Package org.apache.mahout.df.data

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

71
72
73
74
75
76
77
78
79
80
81
    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
154
155
156
157
158
159
160
161
162
163
164
    // write the data to a file
    Path dataPath = Utils.writeDataToTestFile(sData);

    // prepare a data converter
    Dataset dataset = DataLoader.generateDataset(descriptor, sData);
    DataConverter converter = new DataConverter(dataset);

    Job job = new Job();
    job.setInputFormatClass(TextInputFormat.class);
    FileInputFormat.setInputPaths(job, dataPath);
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
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
226
227
228
229
230
231
232
233
234
235
236
      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
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
      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);
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    }

    // 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);

    Configuration conf = new Configuration();
    Step0JobTest.setMaxSplitSize(conf, dataPath, NUM_MAPS);
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
    // write the data to a file
    Path dataPath = Utils.writeDataToTestFile(sData);

    // prepare a data converter
    Dataset dataset = DataLoader.generateDataset(descriptor, sData);
    DataConverter converter = new DataConverter(dataset);

    Job job = new Job();
    job.setInputFormatClass(TextInputFormat.class);
    FileInputFormat.setInputPaths(job, dataPath);
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
    // prepare the data
    String descriptor = Utils.randomDescriptor(rng, nbAttributes);
    double[][] source = Utils.randomDoubles(rng, descriptor, nbInstances);
    String[] sData = Utils.double2String(source);
    Dataset dataset = DataLoader.generateDataset(descriptor, sData);
    String[][] splits = Utils.splitData(sData, nbMappers);

    // prepare first step output
    TreeID[] keys = new TreeID[nbTrees];
    Node[] trees = new Node[nbTrees];
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.