "\n" + "MRR@N: " + totalMRR / F + "\n" + "NDCG@N: " + totalNDCG / F + "\n" + "AUC@N: " + totalAUC / F); logger.flush(); logger.close(); }
From source file:ch.epfl.lsir.xin.test.SocialRegTest.java
/** * @param args//from w ww . j a v a 2s . c o m */ public static void main(String[] args) throws Exception { // TODO Auto-generated method stub PrintWriter logger = new PrintWriter(".//results//SocialReg"); PropertiesConfiguration config = new PropertiesConfiguration(); config.setFile(new File("conf//SocialReg.properties")); try { config.load(); } catch (ConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Read rating data..."); logger.flush(); DataLoaderFile loader = new DataLoaderFile(".//data//Epinions-ratings.txt"); loader.readSimple(); //read social information loader.readRelation(".//data//Epinions-trust.txt"); DataSetNumeric dataset = loader.getDataset(); System.out.println("Number of ratings: " + dataset.getRatings().size() + " Number of users: " + dataset.getUserIDs().size() + " Number of items: " + dataset.getItemIDs().size()); logger.println("Number of ratings: " + dataset.getRatings().size() + ", Number of users: " + dataset.getUserIDs().size() + ", Number of items: " + dataset.getItemIDs().size()); logger.flush(); double totalMAE = 0; double totalRMSE = 0; double totalPrecision = 0; double totalRecall = 0; double totalMAP = 0; double totalNDCG = 0; double totalMRR = 0; double totalAUC = 0; int F = 5; logger.println(F + "- folder cross validation."); logger.flush(); ArrayList<ArrayList<NumericRating>> folders = new ArrayList<ArrayList<NumericRating>>(); for (int i = 0; i < F; i++) { folders.add(new ArrayList<NumericRating>()); } while (dataset.getRatings().size() > 0) { int index = new Random().nextInt(dataset.getRatings().size()); int r = new Random().nextInt(F); folders.get(r).add(dataset.getRatings().get(index)); dataset.getRatings().remove(index); } for (int folder = 1; folder <= F; folder++) { System.out.println("Folder: " + folder); logger.println("Folder: " + folder); logger.flush(); ArrayList<NumericRating> trainRatings = new ArrayList<NumericRating>(); ArrayList<NumericRating> testRatings = new ArrayList<NumericRating>(); for (int i = 0; i < folders.size(); i++) { if (i == folder - 1)//test data { testRatings.addAll(folders.get(i)); } else {//training data trainRatings.addAll(folders.get(i)); } } //create rating matrix HashMap<String, Integer> userIDIndexMapping = dataset.getUserIDMapping(); HashMap<String, Integer> itemIDIndexMapping = dataset.getItemIDMapping(); // for( int i = 0 ; i < dataset.getUserIDs().size() ; i++ ) // { // userIDIndexMapping.put(dataset.getUserIDs().get(i), i); // } // for( int i = 0 ; i < dataset.getItemIDs().size() ; i++ ) // { // itemIDIndexMapping.put(dataset.getItemIDs().get(i) , i); // } RatingMatrix trainRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < trainRatings.size(); i++) { trainRatingMatrix.set(userIDIndexMapping.get(trainRatings.get(i).getUserID()), itemIDIndexMapping.get(trainRatings.get(i).getItemID()), trainRatings.get(i).getValue()); } RatingMatrix testRatingMatrix = new RatingMatrix(dataset.getUserIDs().size(), dataset.getItemIDs().size()); for (int i = 0; i < testRatings.size(); i++) { testRatingMatrix.set(userIDIndexMapping.get(testRatings.get(i).getUserID()), itemIDIndexMapping.get(testRatings.get(i).getItemID()), testRatings.get(i).getValue()); } System.out.println("Training: " + trainRatingMatrix.getTotalRatingNumber() + " vs Test: " + testRatingMatrix.getTotalRatingNumber()); logger.println("Initialize a social regularization recommendation model."); logger.flush(); SocialReg algo = new SocialReg(trainRatingMatrix, dataset.getRelationships(), false, ".//localModels//" + config.getString("NAME")); algo.setLogger(logger); algo.build(); algo.saveModel(".//localModels//" + config.getString("NAME")); logger.println("Save the model."); logger.flush(); System.out.println(trainRatings.size() + " vs. " + testRatings.size()); //rating prediction accuracy double RMSE = 0; double MAE = 0; double precision = 0; double recall = 0; double map = 0; double ndcg = 0; double mrr = 0; double auc = 0; int count = 0; for (int i = 0; i < testRatings.size(); i++) { NumericRating rating = testRatings.get(i); double prediction = algo.predict(userIDIndexMapping.get(rating.getUserID()), itemIDIndexMapping.get(rating.getItemID())); if (prediction > algo.getMaxRating()) prediction = algo.getMaxRating(); if (prediction < algo.getMinRating()) prediction = algo.getMinRating(); if (Double.isNaN(prediction)) { System.out.println("no prediction"); continue; } MAE = MAE + Math.abs(rating.getValue() - prediction); RMSE = RMSE + Math.pow((rating.getValue() - prediction), 2); count++; } MAE = MAE / count; RMSE = Math.sqrt(RMSE / count); totalMAE = totalMAE + MAE; totalRMSE = totalRMSE + RMSE; System.out.println("Folder --- MAE: " + MAE + " RMSE: " + RMSE); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + " Folder --- MAE: " + MAE + " RMSE: " + RMSE); //ranking accuracy // if( algo.getTopN() > 0 ) // { // HashMap<Integer , ArrayList<ResultUnit>> results = new HashMap<Integer , ArrayList<ResultUnit>>(); // for( int i = 0 ; i < trainRatingMatrix.getRow() ; i++ ) // { // ArrayList<ResultUnit> rec = algo.getRecommendationList(i); // results.put(i, rec); // } // RankResultGenerator generator = new RankResultGenerator(results , algo.getTopN() , testRatingMatrix); // precision = generator.getPrecisionN(); // totalPrecision = totalPrecision + precision; // recall = generator.getRecallN(); // totalRecall = totalRecall + recall; // map = generator.getMAPN(); // totalMAP = totalMAP + map; // ndcg = generator.getNDCGN(); // totalNDCG = totalNDCG + ndcg; // mrr = generator.getMRRN(); // totalMRR = totalMRR + mrr; // auc = generator.getAUC(); // totalAUC = totalAUC + auc; // System.out.println("Folder --- precision: " + precision + " recall: " + // recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + mrr + " auc: " + auc); // logger.println("Folder --- precision: " + precision + " recall: " + // recall + " map: " + map + " ndcg: " + ndcg + " mrr: " + // mrr + " auc: " + auc); // } logger.flush(); } System.out.println("MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F); System.out.println("Precision@N: " + totalPrecision / F); System.out.println("Recall@N: " + totalRecall / F); System.out.println("MAP@N: " + totalMAP / F); System.out.println("MRR@N: " + totalMRR / F); System.out.println("NDCG@N: " + totalNDCG / F); System.out.println("AUC@N: " + totalAUC / F); logger.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date()) + "\n" + "MAE: " + totalMAE / F + " RMSE: " + totalRMSE / F + "\n" + "Precision@N: " + totalPrecision / F + "\n" + "Recall@N: " + totalRecall / F + "\n" + "MAP@N: " + totalMAP / F + "\n" + "MRR@N: " + totalMRR / F + "\n" + "NDCG@N: " + totalNDCG / F + "\n" + "AUC@N: " + totalAUC / F); logger.flush(); logger.close(); }
From source file:ms1quant.MS1Quant.java
/** * @param args the command line arguments MS1Quant parameterfile *//*w w w.j av a2 s .c o m*/ public static void main(String[] args) throws Exception { BufferedReader reader = null; try { System.out.println( "================================================================================================="); System.out.println("Umpire MS1 quantification and feature detection analysis (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length < 3 || !args[1].startsWith("-mode")) { System.out .println("command : java -jar -Xmx10G MS1Quant.jar ms1quant.params -mode[1 or 2] [Option]"); System.out.println("\n-mode"); System.out.println("\t1:Single file mode--> mzXML_file PepXML_file"); System.out.println("\t\tEx: -mode1 file1.mzXML file1.pep.xml"); System.out.println( "\t2:Folder mode--> mzXML_Folder PepXML_Folder, all generated csv tables will be merged into a single csv file"); System.out.println("\t\tEx: -mode2 /data/mzxml/ /data/pepxml/"); System.out.println("\nOptions"); System.out.println( "\t-C\tNo of concurrent files to be processed (only for folder mode), Ex. -C5, default:1"); System.out.println("\t-p\tMinimum probability, Ex. -p0.9, default:0.9"); System.out.println("\t-ID\tDetect identified feature only"); System.out.println("\t-O\toutput folder, Ex. -O/data/"); return; } ConsoleLogger consoleLogger = new ConsoleLogger(); consoleLogger.SetConsoleLogger(Level.DEBUG); consoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "ms1quant_debug.log"); Logger logger = Logger.getRootLogger(); logger.debug("Command: " + Arrays.toString(args)); logger.info("MS1Quant version: " + UmpireInfo.GetInstance().Version); String parameterfile = args[0]; logger.info("Parameter file: " + parameterfile); File paramfile = new File(parameterfile); if (!paramfile.exists()) { logger.error("Parameter file " + paramfile.getAbsolutePath() + " cannot be found. The program will exit."); } reader = new BufferedReader(new FileReader(paramfile.getAbsolutePath())); String line = ""; InstrumentParameter param = new InstrumentParameter(InstrumentParameter.InstrumentType.TOF5600); int NoCPUs = 2; int NoFile = 1; param.DetermineBGByID = false; param.EstimateBG = true; //<editor-fold defaultstate="collapsed" desc="Read parameter file"> while ((line = reader.readLine()) != null) { if (!"".equals(line) && !line.startsWith("#")) { logger.info(line); //System.out.println(line); if (line.split("=").length < 2) { continue; } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); if (type.startsWith("para.")) { type = type.replace("para.", "SE."); } String value = line.split("=")[1].trim(); switch (type) { case "Thread": { NoCPUs = Integer.parseInt(value); break; } //<editor-fold defaultstate="collapsed" desc="instrument parameters"> case "SE.MS1PPM": { param.MS1PPM = Float.parseFloat(value); break; } case "SE.MS2PPM": { param.MS2PPM = Float.parseFloat(value); break; } case "SE.SN": { param.SNThreshold = Float.parseFloat(value); break; } case "SE.MS2SN": { param.MS2SNThreshold = Float.parseFloat(value); break; } case "SE.MinMSIntensity": { param.MinMSIntensity = Float.parseFloat(value); break; } case "SE.MinMSMSIntensity": { param.MinMSMSIntensity = Float.parseFloat(value); break; } case "SE.MinRTRange": { param.MinRTRange = Float.parseFloat(value); break; } case "SE.MaxNoPeakCluster": { param.MaxNoPeakCluster = Integer.parseInt(value); param.MaxMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MinNoPeakCluster": { param.MinNoPeakCluster = Integer.parseInt(value); param.MinMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MinMS2NoPeakCluster": { param.MinMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MaxCurveRTRange": { param.MaxCurveRTRange = Float.parseFloat(value); break; } case "SE.Resolution": { param.Resolution = Integer.parseInt(value); break; } case "SE.RTtol": { param.RTtol = Float.parseFloat(value); break; } case "SE.NoPeakPerMin": { param.NoPeakPerMin = Integer.parseInt(value); break; } case "SE.StartCharge": { param.StartCharge = Integer.parseInt(value); break; } case "SE.EndCharge": { param.EndCharge = Integer.parseInt(value); break; } case "SE.MS2StartCharge": { param.MS2StartCharge = Integer.parseInt(value); break; } case "SE.MS2EndCharge": { param.MS2EndCharge = Integer.parseInt(value); break; } case "SE.NoMissedScan": { param.NoMissedScan = Integer.parseInt(value); break; } case "SE.Denoise": { param.Denoise = Boolean.valueOf(value); break; } case "SE.EstimateBG": { param.EstimateBG = Boolean.valueOf(value); break; } case "SE.RemoveGroupedPeaks": { param.RemoveGroupedPeaks = Boolean.valueOf(value); break; } case "SE.MinFrag": { param.MinFrag = Integer.parseInt(value); break; } case "SE.IsoPattern": { param.IsoPattern = Float.valueOf(value); break; } case "SE.StartRT": { param.startRT = Float.valueOf(value); } case "SE.EndRT": { param.endRT = Float.valueOf(value); } //</editor-fold> } } } //</editor-fold> int mode = 1; if (args[1].equals("-mode2")) { mode = 2; } else if (args[1].equals("-mode1")) { mode = 1; } else { logger.error("-mode number not recongized. The program will exit."); } String mzXML = ""; String pepXML = ""; String mzXMLPath = ""; String pepXMLPath = ""; File mzXMLfile = null; File pepXMLfile = null; File mzXMLfolder = null; File pepXMLfolder = null; int idx = 0; if (mode == 1) { mzXML = args[2]; logger.info("Mode1 mzXML file: " + mzXML); mzXMLfile = new File(mzXML); if (!mzXMLfile.exists()) { logger.error("Mode1 mzXML file " + mzXMLfile.getAbsolutePath() + " cannot be found. The program will exit."); return; } pepXML = args[3]; logger.info("Mode1 pepXML file: " + pepXML); pepXMLfile = new File(pepXML); if (!pepXMLfile.exists()) { logger.error("Mode1 pepXML file " + pepXMLfile.getAbsolutePath() + " cannot be found. The program will exit."); return; } idx = 4; } else if (mode == 2) { mzXMLPath = args[2]; logger.info("Mode2 mzXML folder: " + mzXMLPath); mzXMLfolder = new File(mzXMLPath); if (!mzXMLfolder.exists()) { logger.error("Mode2 mzXML folder " + mzXMLfolder.getAbsolutePath() + " does not exist. The program will exit."); return; } pepXMLPath = args[3]; logger.info("Mode2 pepXML folder: " + pepXMLPath); pepXMLfolder = new File(pepXMLPath); if (!pepXMLfolder.exists()) { logger.error("Mode2 pepXML folder " + pepXMLfolder.getAbsolutePath() + " does not exist. The program will exit."); return; } idx = 4; } String outputfolder = ""; float MinProb = 0f; for (int i = idx; i < args.length; i++) { if (args[i].startsWith("-")) { if (args[i].equals("-ID")) { param.TargetIDOnly = true; logger.info("Detect ID feature only: true"); } if (args[i].startsWith("-O")) { outputfolder = args[i].substring(2); logger.info("Output folder: " + outputfolder); File outputfile = new File(outputfolder); if (!outputfolder.endsWith("\\") | outputfolder.endsWith("/")) { outputfolder += "/"; } if (!outputfile.exists()) { outputfile.mkdir(); } } if (args[i].startsWith("-C")) { try { NoFile = Integer.parseInt(args[i].substring(2)); logger.info("No of concurrent files: " + NoFile); } catch (Exception ex) { logger.error(args[i] + " is not a correct integer format, will process only one file at a time."); } } if (args[i].startsWith("-p")) { try { MinProb = Float.parseFloat(args[i].substring(2)); logger.info("probability threshold: " + MinProb); } catch (Exception ex) { logger.error(args[i] + " is not a correct format, will use 0 as threshold instead."); } } } } reader.close(); TandemParam tandemparam = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); PTMManager.GetInstance(); if (param.TargetIDOnly) { param.EstimateBG = false; param.ApexDelta = 1.5f; param.NoMissedScan = 10; param.MiniOverlapP = 0.2f; param.RemoveGroupedPeaks = false; param.CheckMonoIsotopicApex = false; param.DetectByCWT = false; param.FillGapByBK = false; param.IsoCorrThreshold = -1f; param.SmoothFactor = 3; } if (mode == 1) { logger.info("Processing " + mzXMLfile.getAbsolutePath() + "...."); long time = System.currentTimeMillis(); LCMSPeakMS1 LCMS1 = new LCMSPeakMS1(mzXMLfile.getAbsolutePath(), NoCPUs); LCMS1.SetParameter(param); LCMS1.Resume = false; if (!param.TargetIDOnly) { LCMS1.CreatePeakFolder(); } LCMS1.ExportPeakClusterTable = true; if (pepXMLfile.exists()) { tandemparam.InteractPepXMLPath = pepXMLfile.getAbsolutePath(); LCMS1.ParsePepXML(tandemparam, MinProb); logger.info("No. of PSMs included: " + LCMS1.IDsummary.PSMList.size()); logger.info("No. of Peptide ions included: " + LCMS1.IDsummary.GetPepIonList().size()); } if (param.TargetIDOnly) { LCMS1.SaveSerializationFile = false; } if (param.TargetIDOnly || !LCMS1.ReadPeakCluster()) { LCMS1.PeakClusterDetection(); } if (pepXMLfile.exists()) { LCMS1.AssignQuant(false); LCMS1.IDsummary.ExportPepID(outputfolder); } time = System.currentTimeMillis() - time; logger.info(LCMS1.ParentmzXMLName + " processed time:" + String.format("%d hour, %d min, %d sec", TimeUnit.MILLISECONDS.toHours(time), TimeUnit.MILLISECONDS.toMinutes(time) - TimeUnit.HOURS.toMinutes(TimeUnit.MILLISECONDS.toHours(time)), TimeUnit.MILLISECONDS.toSeconds(time) - TimeUnit.MINUTES.toSeconds(TimeUnit.MILLISECONDS.toMinutes(time)))); LCMS1.BaseClearAllPeaks(); LCMS1.SetSpectrumParser(null); LCMS1.IDsummary = null; LCMS1 = null; System.gc(); } else if (mode == 2) { LCMSID IDsummary = new LCMSID("", "", ""); logger.info("Parsing all pepXML files in " + pepXMLPath + "...."); for (File file : pepXMLfolder.listFiles()) { if (file.getName().toLowerCase().endsWith("pep.xml") || file.getName().toLowerCase().endsWith("pepxml")) { PepXMLParser pepXMLParser = new PepXMLParser(IDsummary, file.getAbsolutePath(), MinProb); } } HashMap<String, LCMSID> LCMSIDMap = IDsummary.GetLCMSIDFileMap(); ExecutorService executorPool = null; executorPool = Executors.newFixedThreadPool(NoFile); logger.info("Processing all mzXML files in " + mzXMLPath + "...."); for (File file : mzXMLfolder.listFiles()) { if (file.getName().toLowerCase().endsWith("mzxml")) { LCMSID id = LCMSIDMap.get(FilenameUtils.getBaseName(file.getName())); if (id == null || id.PSMList == null) { logger.warn("No IDs found in :" + FilenameUtils.getBaseName(file.getName()) + ". Quantification for this file is skipped"); continue; } if (!id.PSMList.isEmpty()) { MS1TargetQuantThread thread = new MS1TargetQuantThread(file, id, NoCPUs, outputfolder, param); executorPool.execute(thread); } } } LCMSIDMap.clear(); LCMSIDMap = null; IDsummary = null; executorPool.shutdown(); try { executorPool.awaitTermination(Long.MAX_VALUE, TimeUnit.NANOSECONDS); } catch (InterruptedException e) { logger.info("interrupted.."); } if (outputfolder == null | outputfolder.equals("")) { outputfolder = mzXMLPath; } logger.info("Merging PSM files.."); File output = new File(outputfolder); FileWriter writer = new FileWriter(output.getAbsolutePath() + "/PSM_merge.csv"); boolean header = false; for (File csvfile : output.listFiles()) { if (csvfile.getName().toLowerCase().endsWith("_psms.csv")) { BufferedReader outreader = new BufferedReader(new FileReader(csvfile)); String outline = outreader.readLine(); if (!header) { writer.write(outline + "\n"); header = true; } while ((outline = outreader.readLine()) != null) { writer.write(outline + "\n"); } outreader.close(); csvfile.delete(); } } writer.close(); } logger.info("MS1 quant module is complete."); } catch (Exception e) { Logger.getRootLogger().error(ExceptionUtils.getStackTrace(e)); throw e; } }
From source file:edu.harvard.liblab.ecru.LoadCsvData.java
/** * @param args//from w ww .j ava2 s. c o m */ public static void main(String[] args) { if (args.length > 7 | args.length == 0 || !args[0].equals("-f") || !args[2].equals("-u") || !args[4].equals("-i")) { System.err.println(USAGE); System.exit(1); } String filename = args[1].trim(); url = args[3].trim(); needsPrefix = !args[5].equals("unique"); isVerbose = (args.length == 7 && args[6].equals("-v")); System.out.println("Loading data from " + filename + " " + (needsPrefix ? "IDs will be prefixed " : " ")); long start = System.currentTimeMillis(); boolean isReading = false; CSVPrinter printer = null; CSVFormat format = CSVFormat.EXCEL.withHeader().withDelimiter(',').withAllowMissingColumnNames(true); CSVParser parser; try { if (isVerbose) { printer = new CSVPrinter(System.err, format.withDelimiter('|')); } parser = CSVParser.parse(new File(filename), Charset.forName("UTF-8"), format); solrSrvr = SingletonSolrServer.getSolrServer(url); for (CSVRecord record : parser) { numRecs++; HashMap<String, String> recMap = new HashMap<String, String>(); for (String field : FIELDS) { String value = null; try { value = record.get(field); } catch (IllegalArgumentException e) { if (e.getMessage().indexOf("expected one of") == -1) { e.printStackTrace(); System.exit(1); } } value = value == null ? "" : value.trim(); recMap.put(field, value); } String id = recMap.get("ID"); if (id.isEmpty()) { if (isVerbose) { System.err.println("Record missing ID: "); printer.printRecord(record); } } else { String type = recMap.get("Type"); SolrDocument sdoc = getDocFromSolr(recMap.get("ID")); try { if (type.toLowerCase().equals("course")) { processCourse(recMap, sdoc); isReading = false; } else { if (!isReading) { addUpdateCommit(); // just in case the preceeding course(s) are related } processReading(recMap, sdoc); isReading = true; } } catch (Exception e) { if (isVerbose) { System.err.println("Record # " + numRecs + " not used:\n\t" + e.getMessage()); } errRecs++; } } if (beans.size() > 20) { addUpdateCommit(); } } parser.close(); if (beans.size() > 0 || docUpdates.size() > 0) { addUpdateCommit(); } } catch (FileNotFoundException e) { System.err.println(filename + " not found"); System.exit(1); } catch (Exception e) { e.printStackTrace(); System.exit(1); } long end = System.currentTimeMillis(); long courseTime = (end - start) / (long) 1000; try { solrSrvr.optimize(); } catch (SolrServerException e) { e.printStackTrace(); System.exit(1); } catch (IOException e) { e.printStackTrace(); System.exit(1); } System.out.println(numRecs + " records found, of which " + errRecs + " had a problem; time: " + courseTime + " seconds " + ((courseTime > 60) ? ("(" + (courseTime / (long) 60) + " minutes)") : "")); System.exit(0); }