Package org.apache.mahout.classifier.df.data

Examples of org.apache.mahout.classifier.df.data.Dataset

111
112
113
114
115
116
117
118
119
120
    String descriptor = DescriptorUtils.generateDescriptor(description);

    Path fPath = validateOutput(filePath);

    log.info("generating the dataset...");
    Dataset dataset = generateDataset(descriptor, dataPath, regression);

    log.info("storing the dataset description");
    DFUtils.storeWritable(new Configuration(), fPath, dataset);
  }
View Full Code Here
75
76
77
78
79
80
81
82
   */
  public static String toString(String forestPath, String datasetPath, String[] attrNames)
    throws Exception {
    Configuration conf = new Configuration();
    DecisionForest forest = DecisionForest.load(conf, new Path(forestPath));
    Dataset dataset = Dataset.load(conf, new Path(datasetPath));
    return toString(forest, dataset, attrNames);
  }
View Full Code Here
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
173
174
175
176
177
178
179
180
181
182
183
184
      partPaths[p] = new Path(partsPath, String.format(Locale.ENGLISH, "part.%03d", p));
      files[p] = pfs.create(partPaths[p]);
    }
   
    Path datasetPath = new Path(datasetStr);
    Dataset dataset = Dataset.load(conf, datasetPath);
   
    // currents[label] = next partition file where to place the tuple
    int[] currents = new int[dataset.nblabels()];
   
    // currents is initialized randomly in the range [0, numpartitions[
    Random random = RandomUtils.getRandom();
    for (int c = 0; c < currents.length; c++) {
      currents[c] = random.nextInt(numPartitions);
    }
   
    // foreach tuple of the data
    Path dataPath = new Path(dataStr);
    FileSystem ifs = dataPath.getFileSystem(conf);
    FSDataInputStream input = ifs.open(dataPath);
    Scanner scanner = new Scanner(input);
    DataConverter converter = new DataConverter(dataset);
    int nbInstances = dataset.nbInstances();
   
    int id = 0;
    while (scanner.hasNextLine()) {
      if (id % 1000 == 0) {
        log.info("progress : {} / {}", id, nbInstances);
      }
     
      String line = scanner.nextLine();
      if (line.isEmpty()) {
        continue; // skip empty lines
      }
     
      // write the tuple in files[tuple.label]
      Instance instance = converter.convert(line);
      int label = (int) dataset.getLabel(instance);
      files[currents[label]].writeBytes(line);
      files[currents[label]].writeChar('\n');
     
      // update currents
      currents[label]++;
View Full Code Here
181
182
183
184
185
186
187
188
189
190
191
      return -1;
    }
   
    // load the data
    FileSystem fs = dataPath.getFileSystem(new Configuration());
    Dataset dataset = Dataset.load(getConf(), datasetPath);
    Data data = DataLoader.loadData(dataset, fs, dataPath);
   
    // take m to be the first integer less than log2(M) + 1, where M is the
    // number of inputs
    int m = (int) Math.floor(Maths.log(2, data.getDataset().nbAttributes()) + 1);
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
    super.setUp();
   
    rng = RandomUtils.getRandom();
   
    // Dataset
    Dataset dataset = DataLoader.generateDataset("C N N C L", false, TRAIN_DATA);
   
    // Training data
    data = DataLoader.loadData(dataset, TRAIN_DATA);
   
    // Test data
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
    classifier.run();

    if (analyze) {
      double[][] results = classifier.getResults();
      if (results != null) {
        Dataset dataset = Dataset.load(getConf(), datasetPath);
        if (dataset.isNumerical(dataset.getLabelId())) {
          RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer();
          regressionAnalyzer.setInstances(results);
          log.info("{}", regressionAnalyzer);
        } else {
          ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown");
          for (double[] res : results) {
            analyzer.addInstance(dataset.getLabelString(res[0]),
              new ClassifierResult(dataset.getLabelString(res[1]), 1.0));
          }
          log.info("{}", analyzer);
        }
      }
    }
View Full Code Here
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
      log.error("No Decision Forest found!");
      return;
    }

    // load the dataset
    Dataset dataset = Dataset.load(getConf(), datasetPath);
    DataConverter converter = new DataConverter(dataset);

    log.info("Sequential classification...");
    long time = System.currentTimeMillis();

    Random rng = RandomUtils.getRandom();

    List<double[]> resList = new ArrayList<double[]>();
    if (dataFS.getFileStatus(dataPath).isDir()) {
      //the input is a directory of files
      testDirectory(outputPath, converter, forest, dataset, resList, rng);
    }  else {
      // the input is one single file
      testFile(dataPath, outputPath, converter, forest, dataset, resList, rng);
    }

    time = System.currentTimeMillis() - time;
    log.info("Classification Time: {}", DFUtils.elapsedTime(time));

    if (analyze) {
      if (dataset.isNumerical(dataset.getLabelId())) {
        RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer();
        double[][] results = new double[resList.size()][2];
        regressionAnalyzer.setInstances(resList.toArray(results));
        log.info("{}", regressionAnalyzer);
      } else {
        ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown");
        for (double[] r : resList) {
          analyzer.addInstance(dataset.getLabelString(r[0]),
            new ClassifierResult(dataset.getLabelString(r[1]), 1.0));
        }
        log.info("{}", analyzer);
      }
    }
  }
View Full Code Here
111
112
113
114
115
116
117
118
119
120
121
    // prepare the data
    String descriptor = Utils.randomDescriptor(rng, NUM_ATTRIBUTES);
    double[][] source = Utils.randomDoubles(rng, descriptor, false, NUM_INSTANCES);
    String[] sData = Utils.double2String(source);
    Dataset dataset = DataLoader.generateDataset(descriptor, false, sData);
    String[][] splits = Utils.splitData(sData, NUM_MAPPERS);

    MockTreeBuilder treeBuilder = new MockTreeBuilder();

    LongWritable key = new LongWritable();
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
    super.setUp();
   
    rng = RandomUtils.getRandom(1);
   
    // Dataset
    Dataset dataset = DataLoader
        .generateDataset("C N N C L", false, TRAIN_DATA);
   
    // Training data
    data = DataLoader.loadData(dataset, TRAIN_DATA);
   
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
    rng = RandomUtils.getRandom();
  }

  private static Data[] generateTrainingDataA() throws DescriptorException {
    // Dataset
    Dataset dataset = DataLoader.generateDataset("C N N C L", false, TRAIN_DATA);
   
    // Training data
    Data data = DataLoader.loadData(dataset, TRAIN_DATA);
    @SuppressWarnings("unchecked")
    List<Instance>[] instances = new List[3];
View Full Code Here
TOP

Related Classes of org.apache.mahout.classifier.df.data.Dataset

  • org.apache.hadoop.fs.FileSystem
  • org.apache.hadoop.fs.FSDataInputStream
  • org.apache.mahout.classifier.df.BreimanExample
  • org.apache.mahout.classifier.df.builder.InfiniteRecursionTest
  • org.apache.mahout.classifier.df.DecisionForestTest
  • org.apache.mahout.classifier.df.mapreduce.partial.Step1MapperTest
  • org.apache.mahout.classifier.df.mapreduce.TestForest
  • org.apache.mahout.classifier.df.split.DefaultIgSplitTest
  • org.apache.mahout.classifier.df.split.OptIgSplit
  • org.apache.mahout.classifier.df.split.RegressionSplitTest
    • 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.