Package org.apache.mahout.df.data

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

131
132
133
134
135
136
137
138
139
140
141
    // 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);
   
    JobConf job = new JobConf();
    job.setNumMapTasks(numMaps);
    FileInputFormat.setInputPaths(job, dataPath);
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
    // 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
74
75
76
77
78
79
80
81
82
83
84
    // 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
79
80
81
82
83
84
85
86
87
88
89
    // 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);

    MockTreeBuilder treeBuilder = new MockTreeBuilder();

    LongWritable key = new LongWritable();
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
    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
72
73
74
75
76
77
78
79
80
81
82
    // 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
78
79
80
81
82
83
84
85
86
87
88
    // 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);

    MockTreeBuilder treeBuilder = new MockTreeBuilder();

    LongWritable key = new LongWritable();
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
181
182
    }

    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
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
45
46
47
48
49
50
51
52
53
54
    TreeBuilder builder = new DefaultTreeBuilder();

    String[] source = Utils.double2String(dData);
    String descriptor = "N N N N N N N N L";
    Dataset dataset = DataLoader.generateDataset(descriptor, source);
    Data data = DataLoader.loadData(dataset, source);

    builder.build(rng, data);
  }
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.