Package org.apache.mahout.df.data

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

66
67
68
69
70
71
72
73
74
75
76
    log.info("DistributedCache.getCacheFiles(): {}", ArrayUtils.toString(files));
   
    Preconditions.checkArgument(files != null && files.length >= 2, "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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
      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();
    ResultAnalyzer analyzer = analyze ? new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown") : null;

    if (dataFS.getFileStatus(dataPath).isDir()) {
      //the input is a directory of files
      testDirectory(outputPath, converter, forest, dataset, analyzer, rng);
    }  else {
View Full Code Here
214
215
216
217
218
219
220
221
222
223
224
      if (files == null || files.length < 2) {
        throw new IOException("not enough paths in the DistributedCache");
      }

      Dataset dataset = Dataset.load(conf, new Path(files[0].getPath()));

      converter = new DataConverter(dataset);

      forest = DecisionForest.load(conf, new Path(files[1].getPath()));
      if (forest == null) {
View Full Code Here
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");
    DFUtils.storeWritable(new Configuration(), fPath, dataset);
  }
View Full Code Here
166
167
168
169
170
171
172
173
   
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
      Configuration conf = context.getConfiguration();
     
      Dataset dataset = Builder.loadDataset(conf);
      setup(dataset);
    }
View Full Code Here
198
199
200
201
202
203
204
205
    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
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.