List of usage examples for org.apache.hadoop.util ProgramDriver driver
public void driver(String[] argv) throws Throwable
From source file:edu.uci.ics.fuzzyjoin.hadoop.FuzzyJoinDriver.java
License:Apache License
public static void main(String argv[]) { int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try {/*from ww w. j av a2 s.c o m*/ pgd.addClass("dummyjob", DummyJob.class, ""); pgd.addClass("recordbuild", RecordBuild.class, ""); pgd.addClass("fuzzyjoin", FuzzyJoin.class, ""); pgd.addClass("tokensbasic", TokensBasic.class, ""); pgd.addClass("tokensimproved", TokensImproved.class, ""); // pgd.addClass("ridpairsbasic", RIDPairsBasic.class, ""); pgd.addClass("ridpairsimproved", RIDPairsImproved.class, ""); pgd.addClass("ridpairsppjoin", RIDPairsPPJoin.class, ""); pgd.addClass("recordpairsbasic", RecordPairsBasic.class, ""); pgd.addClass("recordpairsimproved", RecordPairsImproved.class, ""); pgd.addClass("ridrecordpairsimproved", RIDRecordPairsImproved.class, ""); pgd.addClass("ridrecordpairsppjoin", RIDRecordPairsPPJoin.class, ""); pgd.addClass("recordgenerate", RecordGenerate.class, ""); pgd.addClass("recordbalance", RecordBalance.class, ""); pgd.driver(argv); // Success exitCode = 0; } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:edu.ucsb.cs.knn.KnnDriver.java
License:Apache License
/** * Presents the available job options for the user to choose from. Then * invoke the class responsible for configuring the job. *//* www .j ava 2 s .c o m*/ public static void main(String argv[]) { int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try { pgd.addClass("invindex", SongInvertedIndexMain.class, "Generate song inverted index for Yahoo data."); pgd.addClass("forindex", UserForwardIndexMain.class, "Generate user forward index for Yahoo data."); pgd.addClass("invertedknn", InvertedMain.class, " knn over songs inverted index."); pgd.addClass("hybridknn", HybridMain.class, " not yet done ...knn over songs forward index."); // pgd.addClass("estimateknn", InvertedMain.class, " TO-DO."); pgd.addClass("readseq", SequenceReader.class, " View sequence file as text to read."); pgd.addClass("queryknn", QueryMain.class, " Query the KNN results for recommendation."); pgd.driver(argv); exitCode = 0; } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:edu.ucsb.cs.lsh.LshDriver.java
License:Apache License
public static void main(String argv[]) { int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try {/*from w w w .j av a2 s . co m*/ pgd.addClass("randomlsh", ProjectionLshDriver.class, "Partition input vectors according to random projections."); pgd.addClass("minhashlsh", MinHashLshDriver.class, "Partition input vectors according to minhash values."); pgd.addClass("lshstat", LshStat.class, "Collect statistics from binray lshpartitions/"); pgd.driver(argv); } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:edu.ucsb.cs.preprocessing.PreprocessDriver.java
License:Apache License
/** * Prints these options to chose from:<br> * - [clean] documents to produce document ID: bag of cleaned words. <br> * - [hash] bag of words into bag of hashed tokens.<br> * - Produce [sequence] records [LongWritable,FeatureWeightArrayWritable] <br> * - [seq] deals with writing/reading/combining sequence files. * //ww w. j av a 2s . c o m * @param argv : command line inputs */ public static void main(String argv[]) { int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try { pgd.addClass("clean", CleanPagesDriver.class, "A MapReduce job to clean input pages. See options."); pgd.addClass("hash", HashPagesDriver.class, "A MapReduce job to collect features then hash input data into [docId <features>] with associated weights if desired. "); pgd.addClass("seq", SequenceDriver.class, "For writing/reading/merging sequence files. See optoins.\n\n"); pgd.driver(argv); } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:edu.ucsb.cs.sort.SortDriver.java
License:Apache License
public static void main(String args[]) throws UnsupportedEncodingException { ProgramDriver pgd = new ProgramDriver(); try {/* w ww. j av a 2 s . c o m*/ pgd.addClass("lengthsort", LengthSortMain.class, "\tSort documents based on length"); pgd.addClass("normsort", NormSortMain.class, "\tSort documents based on p-norm"); pgd.addClass("maxwsort", MaxwSortMain.class, "\tSort documents based on max weight");// del pgd.addClass("sigsort", SigSortMain.class, "\tSort documents based on their signatures"); pgd.driver(args); } catch (Throwable e) { e.printStackTrace(); } }
From source file:edu.umn.cs.spatialHadoop.operations.Main.java
License:Open Source License
public static void main(String[] args) { int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try {/*from w w w. j a va 2 s. c om*/ pgd.addClass("rangequery", RangeQuery.class, "Finds all objects in the query range given by a rectangle"); pgd.addClass("knn", KNN.class, "Finds the k nearest neighbor in a file to a point"); pgd.addClass("dj", DistributedJoin.class, "Computes the spatial join between two input files using the " + "distributed join algorithm"); pgd.addClass("sjmr", SJMR.class, "Computes the spatial join between two input files using the " + "SJMR algorithm"); pgd.addClass("index", Indexer.class, "Spatially index a file using a specific indexer"); pgd.addClass("oldindex", Repartition.class, "Spatially index a file using a specific indexer"); pgd.addClass("mbr", FileMBR.class, "Finds the minimal bounding rectangle of an input file"); pgd.addClass("readfile", ReadFile.class, "Retrieve some information about the index of a file"); pgd.addClass("sample", Sampler.class, "Reads a random sample from the input file"); pgd.addClass("generate", RandomSpatialGenerator.class, "Generates a random file containing spatial data"); pgd.addClass("union", Union.class, "Computes the union of input shapes"); pgd.addClass("uunion", UltimateUnion.class, "Computes the union of input shapes using the UltimateUnion algorithm"); pgd.addClass("delaunay", DelaunayTriangulation.class, "Computes the Delaunay triangulation for a set of points"); pgd.addClass("multihdfplot", MultiHDFPlot.class, "Plots NASA datasets in the spatiotemporal range provided by user"); pgd.addClass("hdfplot", HDFPlot.class, "Plots a heat map for a give NASA dataset"); pgd.addClass("gplot", GeometricPlot.class, "Plots a file to an image"); pgd.addClass("hplot", HeatMapPlot.class, "Plots a heat map to an image"); pgd.addClass("lakesplot", LakesPlot.class, "Plots lakes to SVG image"); pgd.addClass("hdfx", HDFToText.class, "Extracts data from a set of HDF files to text files"); pgd.addClass("skyline", Skyline.class, "Computes the skyline of an input set of points"); pgd.addClass("convexhull", ConvexHull.class, "Computes the convex hull of an input set of points"); pgd.addClass("farthestpair", FarthestPair.class, "Computes the farthest pair of point of an input set of points"); pgd.addClass("closestpair", ClosestPair.class, "Computes the closest pair of point of an input set of points"); pgd.addClass("distcp", DistributedCopy.class, "Copies a directory or file using a MapReduce job"); pgd.addClass("vizserver", ShahedServer.class, "Starts a server that handles visualization requests"); pgd.addClass("staggquery", SpatioAggregateQueries.class, "Runs a spatio temporal aggregate query on HDF files"); pgd.addClass("shahedindexer", AggregateQuadTree.class, "Creates a multilevel spatio-temporal indexer for NASA data"); pgd.addClass("hadoopviz", HadoopvizServer.class, "Run Hadoopviz Server"); pgd.addClass("mplot", MagickPlot.class, "Plot using ImageMagick"); pgd.driver(args); // Success exitCode = 0; } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:hadoop.examples.mapreduce.ExampleDriver.java
License:Open Source License
public static void main(String[] args) { int exitCode = -1; try {//w w w . ja v a 2 s. c om ProgramDriver prog = new ProgramDriver(); prog.addClass("wordcountV1", WordCountV1.class, " Word count Version 1"); prog.addClass("wordcountV2", WordCountV2.class, " Word count Version 2"); prog.driver(args); //Success exitCode = 0; } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:hjkoo.Driver.java
License:Apache License
public static void main(String argv[]) { int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try {/*from ww w. j a v a 2 s . c o m*/ pgd.addClass("skewedreducer", SkewedReducer.class, "Test for Skewed Reducer"); pgd.addClass("wordcount", WordCount.class, "WordCount example"); pgd.addClass("invind", InvInd.class, "Inverted Index"); pgd.addClass("kmeans", kmeans.class, "sequential_kmeans clustering"); pgd.addClass("kmeans2", kmeans2.class, "parallel_kmeans clustering"); /* pgd.addClass("aggregatewordcount", AggregateWordCount.class, "An Aggregate based map/reduce program that counts the words in the input files."); pgd.addClass("aggregatewordhist", AggregateWordHistogram.class, "An Aggregate based map/reduce program that computes the histogram of the words in the input files."); pgd.addClass("grep", Grep.class, "A map/reduce program that counts the matches of a regex in the input."); pgd.addClass("randomwriter", RandomWriter.class, "A map/reduce program that writes 10GB of random data per node."); pgd.addClass("randomtextwriter", RandomTextWriter.class, "A map/reduce program that writes 10GB of random textual data per node."); pgd.addClass("sort", Sort.class, "A map/reduce program that sorts the data written by the random writer."); pgd.addClass("pi", PiEstimator.class, "A map/reduce program that estimates Pi using monte-carlo method."); pgd.addClass("pentomino", DistributedPentomino.class, "A map/reduce tile laying program to find solutions to pentomino problems."); pgd.addClass("secondarysort", SecondarySort.class, "An example defining a secondary sort to the reduce."); pgd.addClass("sudoku", Sudoku.class, "A sudoku solver."); pgd.addClass("sleep", SleepJob.class, "A job that sleeps at each map and reduce task."); pgd.addClass("join", Join.class, "A job that effects a join over sorted, equally partitioned datasets"); pgd.addClass("multifilewc", MultiFileWordCount.class, "A job that counts words from several files."); pgd.addClass("dbcount", DBCountPageView.class, "An example job that count the pageview counts from a database."); pgd.addClass("teragen", TeraGen.class, "Generate data for the terasort"); pgd.addClass("terasort", TeraSort.class, "Run the terasort"); pgd.addClass("teravalidate", TeraValidate.class, "Checking results of terasort"); */ pgd.driver(argv); // Success exitCode = 0; } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:net.java.jatextmining.JaTextminingDriver.java
License:Apache License
/** * A main method for this class./*from w w w. ja v a 2 s.c o m*/ * @param argv A arguments from command-line. */ public static void main(String[] argv) { int exitCode = -1; ProgramDriver driver = new ProgramDriver(); try { driver.addClass("wordcount", JaWordCounter.class, "A map/reduce " + "program that counts the words from Japnese document."); driver.addClass("cooccurrence", JaCoOccurrence.class, "A map/reduce" + " program that count the co-occurrence word."); driver.addClass("tokenize", TokenizerSample.class, "A Sample of" + " tokenizing Japanese document with map/reduce"); driver.driver(argv); exitCode = 0; } catch (Throwable e) { e.printStackTrace(); } System.exit(exitCode); }
From source file:org.ankus.mapreduce.AnkusDriver.java
License:Apache License
public static void main(String[] args) { ProgramDriver programDriver = new ProgramDriver(); try {/*from w ww.jav a 2s . c om*/ /** * Similarity and distance algorithms */ // Boolean Set programDriver.addClass(Constants.ALGORITHM_BOOLEAN_DATA_CORRELATION, BooleanSetDriver.class, "BooleanSet driver based map/reduce program that computes the data of the boolean set in the input files."); // Numerical Set programDriver.addClass(Constants.ALGORITHM_NUMERIC_DATA_CORRELATION, NumericSetDriver.class, "NumericSet driver based map/reduce program that computes the data of the numeric set in the input files."); // String Set programDriver.addClass(Constants.ALGORITHM_STRING_DATA_CORRELATION, StringSetDriver.class, "StringSet driver based map/reduce program that computes the data of the string set in the input files."); /** * Collaborative Filtering by CF-base */ programDriver.addClass(Constants.ALGORITHM_COLLABORATIVE_FILTERING_BASED_SIMILARITY, CFBasedSimilarityDriver.class, "Collaborative filtering driver based map/reduce program that computes the data of the data set in the input files."); /** * Recommendation system by user-base */ programDriver.addClass(Constants.ALGORITHM_USER_BASED_RECOMMENDATION, UserbasedRecommendationDriver.class, "Recommendation driver user based map/reduce program that computes the data of the data set in the input files."); /** * Development Finish Classes (need to generate comments and documents of codes)> * statistics.NumericStatsDriver * statistics.NominalStatsDriver * statistics.CertaintyFactorSumDriver * preprocessing.Normalize */ programDriver.addClass(Constants.ALGORITHM_NUMERIC_STATS, NumericStatsDriver.class, "Statistics for Numeric Attributes of Data"); programDriver.addClass(Constants.ALGORITHM_NOMINAL_STATS, NominalStatsDriver.class, "Statistics(frequency/ratio) for Nominal Attributes of Data"); programDriver.addClass(Constants.ALGORITHM_CERTAINTYFACTOR_SUM, CertaintyFactorSumDriver.class, "Certainty Factor based Summation for Numeric Attributes of Data"); programDriver.addClass(Constants.ALGORITHM_NORMALIZE, NormalizeDriver.class, "Normalization for Numeric Attributes of Data"); programDriver.addClass(Constants.ALGORITHM_KMEANS_CLUSTERING, KMeansDriver.class, "K-means clustering Algorithm"); programDriver.driver(args); // Success System.exit(0); } catch (Throwable e) { e.printStackTrace(); System.exit(-1); } }