Package org.apache.mahout.vectorizer.encoders

Examples of org.apache.mahout.vectorizer.encoders.Dictionary

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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
    output.mkdirs();
    int numCats = Integer.parseInt(getOption("categories"));
    int cardinality = Integer.parseInt(getOption("cardinality", "100000"));
    int threadCount = Integer.parseInt(getOption("threads", "20"));
    int poolSize = Integer.parseInt(getOption("poolSize", "5"));
    Dictionary asfDictionary = new Dictionary();
    AdaptiveLogisticRegression learningAlgorithm =
        new AdaptiveLogisticRegression(numCats, cardinality, new L1(), threadCount, poolSize);
    learningAlgorithm.setInterval(800);
    learningAlgorithm.setAveragingWindow(500);

    //We ran seq2encoded and split input already, so let's just build up the dictionary
    Configuration conf = new Configuration();
    PathFilter trainFilter = new PathFilter() {
      @Override
      public boolean accept(Path path) {
        return path.getName().contains("training");
      }
    };
    SequenceFileDirIterator<Text, VectorWritable> iter =
        new SequenceFileDirIterator<Text, VectorWritable>(new Path(base.toString()),
                                                          PathType.LIST,
                                                          trainFilter,
                                                          null,
                                                          true,
                                                          conf);
    long numItems = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      asfDictionary.intern(next.getFirst().toString());
      numItems++;
    }

    System.out.println(numItems + " training files");


    SGDInfo info = new SGDInfo();

    iter = new SequenceFileDirIterator<Text, VectorWritable>(new Path(base.toString()), PathType.LIST, trainFilter,
            null, true, conf);
    int k = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      String ng = next.getFirst().toString();
      int actual = asfDictionary.intern(ng);
      //we already have encoded
      learningAlgorithm.train(actual, next.getSecond().get());
      k++;
      State<AdaptiveLogisticRegression.Wrapper, CrossFoldLearner> best = learningAlgorithm.getBest();
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
    int leakType = 0;
    if (args.length > 1) {
      leakType = Integer.parseInt(args[1]);
    }

    Dictionary newsGroups = new Dictionary();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setProbes(2);
    AdaptiveLogisticRegression learningAlgorithm =
        new AdaptiveLogisticRegression(20, NewsgroupHelper.FEATURES, new L1());
    learningAlgorithm.setInterval(800);
    learningAlgorithm.setAveragingWindow(500);

    List<File> files = Lists.newArrayList();
    for (File newsgroup : base.listFiles()) {
      if (newsgroup.isDirectory()) {
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    Collections.shuffle(files);
    System.out.println(files.size() + " training files");
    SGDInfo info = new SGDInfo();

    int k = 0;


    for (File file : files) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

      Vector v = helper.encodeFeatureVector(file, actual, leakType, overallCounts);
      learningAlgorithm.train(actual, v);

      k++;
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
    //contains the best model
    OnlineLogisticRegression classifier =
        ModelSerializer.readBinary(new FileInputStream(modelFile), OnlineLogisticRegression.class);


    Dictionary asfDictionary = new Dictionary();
    Configuration conf = new Configuration();
    PathFilter testFilter = new PathFilter() {
      @Override
      public boolean accept(Path path) {
        return path.getName().contains("test");
      }
    };
    SequenceFileDirIterator<Text, VectorWritable> iter =
        new SequenceFileDirIterator<Text, VectorWritable>(new Path(base.toString()), PathType.LIST, testFilter,
        null, true, conf);

    long numItems = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      asfDictionary.intern(next.getFirst().toString());
      numItems++;
    }

    System.out.println(numItems + " test files");
    ResultAnalyzer ra = new ResultAnalyzer(asfDictionary.values(), "DEFAULT");
    iter = new SequenceFileDirIterator<Text, VectorWritable>(new Path(base.toString()), PathType.LIST, testFilter,
            null, true, conf);
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      String ng = next.getFirst().toString();

      int actual = asfDictionary.intern(ng);
      Vector result = classifier.classifyFull(next.getSecond().get());
      int cat = result.maxValueIndex();
      double score = result.maxValue();
      double ll = classifier.logLikelihood(actual, next.getSecond().get());
      ClassifierResult cr = new ClassifierResult(asfDictionary.values().get(cat), score, ll);
      ra.addInstance(asfDictionary.values().get(actual), cr);

    }
    output.println(ra);
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
    assertEquals(1.5849625007211563, v.maxValue(), 1.0e-6);
  }

  @Test
  public void testDictionaryOrder() {
    Dictionary dict = new Dictionary();

    dict.intern("a");
    dict.intern("d");
    dict.intern("c");
    dict.intern("b");
    dict.intern("qrz");

    assertEquals("[a, d, c, b, qrz]", dict.values().toString());

    Dictionary dict2 = Dictionary.fromList(dict.values());
    assertEquals("[a, d, c, b, qrz]", dict2.values().toString());

  }
View Full Code Here
104
105
106
107
108
109
110
   * @param typeMap               A map describing the types of the predictor variables.
   */
  public CsvRecordFactory(String targetName, Map<String, String> typeMap) {
    this.targetName = targetName;
    this.typeMap = typeMap;
    targetDictionary = new Dictionary();
  }
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
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
    int leakType = 0;
    if (args.length > 1) {
      leakType = Integer.parseInt(args[1]);
    }

    Dictionary newsGroups = new Dictionary();

    encoder.setProbes(2);
    AdaptiveLogisticRegression learningAlgorithm = new AdaptiveLogisticRegression(20, FEATURES, new L1());
    learningAlgorithm.setInterval(800);
    learningAlgorithm.setAveragingWindow(500);

    List<File> files = Lists.newArrayList();
    for (File newsgroup : base.listFiles()) {
      if (newsgroup.isDirectory()) {
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    Collections.shuffle(files);
    System.out.printf("%d training files\n", files.size());

    double averageLL = 0;
    double averageCorrect = 0;

    int k = 0;
    double step = 0;
    int[] bumps = {1, 2, 5};
    for (File file : files.subList(0, 3000)) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

      Vector v = encodeFeatureVector(file, actual, leakType);
      learningAlgorithm.train(actual, v);

      k++;
View Full Code Here
129
130
131
132
133
134
135
   * @param typeMap               A map describing the types of the predictor variables.
   */
  public CsvRecordFactory(String targetName, Map<String, String> typeMap) {
    this.targetName = targetName;
    this.typeMap = typeMap;
    targetDictionary = new Dictionary();
  }
View Full Code Here
108
109
110
111
112
113
114
   * @param typeMap               A map describing the types of the predictor variables.
   */
  public CsvRecordFactory(String targetName, Map<String, String> typeMap) {
    this.targetName = targetName;
    this.typeMap = typeMap;
    targetDictionary = new Dictionary();
  }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
    //contains the best model
    OnlineLogisticRegression classifier =
        ModelSerializer.readBinary(new FileInputStream(modelFile), OnlineLogisticRegression.class);


    Dictionary asfDictionary = new Dictionary();
    //<String> overallCounts = HashMultiset.create();
    Configuration conf = new Configuration();
    PathFilter testFilter = new PathFilter() {
      @Override
      public boolean accept(Path path) {
        return path.getName().contains("test");
      }
    };
    SequenceFileDirIterator<Text, VectorWritable> iter = new SequenceFileDirIterator<Text, VectorWritable>(new Path(base.toString()), PathType.LIST, testFilter,
            null, true, conf);

    long numItems = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      asfDictionary.intern(next.getFirst().toString());
      numItems++;
    }

    System.out.printf("%d test files\n", numItems);
    ResultAnalyzer ra = new ResultAnalyzer(asfDictionary.values(), "DEFAULT");
    iter = new SequenceFileDirIterator<Text, VectorWritable>(new Path(base.toString()), PathType.LIST, testFilter,
            null, true, conf);
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      String ng = next.getFirst().toString();

      int actual = asfDictionary.intern(ng);
      Vector result = classifier.classifyFull(next.getSecond().get());
      int cat = result.maxValueIndex();
      double score = result.maxValue();
      double ll = classifier.logLikelihood(actual, next.getSecond().get());
      ClassifierResult cr = new ClassifierResult(asfDictionary.values().get(cat), score, ll);
      ra.addInstance(asfDictionary.values().get(actual), cr);

    }
    output.printf("%s\n\n", ra.toString());
  }
View Full Code Here
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
91
92
93
94
95
96
97
    File base = new File(inputFile);
    //contains the best model
    OnlineLogisticRegression classifier = ModelSerializer.readBinary(new FileInputStream(modelFile), OnlineLogisticRegression.class);


    Dictionary newsGroups = new Dictionary();
    Multiset<String> overallCounts = HashMultiset.create();

    List<File> files = Lists.newArrayList();
    for (File newsgroup : base.listFiles()) {
      if (newsgroup.isDirectory()) {
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    System.out.printf("%d test files\n", files.size());
    ResultAnalyzer ra = new ResultAnalyzer(newsGroups.values(), "DEFAULT");
    for (File file : files) {
      String ng = file.getParentFile().getName();

      int actual = newsGroups.intern(ng);
      NewsgroupHelper helper = new NewsgroupHelper();
      Vector input = helper.encodeFeatureVector(file, actual, 0, overallCounts); //no leak type ensures this is a normal vector
      Vector result = classifier.classifyFull(input);
      int cat = result.maxValueIndex();
      double score = result.maxValue();
      double ll = classifier.logLikelihood(actual, input);
      ClassifierResult cr = new ClassifierResult(newsGroups.values().get(cat), score, ll);
      ra.addInstance(newsGroups.values().get(actual), cr);

    }
    output.printf("%s\n\n", ra.toString());
  }
View Full Code Here
TOP

Related Classes of org.apache.mahout.vectorizer.encoders.Dictionary

  • mia.classifier.ch14.TrainNewsGroups
  • mia.classifier.ch16.train.TrainNewsGroups
  • org.apache.mahout.classifier.sgd.CsvRecordFactory
  • org.apache.mahout.classifier.sgd.CsvRecordFactoryTest
  • org.apache.mahout.classifier.sgd.OnlineLogisticRegressionTest
  • org.apache.mahout.classifier.sgd.TestASFEmail
  • org.apache.mahout.classifier.sgd.TestNewsGroups
  • org.apache.mahout.classifier.sgd.TrainASFEmail
  • org.apache.mahout.classifier.sgd.TrainNewsGroups
    • 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.