Package org.apache.mahout.common.iterator

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

73
74
75
76
77
78
79
80
81
82
83
    File outputDir2 = getTestTempDir("frequentpatterns2");
    paramsImpl2.set(PFPGrowth.OUTPUT, outputDir2.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
38
39
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
  @Test
  public void testSpecificCaseFromRetailDataMinSup500() throws IOException {
    FPGrowthObj<String> fp = new FPGrowthObj<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
39
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
  @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
63
64
65
66
67
68
69
70
71
72
73
    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
91
92
93
94
95
96
97
98
99
100
101
  /**
   * 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
143
144
145
146
147
148
149
150
151
152
153
  /**
   * 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
86
87
88
89
90
91
92
93
94
95
96
    indexItemIDMap = TasteHadoopUtils.readItemIDIndexMap(conf.get(ITEMID_INDEX_PATH), conf);

    String itemFilePathString = conf.get(ITEMS_FILE);
    if (itemFilePathString != null) {
      itemsToRecommendFor = new FastIDSet();
      for (String line : new FileLineIterable(HadoopUtil.openStream(new Path(itemFilePathString), conf))) {
        try {
          itemsToRecommendFor.add(Long.parseLong(line));
        } catch (NumberFormatException nfe) {
          log.warn("itemsFile line ignored: {}", line);
        }
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
61
62
63
64
65
66
67
68
69
70
71
        Path unqualifiedUsersFilePath = new Path(usersFilePathString);
        FileSystem fs = FileSystem.get(unqualifiedUsersFilePath.toUri(), jobConf);
        usersToRecommendFor = new FastIDSet();
        Path usersFilePath = unqualifiedUsersFilePath.makeQualified(fs);
        in = fs.open(usersFilePath);
        for (String line : new FileLineIterable(in)) {
          try {
            usersToRecommendFor.add(Long.parseLong(line));
          } catch (NumberFormatException nfe) {
            log.warn("usersFile line ignored: {}", line);
          }
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
        = new org.apache.mahout.fpm.pfpgrowth.fpgrowth2.FPGrowthObj<String>();
      Collection<String> features = new HashSet<String>();

      try {
        fp.generateTopKFrequentPatterns(
                new StringRecordIterator(new FileLineIterable(new File(input), encoding, false), pattern),
                fp.generateFList(
                        new StringRecordIterator(new FileLineIterable(new File(input), encoding, false), pattern),
                        minSupport),
                minSupport,
                maxHeapSize,
                features,
                new StringOutputConverter(new SequenceFileOutputCollector<Text, TopKStringPatterns>(writer)),
                new ContextStatusUpdater(null));
      } finally {
        Closeables.closeQuietly(writer);
      }
    } else {
      FPGrowth<String> fp = new FPGrowth<String>();
      Collection<String> features = new HashSet<String>();
      try {
        fp.generateTopKFrequentPatterns(
                new StringRecordIterator(new FileLineIterable(new File(input), encoding, false), pattern),
                fp.generateFList(
                        new StringRecordIterator(new FileLineIterable(new File(input), encoding, false), pattern),
                        minSupport),
                minSupport,
                maxHeapSize,
                features,
                new StringOutputConverter(new SequenceFileOutputCollector<Text, TopKStringPatterns>(writer)),
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.