Examples with FeatureDistribution org.kie.kogito.explainability.model.FeatureDistribution used on opensource projects

Example 1 with FeatureDistribution

use of org.kie.kogito.explainability.model.FeatureDistribution in project kogito-apps by kiegroup.

the class CounterfactualEntityFactoryTest method testDurationFactory.

@Test
void testDurationFactory() {
    final Duration value = Duration.ofDays(1);
    Feature feature = FeatureFactory.newDurationFeature("duration-feature", value);
    CounterfactualEntity counterfactualEntity = CounterfactualEntityFactory.from(feature);
    assertTrue(counterfactualEntity instanceof FixedDurationEntity);
    assertEquals(Type.DURATION, counterfactualEntity.asFeature().getType());
    FeatureDomain domain = DurationFeatureDomain.create(0, 60, ChronoUnit.SECONDS);
    feature = FeatureFactory.newDurationFeature("duration-feature", value, domain);
    counterfactualEntity = CounterfactualEntityFactory.from(feature);
    assertTrue(counterfactualEntity instanceof DurationEntity);
    assertEquals(Type.DURATION, counterfactualEntity.asFeature().getType());
    assertFalse(counterfactualEntity.isConstrained());
    CounterfactualEntity entity = DurationEntity.from(feature, Duration.ZERO, Duration.ofDays(2));
    assertEquals(0, entity.distance());
    assertTrue(((DurationEntity) entity).getValueRange().contains(1e5));
    assertFalse(((DurationEntity) entity).getValueRange().contains(2e5));
    assertFalse(entity.isConstrained());
    entity = DurationEntity.from(feature, Duration.ZERO, Duration.ofDays(2), false);
    assertEquals(0, entity.distance());
    assertFalse(entity.isConstrained());
    FeatureDistribution distribution = new NumericFeatureDistribution(feature, new Random().doubles(10).toArray());
    entity = DurationEntity.from(feature, Duration.ZERO, Duration.ofDays(2), distribution);
    assertEquals(0, entity.distance());
    assertFalse(entity.isConstrained());
}

Example 2 with FeatureDistribution

use of org.kie.kogito.explainability.model.FeatureDistribution in project kogito-apps by kiegroup.

the class CounterfactualExplainerTest method testCounterfactualConstrainedMatchScaled.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2 })
void testCounterfactualConstrainedMatchScaled(int seed) throws ExecutionException, InterruptedException, TimeoutException {
    Random random = new Random();
    random.setSeed(seed);
    final List<Output> goal = List.of(new Output("inside", Type.BOOLEAN, new Value(true), 0.0d));
    List<Feature> features = new LinkedList<>();
    List<FeatureDistribution> featureDistributions = new LinkedList<>();
    final Feature fnum1 = FeatureFactory.newNumericalFeature("f-num1", 100.0);
    features.add(fnum1);
    featureDistributions.add(new NumericFeatureDistribution(fnum1, (new NormalDistribution(500, 1.1)).sample(1000)));
    final Feature fnum2 = FeatureFactory.newNumericalFeature("f-num2", 100.0, NumericalFeatureDomain.create(0.0, 1000.0));
    features.add(fnum2);
    featureDistributions.add(new NumericFeatureDistribution(fnum2, (new NormalDistribution(430.0, 1.7)).sample(1000)));
    final Feature fnum3 = FeatureFactory.newNumericalFeature("f-num3", 100.0, NumericalFeatureDomain.create(0.0, 1000.0));
    features.add(fnum3);
    featureDistributions.add(new NumericFeatureDistribution(fnum3, (new NormalDistribution(470.0, 2.9)).sample(1000)));
    final Feature fnum4 = FeatureFactory.newNumericalFeature("f-num4", 100.0);
    features.add(fnum4);
    featureDistributions.add(new NumericFeatureDistribution(fnum4, (new NormalDistribution(2390.0, 0.3)).sample(1000)));
    final double center = 500.0;
    final double epsilon = 10.0;
    final CounterfactualResult result = runCounterfactualSearch((long) seed, goal, features, TestUtils.getSumThresholdModel(center, epsilon), DEFAULT_GOAL_THRESHOLD);
    final List<CounterfactualEntity> counterfactualEntities = result.getEntities();
    double totalSum = 0;
    for (CounterfactualEntity entity : counterfactualEntities) {
        totalSum += entity.asFeature().getValue().asNumber();
        logger.debug("Entity: {}", entity);
    }
    assertFalse(counterfactualEntities.get(0).isChanged());
    assertFalse(counterfactualEntities.get(3).isChanged());
    assertTrue(totalSum <= center + epsilon);
    assertTrue(totalSum >= center - epsilon);
    assertTrue(result.isValid());
}

Example 3 with FeatureDistribution

use of org.kie.kogito.explainability.model.FeatureDistribution in project kogito-apps by kiegroup.

the class DataUtils method boostrapFeatureDistributions.

/**
 * Generate feature distributions from an existing (evantually small) {@link DataDistribution} for each {@link Feature}.
 * Each feature intervals (min, max) and density information (mean, stdDev) are generated using bootstrap, then
 * data points are sampled from a normal distribution (see {@link #generateData(double, double, int, Random)}).
 *
 * @param dataDistribution data distribution to take feature values from
 * @param perturbationContext perturbation context
 * @param featureDistributionSize desired size of generated feature distributions
 * @param draws number of times sampling from feature values is performed
 * @param sampleSize size of each sample draw
 * @param numericFeatureZonesMap high feature score zones
 * @return a map feature name -> generated feature distribution
 */
public static Map<String, FeatureDistribution> boostrapFeatureDistributions(DataDistribution dataDistribution, PerturbationContext perturbationContext, int featureDistributionSize, int draws, int sampleSize, Map<String, HighScoreNumericFeatureZones> numericFeatureZonesMap) {
    Map<String, FeatureDistribution> featureDistributions = new HashMap<>();
    for (FeatureDistribution featureDistribution : dataDistribution.asFeatureDistributions()) {
        Feature feature = featureDistribution.getFeature();
        if (Type.NUMBER.equals(feature.getType())) {
            List<Value> values = featureDistribution.getAllSamples();
            double[] means = new double[draws];
            double[] stdDevs = new double[draws];
            double[] mins = new double[draws];
            double[] maxs = new double[draws];
            for (int i = 0; i < draws; i++) {
                List<Value> sampledValues = DataUtils.sampleWithReplacement(values, sampleSize, perturbationContext.getRandom());
                double[] data = sampledValues.stream().mapToDouble(Value::asNumber).toArray();
                double mean = DataUtils.getMean(data);
                double stdDev = Math.pow(DataUtils.getStdDev(data, mean), 2);
                double min = Arrays.stream(data).min().orElse(Double.MIN_VALUE);
                double max = Arrays.stream(data).max().orElse(Double.MAX_VALUE);
                means[i] = mean;
                stdDevs[i] = stdDev;
                mins[i] = min;
                maxs[i] = max;
            }
            double finalMean = DataUtils.getMean(means);
            double finalStdDev = Math.sqrt(DataUtils.getMean(stdDevs));
            double finalMin = DataUtils.getMean(mins);
            double finalMax = DataUtils.getMean(maxs);
            double[] doubles = DataUtils.generateData(finalMean, finalStdDev, featureDistributionSize, perturbationContext.getRandom());
            double[] boundedData = Arrays.stream(doubles).map(d -> Math.min(Math.max(d, finalMin), finalMax)).toArray();
            HighScoreNumericFeatureZones highScoreNumericFeatureZones = numericFeatureZonesMap.get(feature.getName());
            double[] finaldata;
            if (highScoreNumericFeatureZones != null) {
                double[] filteredData = DoubleStream.of(boundedData).filter(highScoreNumericFeatureZones::test).toArray();
                // only use the filtered data if it's not discarding more than 50% of the points
                if (filteredData.length > featureDistributionSize / 2) {
                    finaldata = filteredData;
                } else {
                    finaldata = boundedData;
                }
            } else {
                finaldata = boundedData;
            }
            NumericFeatureDistribution numericFeatureDistribution = new NumericFeatureDistribution(feature, finaldata);
            featureDistributions.put(feature.getName(), numericFeatureDistribution);
        }
    }
    return featureDistributions;
}

Example 4 with FeatureDistribution

use of org.kie.kogito.explainability.model.FeatureDistribution in project kogito-apps by kiegroup.

the class HighScoreNumericFeatureZonesProviderTest method testEmptyData.

@Test
void testEmptyData() {
    List<Feature> features = new ArrayList<>();
    PredictionProvider predictionProvider = TestUtils.getSumThresholdModel(0.1, 0.1);
    List<FeatureDistribution> featureDistributions = new ArrayList<>();
    DataDistribution dataDistribution = new IndependentFeaturesDataDistribution(featureDistributions);
    Map<String, HighScoreNumericFeatureZones> highScoreFeatureZones = HighScoreNumericFeatureZonesProvider.getHighScoreFeatureZones(dataDistribution, predictionProvider, features, 10);
    assertThat(highScoreFeatureZones).isNotNull();
    assertThat(highScoreFeatureZones.size()).isZero();
}

Example 5 with FeatureDistribution

use of org.kie.kogito.explainability.model.FeatureDistribution in project kogito-apps by kiegroup.

the class LimeExplainerTest method testWithDataDistribution.

@Test
void testWithDataDistribution() throws InterruptedException, ExecutionException, TimeoutException {
    Random random = new Random();
    PerturbationContext perturbationContext = new PerturbationContext(4L, random, 1);
    List<FeatureDistribution> featureDistributions = new ArrayList<>();
    int nf = 4;
    List<Feature> features = new ArrayList<>();
    for (int i = 0; i < nf; i++) {
        Feature numericalFeature = FeatureFactory.newNumericalFeature("f-" + i, Double.NaN);
        features.add(numericalFeature);
        List<Value> values = new ArrayList<>();
        for (int r = 0; r < 4; r++) {
            values.add(Type.NUMBER.randomValue(perturbationContext));
        }
        featureDistributions.add(new GenericFeatureDistribution(numericalFeature, values));
    }
    DataDistribution dataDistribution = new IndependentFeaturesDataDistribution(featureDistributions);
    LimeConfig limeConfig = new LimeConfig().withDataDistribution(dataDistribution).withPerturbationContext(perturbationContext).withSamples(10);
    LimeExplainer limeExplainer = new LimeExplainer(limeConfig);
    PredictionInput input = new PredictionInput(features);
    PredictionProvider model = TestUtils.getSumThresholdModel(random.nextDouble(), random.nextDouble());
    PredictionOutput output = model.predictAsync(List.of(input)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit()).get(0);
    Prediction prediction = new SimplePrediction(input, output);
    Map<String, Saliency> saliencyMap = limeExplainer.explainAsync(prediction, model).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    assertThat(saliencyMap).isNotNull();
    String decisionName = "inside";
    Saliency saliency = saliencyMap.get(decisionName);
    assertThat(saliency).isNotNull();
}