Package org.apache.mahout.common.iterator

Examples of org.apache.mahout.common.iterator.FileLineIterable

103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
      FPGrowth<String> fp1 = new org.apache.mahout.fpm.pfpgrowth.fpgrowth.FPGrowth<String>();

    Map<Set<String>,Long> results1 = Maps.newHashMap();
   
    fp1.generateTopKFrequentPatterns(
      new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename).openStream()), "\\s+"),

      fp1.generateFList(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename)
           .openStream()), "\\s+"), minSupport), minSupport, 100000,
      returnableFeatures,
      new MapCollector(results1), new DummyUpdater());

    FPGrowthObj<String> fp2 = new FPGrowthObj<String>();
    Map<Set<String>,Long> initialResults2 = Maps.newHashMap();
    fp2.generateTopKFrequentPatterns(
      new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename).openStream()), "\\s+"),

      fp2.generateFList(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename)
           .openStream()), "\\s+"), minSupport), minSupport, 100000,
        Sets.<String>newHashSet(),
      new MapCollector(initialResults2), new DummyUpdater());

    Map<Set<String>, Long> results2;
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
      InputStream in = null;
      try {
        in = fs.open(fst.getPath());

        StringBuilder file = new StringBuilder();
        for (String aFit : new FileLineIterable(in, getCharset(), false)) {
          file.append(aFit).append('\n');
        }
        String name = current.getName().equals(fst.getPath().getName())
            ? current.getName()
            : current.getName() + Path.SEPARATOR + fst.getPath().getName();
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
    }

    log.info("Reading probes...");
    List<Preference> probes = Lists.newArrayListWithExpectedSize(2817131);
    long currentMovieID = -1;
    for (String line : new FileLineIterable(new File(qualifyingTxt))) {
      if (line.contains(MOVIE_DENOTER)) {
        currentMovieID = Long.parseLong(line.replaceAll(MOVIE_DENOTER, ""));
      } else {
        long userID = Long.parseLong(SEPARATOR.split(line)[0]);
        probes.add(new GenericPreference(userID, currentMovieID, 0));
      }
    }
    log.info("{} probes read...", probes.size());

    log.info("Reading ratings, creating probe set at {}/probeSet/ratings.tsv ...", outputPath);
    writer = null;
    try {
      FSDataOutputStream outputStream = fs.create(new Path(outputPath, "probeSet/ratings.tsv"));
      writer = new BufferedWriter(new OutputStreamWriter(outputStream, Charsets.UTF_8));

      int ratingsProcessed = 0;
      for (String line : new FileLineIterable(new File(judgingTxt))) {
        if (line.contains(MOVIE_DENOTER)) {
          currentMovieID = Long.parseLong(line.replaceAll(MOVIE_DENOTER, ""));
        } else {
          float rating = Float.parseFloat(SEPARATOR.split(line)[0]);
          Preference pref = probes.get(ratingsProcessed);
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
      resultFile.delete();
    }
    Writer writer = null;
    try {
      writer = new OutputStreamWriter(new FileOutputStream(resultFile), Charsets.UTF_8);
      for (String line : new FileLineIterable(originalFile, false)) {
        int lastDelimiterStart = line.lastIndexOf(COLON_DELIMTER);
        if (lastDelimiterStart < 0) {
          throw new IOException("Unexpected input format on line: " + line);
        }
        String subLine = line.substring(0, lastDelimiterStart);
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    File resultFile = new File(new File(System.getProperty("java.io.tmpdir")), "taste.bookcrossing.txt");
    resultFile.delete();
    Writer writer = null;
    try {
      writer = new OutputStreamWriter(new FileOutputStream(resultFile), Charsets.UTF_8);
      for (String line : new FileLineIterable(originalFile, true)) {
        // 0 ratings are basically "no rating", ignore them (thanks h.9000)
        if (line.endsWith("\"0\"")) {
          continue;
        }
        // Delete replace anything that isn't numeric, or a semicolon delimiter. Make comma the delimiter.
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
  @Test
  public void testSpecificCaseFromRetailDataMinSup500() throws IOException {
    FPGrowth<String> fp = new FPGrowth<String>();
   
    StringRecordIterator it = new StringRecordIterator(new FileLineIterable(Resources.getResource(
      "retail.dat").openStream()), "\\s+");
    int pattern_41_36_39 = 0;
    while (it.hasNext()) {
      Pair<List<String>,Long> next = it.next();
      List<String> items = next.getFirst();
      if (items.contains("41") && items.contains("36") && items.contains("39")) {
        pattern_41_36_39++;
      }
    }
   
    final Map<Set<String>,Long> results = Maps.newHashMap();
   
    Set<String> returnableFeatures = Sets.newHashSet();
    returnableFeatures.add("41");
    returnableFeatures.add("36");
    returnableFeatures.add("39");
   
    fp.generateTopKFrequentPatterns(
      new StringRecordIterator(new FileLineIterable(Resources.getResource("retail.dat").openStream()), "\\s+"),

      fp.generateFList(new StringRecordIterator(new FileLineIterable(Resources.getResource("retail.dat")
          .openStream()), "\\s+"), 500), 500, 1000, returnableFeatures,
      new OutputCollector<String,List<Pair<List<String>,Long>>>() {
       
        @Override
        public void collect(String key, List<Pair<List<String>,Long>> value) {
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
    File input = new File(inputDir, "test.txt");
    params.set(PFPGrowth.INPUT, input.getAbsolutePath());
    params.set(PFPGrowth.OUTPUT, outputDir.getAbsolutePath());
    Writer writer = Files.newWriter(input, Charsets.UTF_8);
    try {
      StringRecordIterator it = new StringRecordIterator(new FileLineIterable(Resources.getResource(
        "retail.dat").openStream()), "\\s+");
      Collection<List<String>> transactions = Lists.newArrayList();
     
      while (it.hasNext()) {
        Pair<List<String>,Long> next = it.next();
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
  /**
   * Test Parallel FPGrowth on retail data using top-level runPFPGrowth() method
   */
  @Test
  public void testRetailDataMinSup100() throws Exception {
    StringRecordIterator it = new StringRecordIterator(new FileLineIterable(Resources.getResource(
      "retail_results_with_min_sup_100.dat").openStream()), "\\s+");
    Map<Set<String>,Long> expectedResults = Maps.newHashMap();
    while (it.hasNext()) {
      Pair<List<String>,Long> next = it.next();
      List<String> items = Lists.newArrayList(next.getFirst());
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
  /**
   * Test Parallel FPG on retail data, running various stages individually
   */
  @Test
  public void testRetailDataMinSup100InSteps() throws Exception {
    StringRecordIterator it = new StringRecordIterator(new FileLineIterable(Resources.getResource(
      "retail_results_with_min_sup_100.dat").openStream()), "\\s+");   
    Map<Set<String>,Long> expectedResults = Maps.newHashMap();
    while (it.hasNext()) {
      Pair<List<String>,Long> next = it.next();
      List<String> items = Lists.newArrayList(next.getFirst());
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
    params.set(PFPGrowth.INPUT, input.getAbsolutePath());
    params.set(PFPGrowth.OUTPUT, outputDir.getAbsolutePath());

    Writer writer = Files.newWriter(input, Charsets.UTF_8);
    try {
      StringRecordIterator it = new StringRecordIterator(new FileLineIterable(Resources.getResource(
        "retail.dat").openStream()), "\\s+");
      Collection<List<String>> transactions = Lists.newArrayList();
     
      while (it.hasNext()) {
        Pair<List<String>,Long> next = it.next();
View Full Code Here
TOP

Related Classes of org.apache.mahout.common.iterator.FileLineIterable

  • mia.recommender.ch05.GenderRescorer
  • org.apache.mahout.cf.taste.example.bookcrossing.BookCrossingDataModel
  • org.apache.mahout.cf.taste.example.grouplens.BooleanDataAndDateDataModel
  • org.apache.mahout.cf.taste.example.grouplens.GroupLensDataModel
  • org.apache.mahout.cf.taste.example.kddcup.track2.TrackItemSimilarity
  • org.apache.mahout.cf.taste.example.netflix.NetflixDataModel
  • org.apache.mahout.cf.taste.example.netflix.NetflixFileDataModel
  • org.apache.mahout.cf.taste.example.netflix.TransposeToByUser
  • org.apache.mahout.cf.taste.hadoop.example.als.netflix.NetflixDatasetConverter
  • org.apache.mahout.cf.taste.hadoop.item.AggregateAndRecommendReducer
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.