Package quickml.supervised.classifier.decisionTree.scorers

Examples of quickml.supervised.classifier.decisionTree.scorers.SplitDiffScorer

31
32
33
34
35
36
37
38
        parametersToOptimize.put(IGNORE_ATTR_PROB, new FixedOrderRecommender(0.5, 0.0, 0.1, 0.2, 0.4, 0.7, 0.8, 0.9, 0.95, 0.98, 0.99));
        parametersToOptimize.put(MAX_DEPTH, new FixedOrderRecommender(Integer.MAX_VALUE, 2, 3, 4, 5, 6, 7, 9));
        parametersToOptimize.put(MIN_SCORE, new FixedOrderRecommender(0.00000000000001, Double.MIN_VALUE, 0.0, 0.000001, 0.0001, 0.001, 0.01, 0.1));
        parametersToOptimize.put(MIN_CAT_ATTR_OCC, new FixedOrderRecommender(5, 0, 1, 64, 1024, 4098));
        parametersToOptimize.put(MIN_LEAF_INSTANCES, new FixedOrderRecommender(0, 10, 100, 1000, 10000, 100000));
        parametersToOptimize.put(SCORER, new FixedOrderRecommender(new MSEScorer(MSEScorer.CrossValidationCorrection.FALSE), new MSEScorer(MSEScorer.CrossValidationCorrection.TRUE), new SplitDiffScorer(), new InformationGainScorer(), new GiniImpurityScorer()));
        return parametersToOptimize;
    }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
    }

    private static void testWithInstances(String dsName, final List<Instance<AttributesMap>> instances) {
        StationaryCrossValidator crossValidator = new StationaryCrossValidator(new ClassifierLogCVLossFunction());

        for (final Scorer scorer : Lists.newArrayList(new SplitDiffScorer(), new MSEScorer(MSEScorer.CrossValidationCorrection.FALSE), new MSEScorer(MSEScorer.CrossValidationCorrection.TRUE))) {
            final TreeBuilder singleTreeBuilder = new TreeBuilder(scorer).binaryClassification(true);
            System.out.println(dsName+", single-tree, "+scorer+", "+crossValidator.getCrossValidatedLoss(singleTreeBuilder, instances));

            TreeBuilder forestTreeBuilder = new TreeBuilder(scorer).ignoreAttributeAtNodeProbability(0.5).binaryClassification(true);
            RandomForestBuilder randomForestBuilder = new RandomForestBuilder(forestTreeBuilder).numTrees(100).executorThreadCount(8);
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
    }

    @Test
    public void simpleBmiTest() throws Exception {
        final List<Instance<AttributesMap>> instances = TreeBuilderTestUtils.getIntegerInstances(10000);
        final PredictiveModelBuilder tb = new TreeBuilder(new SplitDiffScorer());
        final TemporallyReweightedClassifierBuilder builder = new TemporallyReweightedClassifierBuilder(tb, new MapDateTimeExtractor());
        final long startTime = System.currentTimeMillis();
        final TemporallyReweightedClassifier model = builder.buildPredictiveModel(instances);

        TreeBuilderTestUtils.serializeDeserialize(model);
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
*/
public class RandomForestBuilderTest {
    @Test
    public void simpleBmiTest() throws Exception {
        final List<Instance<AttributesMap>> instances = TreeBuilderTestUtils.getInstances(10000);
        final TreeBuilder tb = new TreeBuilder(new SplitDiffScorer());
        final RandomForestBuilder rfb = new RandomForestBuilder(tb);
        final long startTime = System.currentTimeMillis();
        final RandomForest randomForest = rfb.buildPredictiveModel(instances);

        TreeBuilderTestUtils.serializeDeserialize(randomForest);
View Full Code Here
70
71
72
73
74
75
76
77
78
        Assert.assertEquals(treeSize, newRandomForest.trees.size(), "Expected same trees");
        Assert.assertEquals(firstTreeNodeSize, newRandomForest.trees.get(0).node.size(), "Expected same nodes");
    }

    private PredictiveModelWithDataBuilder<AttributesMap ,RandomForest> getWrappedUpdatablePredictiveModelBuilder() {
        final TreeBuilder tb = new TreeBuilder(new SplitDiffScorer()).updatable(true);
        final RandomForestBuilder urfb = new RandomForestBuilder(tb);
        return new PredictiveModelWithDataBuilder<>(urfb);
    }
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
    }

    @Test
    public void twoDeterministicRandomForestsAreEqual() throws IOException, ClassNotFoundException {
        final List<Instance<AttributesMap>> instancesTrain = TreeBuilderTestUtils.getInstances(10000);
        final RandomForestBuilder urfb = new RandomForestBuilder(new TreeBuilder(new SplitDiffScorer()).updatable(true));
        MapUtils.random.setSeed(1l);
        final RandomForest randomForest1 = urfb.executorThreadCount(1).buildPredictiveModel(instancesTrain);
        MapUtils.random.setSeed(1l);
        final RandomForest randomForest2 = urfb.executorThreadCount(1).buildPredictiveModel(instancesTrain);
View Full Code Here
23
24
25
26
27
28
29
30
31
32
33
public class TreeBuilderTest {
  @Test
  public void simpleBmiTest() throws Exception {
        final List<Instance<AttributesMap>> instances = TreeBuilderTestUtils.getInstances(10000);
    final TreeBuilder tb = new TreeBuilder(new SplitDiffScorer());
    final long startTime = System.currentTimeMillis();
        final Tree tree = tb.buildPredictiveModel(instances);
    final Node node = tree.node;

        TreeBuilderTestUtils.serializeDeserialize(node);
View Full Code Here
51
52
53
54
55
56
57
58
59
60
            attributes.put("height", height);
      final Instance<AttributesMap> instance = new InstanceImpl<>(attributes, TreeBuilderTestUtils.bmiHealthy(weight, height));
      instances.add(instance);
    }
    {
      final TreeBuilder tb = new TreeBuilder(new SplitDiffScorer());
      final Tree tree = tb.buildPredictiveModel(instances);
      System.out.println("SplitDiffScorer node size: " + tree.node.size());
    }
  }
View Full Code Here
136
137
138
139
140
141
142
143
        final Tree newTree = wb.buildPredictiveModel(newInstances);
        Assert.assertFalse(tree == newTree, "Expect new tree to be built");
    }

    private PredictiveModelWithDataBuilder<AttributesMap ,Tree> getWrappedUpdatablePredictiveModelBuilder() {
        final TreeBuilder tb = new TreeBuilder(new SplitDiffScorer());
        return new PredictiveModelWithDataBuilder<>(tb);
    }
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
156
157
    @Test
    public void twoDeterministicDecisionTreesAreEqual() throws IOException, ClassNotFoundException {

        final List<Instance<AttributesMap>> instancesTrain = TreeBuilderTestUtils.getInstances(10000);
        MapUtils.random.setSeed(1l);
        final Tree tree1 = (new TreeBuilder(new SplitDiffScorer())).buildPredictiveModel(instancesTrain);
        MapUtils.random.setSeed(1l);
        final Tree tree2 = (new TreeBuilder(new SplitDiffScorer())).buildPredictiveModel(instancesTrain);

        TreeBuilderTestUtils.serializeDeserialize(tree1.node);
        TreeBuilderTestUtils.serializeDeserialize(tree2.node);
        Assert.assertTrue(tree1.node.size() == tree2.node.size(), "Deterministic Decision Trees must have same number of nodes");
View Full Code Here
TOP

Related Classes of quickml.supervised.classifier.decisionTree.scorers.SplitDiffScorer

  • quickml.Benchmarks
  • quickml.supervised.classifier.decisionTree.TreeBuilderFactory
  • quickml.supervised.classifier.decisionTree.TreeBuilderTest
  • quickml.supervised.classifier.downsampling.DownsamplingClassifierBuilderTest
  • quickml.supervised.classifier.randomForest.RandomForestBuilderTest
  • quickml.supervised.classifier.splitOnAttribute.SplitOnAttributeClassifierBuilderTest
  • quickml.supervised.classifier.temporallyWeightClassifier.TemporallyReweightedClassifierBuilderTest
    • 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.