Package org.apache.mahout.common.iterator

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

33
34
35
36
37
38
39
40
41
42
  private final FastByIDMap<TrackData> trackData;

  TrackItemSimilarity(File dataFileDirectory) throws IOException {
    trackData = new FastByIDMap<TrackData>();
    for (String line : new FileLineIterable(KDDCupDataModel.getTrackFile(dataFileDirectory))) {
      TrackData trackDatum = new TrackData(line);
      trackData.put(trackDatum.getTrackID(), trackDatum);
    }
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
    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
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 {
    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
67
68
69
70
71
72
73
74
75
76
77
    File input = new File(inputDir, "synth_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(
        "FPGsynth.dat").openStream()), "\\s+");
      Collection<List<String>> transactions = Lists.newArrayList();
     
      while (it.hasNext()) {
        Pair<List<String>,Long> next = it.next();
View Full Code Here
113
114
115
116
117
118
119
120
121
122
123
124
125
    final Map<Set<String>,Long> seqResult = Maps.newHashMap();
   
    FPGrowthObj<String> fpSeq = new FPGrowthObj<String>();
    fpSeq.generateTopKFrequentPatterns(
      new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename).openStream()), "\\s+"),

      fpSeq.generateFList(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename)
           .openStream()), "\\s+"), minSupport), minSupport, 1000000,
      null,
      new OutputCollector<String,List<Pair<List<String>,Long>>>() {
       
        @Override
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
             + "org.apache.hadoop.io.serializer.WritableSerialization");
    // Dont ever forget this. People should keep track of how hadoop conf
    // parameters can make or break a piece of code
   
    Set<String> categories = Sets.newHashSet();
    for (String line : new FileLineIterable(new File(catFile))) {
      categories.add(line.trim().toLowerCase(Locale.ENGLISH));
    }
   
    Stringifier<Set<String>> setStringifier =
        new DefaultStringifier<Set<String>>(conf, GenericsUtil.getClass(categories));
View Full Code Here
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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
    FPGrowthObj<String> fp = new FPGrowthObj<String>();
   
    String inputFilename = "FPGsynth.dat";

    StringRecordIterator it =
        new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename).openStream()), "\\s+");
    int patternCnt_10_13_1669 = 0;
    int patternCnt_10_13 = 0;
    while (it.hasNext()) {
      Pair<List<String>,Long> next = it.next();
      List<String> items = next.getFirst();
      if (items.contains("10") && items.contains("13")) {
        patternCnt_10_13++;
        if (items.contains("1669")) {
          patternCnt_10_13_1669++;
        }
      }
    }

    int minSupport = 50;
    if (patternCnt_10_13_1669 < minSupport) {
      throw new IllegalStateException("the test is broken or data is missing ("
                                          + patternCnt_10_13_1669 + ", "
                                          + patternCnt_10_13 + ')');
    }

    final Map<Set<String>,Long> results = Maps.newHashMap();
   
    Set<String> features_10_13 = Sets.newHashSet();
    features_10_13.add("10");
    features_10_13.add("13");

    Set<String> returnableFeatures = Sets.newHashSet();
    returnableFeatures.add("10");
    returnableFeatures.add("13");
    returnableFeatures.add("1669");
   
    fp.generateTopKFrequentPatterns(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename).openStream()), "\\s+"),

                                    fp.generateFList(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename)
                                                                                                   .openStream()), "\\s+"), minSupport), minSupport, 100000,
                                    returnableFeatures,
                                    new OutputCollector<String,List<Pair<List<String>,Long>>>() {
       
                                      @Override
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
    final Map<Set<String>,Long> results1 = Maps.newHashMap();

    String inputFilename = "FPGsynth.dat";
    int minSupport = 100;
    fp1.generateTopKFrequentPatterns(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename).openStream()), "\\s+"),

                                     fp1.generateFList(new StringRecordIterator(new FileLineIterable(Resources.getResource(inputFilename)
                                                                                                     .openStream()), "\\s+"), minSupport), minSupport, 1000000,
                                     returnableFeatures,
                                     new OutputCollector<String,List<Pair<List<String>,Long>>>() {
       
                                       @Override
                                         public void collect(String key, List<Pair<List<String>,Long>> value) {
         
                                         for (Pair<List<String>,Long> v : value) {
                                           List<String> l = v.getFirst();
                                           results1.put(Sets.newHashSet(l), v.getSecond());
                                           System.out.println("found pat ["+v.getSecond()+"]: "+ v.getFirst());
                                         }
                                       }
       
                                     }, new StatusUpdater() {
       
                                         @Override
                                           public void update(String status) {}
                                       });

    FPGrowthObj<String> fp2 = new FPGrowthObj<String>();
    final 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, 1000000,
                                     Sets.<String>newHashSet(),
                                     new OutputCollector<String,List<Pair<List<String>,Long>>>() {
       
                                       @Override
View Full Code Here
895
896
897
898
899
900
901
902
903
904
905
     assertEquals(3.5, recommendedItem.getValue(), 0.05);
   }

  static Map<Pair<Long,Long>, Double> readSimilarities(File file) throws IOException {
    Map<Pair<Long,Long>, Double> similarities = Maps.newHashMap();
    for (String line : new FileLineIterable(file)) {
      String[] parts = line.split("\t");
      similarities.put(new Pair<Long,Long>(Long.parseLong(parts[0]), Long.parseLong(parts[1])),
          Double.parseDouble(parts[2]));
    }
    return similarities;
View Full Code Here
905
906
907
908
909
910
911
912
913
914
915
    return similarities;
  }

  static Map<Long,List<RecommendedItem>> readRecommendations(File file) throws IOException {
    Map<Long,List<RecommendedItem>> recommendations = Maps.newHashMap();
    for (String line : new FileLineIterable(file)) {

      String[] keyValue = line.split("\t");
      long userID = Long.parseLong(keyValue[0]);
      String[] tokens = keyValue[1].replaceAll("\\[", "")
          .replaceAll("\\]", "").split(",");
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.