Package org.apache.mahout.df.data

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

105
106
107
108
109
110
111
112
113
114
    String descriptor = DescriptorUtils.generateDescriptor(description);
   
    Path fPath = validateOutput(filePath);
   
    log.info("generating the dataset...");
    Dataset dataset = generateDataset(descriptor, dataPath);
   
    log.info("storing the dataset description");
    storeWritable(new Configuration(), fPath, dataset);
  }
View Full Code Here
179
180
181
182
183
184
185
186
   
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
      Configuration conf = context.getConfiguration();
     
      Dataset dataset = Builder.loadDataset(conf);
      setup(dataset);
    }
View Full Code Here
212
213
214
215
216
217
218
219
    private int nblabels;
   
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
      Configuration conf = context.getConfiguration();
      Dataset dataset = Builder.loadDataset(conf);
      setup(dataset.nblabels());
    }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
    if ((files == null) || (files.length < 2)) {
      throw new IllegalArgumentException("missing paths from the DistributedCache");
    }
   
    Path datasetPath = new Path(files[0].getPath());
    Dataset dataset = Dataset.load(conf, datasetPath);
   
    int numMaps = Builder.getNumMaps(conf);
    int p = conf.getInt("mapred.task.partition", -1);
   
    // total number of trees in the forest
View Full Code Here
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
      partPaths[p] = new Path(partsPath, String.format("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(String.format("progress : %d / %d", id, nbInstances));
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
   
    if ((files == null) || (files.length < 2)) {
      throw new IllegalArgumentException("missing paths from the DistributedCache");
    }
   
    Dataset dataset;
    try {
      Path datasetPath = new Path(files[0].getPath());
      dataset = Dataset.load(job, datasetPath);
    } catch (IOException e) {
      throw new IllegalStateException("Exception while loading the dataset : ", e);
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
    int label = Utils.findLabel(descriptor);

    // all the vectors have the same label (0)
    double[][] temp = Utils.randomDoublesWithSameLabel(rng, descriptor, 100, 0);
    String[] sData = Utils.double2String(temp);
    Dataset dataset = DataLoader.generateDataset(descriptor, sData);
    Data data = DataLoader.loadData(dataset, sData);
    DefaultIgSplit iG = new DefaultIgSplit();

    double expected = 0.0 - 1.0 * Math.log(1.0) / Math.log(2.0);
    assertEquals(expected, iG.entropy(data));
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
    }

    // store the data into a file
    String[] sData = Utils.double2String(source);
    Path dataPath = Utils.writeDataToTestFile(sData);
    Dataset dataset = DataLoader.generateDataset(descriptor, sData);
    Data data = DataLoader.loadData(dataset, sData);

    JobConf jobConf = new JobConf();
    jobConf.setNumMapTasks(numMaps);
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
 
  private DecisionForest buildForest() throws IOException {
    DefaultTreeBuilder treeBuilder = new DefaultTreeBuilder();
    treeBuilder.setM(m);
   
    Dataset dataset = Dataset.load(getConf(), datasetPath);
   
    ForestPredictions callback = isOob ? new ForestPredictions(dataset.nbInstances(), dataset.nblabels())
        : null;
   
    Builder forestBuilder;
   
    if (isPartial) {
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
 
  private DecisionForest buildForest() throws IOException, ClassNotFoundException, InterruptedException {
    DefaultTreeBuilder treeBuilder = new DefaultTreeBuilder();
    treeBuilder.setM(m);
   
    Dataset dataset = Dataset.load(getConf(), datasetPath);
   
    ForestPredictions callback = isOob ? new ForestPredictions(dataset.nbInstances(), dataset.nblabels())
        : null;
   
    Builder forestBuilder;
   
    if (isPartial) {
View Full Code Here
TOP

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

  • org.apache.hadoop.fs.FileSystem
  • org.apache.hadoop.fs.FSDataInputStream
  • org.apache.mahout.df.BreimanExample
  • org.apache.mahout.df.builder.InfiniteRecursionTest
  • org.apache.mahout.df.mapred.BuildForest
  • org.apache.mahout.df.mapred.partial.PartitionBugTest
  • org.apache.mahout.df.mapred.partial.Step0JobTest
  • org.apache.mahout.df.mapred.partial.Step1MapperTest
  • org.apache.mahout.df.mapred.partial.Step2Mapper
  • org.apache.mahout.df.mapred.partial.Step2MapperTest
    • 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.