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

Example 76 with Output

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

the class TestUtils method getEvenFeatureModel.

public static PredictionProvider getEvenFeatureModel(int featureIndex) {
    return inputs -> supplyAsync(() -> {
        List<PredictionOutput> predictionOutputs = new LinkedList<>();
        for (PredictionInput predictionInput : inputs) {
            List<Feature> features = predictionInput.getFeatures();
            Feature feature = features.get(featureIndex);
            double v = feature.getValue().asNumber();
            PredictionOutput predictionOutput = new PredictionOutput(List.of(new Output("feature-" + featureIndex, Type.BOOLEAN, new Value(v % 2 == 0), 1d)));
            predictionOutputs.add(predictionOutput);
        }
        return predictionOutputs;
    });
}

Example 77 with Output

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

the class PartialDependencePlotExplainerTest method getMetadata.

private PredictionProviderMetadata getMetadata(Random random) {
    return new PredictionProviderMetadata() {

        @Override
        public DataDistribution getDataDistribution() {
            return DataUtils.generateRandomDataDistribution(3, 100, random);
        }

        @Override
        public PredictionInput getInputShape() {
            List<Feature> features = new LinkedList<>();
            features.add(FeatureFactory.newNumericalFeature("f0", 0));
            features.add(FeatureFactory.newNumericalFeature("f1", 0));
            features.add(FeatureFactory.newNumericalFeature("f2", 0));
            return new PredictionInput(features);
        }

        @Override
        public PredictionOutput getOutputShape() {
            List<Output> outputs = new LinkedList<>();
            outputs.add(new Output("sum-but0", Type.BOOLEAN, new Value(false), 0d));
            return new PredictionOutput(outputs);
        }
    };
}

Example 78 with Output

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

the class CounterfactualExplainerTest method testConsumers.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2 })
void testConsumers(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), 0.0));
    List<Feature> features = new LinkedList<>();
    features.add(FeatureFactory.newNumericalFeature("f-num1", 100.0, NumericalFeatureDomain.create(0.0, 1000.0)));
    features.add(FeatureFactory.newNumericalFeature("f-num2", 100.0, NumericalFeatureDomain.create(0.0, 1000.0)));
    features.add(FeatureFactory.newNumericalFeature("f-num3", 100.0, NumericalFeatureDomain.create(0.0, 1000.0)));
    features.add(FeatureFactory.newNumericalFeature("f-num4", 100.0, NumericalFeatureDomain.create(0.0, 1000.0)));
    final TerminationConfig terminationConfig = new TerminationConfig().withScoreCalculationCountLimit(10_000L);
    // for the purpose of this test, only a few steps are necessary
    final SolverConfig solverConfig = SolverConfigBuilder.builder().withTerminationConfig(terminationConfig).build();
    solverConfig.setRandomSeed((long) seed);
    solverConfig.setEnvironmentMode(EnvironmentMode.REPRODUCIBLE);
    @SuppressWarnings("unchecked") final Consumer<CounterfactualResult> assertIntermediateCounterfactualNotNull = mock(Consumer.class);
    final CounterfactualConfig counterfactualConfig = new CounterfactualConfig().withSolverConfig(solverConfig).withGoalThreshold(0.01);
    final CounterfactualExplainer counterfactualExplainer = new CounterfactualExplainer(counterfactualConfig);
    PredictionInput input = new PredictionInput(features);
    final double center = 500.0;
    final double epsilon = 10.0;
    final PredictionProvider model = TestUtils.getSumThresholdModel(center, epsilon);
    PredictionOutput output = new PredictionOutput(goal);
    Prediction prediction = new CounterfactualPrediction(input, output, null, UUID.randomUUID(), null);
    final CounterfactualResult counterfactualResult = counterfactualExplainer.explainAsync(prediction, model, assertIntermediateCounterfactualNotNull).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    for (CounterfactualEntity entity : counterfactualResult.getEntities()) {
        logger.debug("Entity: {}", entity);
    }
    logger.debug("Outputs: {}", counterfactualResult.getOutput().get(0).getOutputs());
    // At least one intermediate result is generated
    verify(assertIntermediateCounterfactualNotNull, atLeast(1)).accept(any());
}

Example 79 with Output

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

the class CounterfactualExplainerTest method testNonEmptyInput.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2 })
void testNonEmptyInput(int seed) throws ExecutionException, InterruptedException, TimeoutException {
    Random random = new Random();
    random.setSeed(seed);
    final List<Output> goal = List.of(new Output("class", Type.NUMBER, new Value(10.0), 0.0d));
    List<Feature> features = new LinkedList<>();
    for (int i = 0; i < 4; i++) {
        features.add(FeatureFactory.newNumericalFeature("f-" + i, random.nextDouble(), NumericalFeatureDomain.create(0.0, 1000.0)));
    }
    final TerminationConfig terminationConfig = new TerminationConfig().withScoreCalculationCountLimit(10L);
    // for the purpose of this test, only a few steps are necessary
    final SolverConfig solverConfig = SolverConfigBuilder.builder().withTerminationConfig(terminationConfig).build();
    solverConfig.setRandomSeed((long) seed);
    solverConfig.setEnvironmentMode(EnvironmentMode.REPRODUCIBLE);
    final CounterfactualConfig counterfactualConfig = new CounterfactualConfig().withSolverConfig(solverConfig);
    final CounterfactualExplainer counterfactualExplainer = new CounterfactualExplainer(counterfactualConfig);
    PredictionProvider model = TestUtils.getSumSkipModel(0);
    PredictionInput input = new PredictionInput(features);
    PredictionOutput output = new PredictionOutput(goal);
    Prediction prediction = new CounterfactualPrediction(input, output, null, UUID.randomUUID(), null);
    final CounterfactualResult counterfactualResult = counterfactualExplainer.explainAsync(prediction, model).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    for (CounterfactualEntity entity : counterfactualResult.getEntities()) {
        logger.debug("Entity: {}", entity);
    }
    logger.debug("Outputs: {}", counterfactualResult.getOutput().get(0).getOutputs());
    assertNotNull(counterfactualResult);
    assertNotNull(counterfactualResult.getEntities());
}

Example 80 with Output

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

the class CounterfactualExplainerTest method testCounterfactualCategoricalStrictFail.

/**
 * Search for a counterfactual using categorical features with the Symbolic arithmetic model.
 * The outcome match is strict (goal threshold of zero).
 * The CF should be invalid with this number of iterations.
 *
 * @param seed
 * @throws ExecutionException
 * @throws InterruptedException
 * @throws TimeoutException
 */
@ParameterizedTest
@ValueSource(ints = { 0, 1, 2 })
void testCounterfactualCategoricalStrictFail(int seed) throws ExecutionException, InterruptedException, TimeoutException {
    Random random = new Random();
    random.setSeed(seed);
    final List<Output> goal = List.of(new Output("result", Type.NUMBER, new Value(25.0), 0.0d));
    List<Feature> features = new LinkedList<>();
    features.add(FeatureFactory.newNumericalFeature("x-1", 5.0, NumericalFeatureDomain.create(0.0, 100.0)));
    features.add(FeatureFactory.newNumericalFeature("x-2", 40.0, NumericalFeatureDomain.create(0.0, 100.0)));
    features.add(FeatureFactory.newCategoricalFeature("operand", "*", CategoricalFeatureDomain.create("+", "-", "/", "*")));
    final CounterfactualResult result = runCounterfactualSearch((long) seed, goal, features, TestUtils.getSymbolicArithmeticModel(), 0.0);
    final List<CounterfactualEntity> counterfactualEntities = result.getEntities();
    Stream<Feature> counterfactualFeatures = counterfactualEntities.stream().map(CounterfactualEntity::asFeature);
    String operand = counterfactualFeatures.filter(feature -> feature.getName().equals("operand")).findFirst().get().getValue().asString();
    List<Feature> numericalFeatures = counterfactualEntities.stream().map(CounterfactualEntity::asFeature).filter(feature -> !feature.getName().equals("operand")).collect(Collectors.toList());
    double opResult = 0.0;
    for (Feature feature : numericalFeatures) {
        switch(operand) {
            case "+":
                opResult += feature.getValue().asNumber();
                break;
            case "-":
                opResult -= feature.getValue().asNumber();
                break;
            case "*":
                opResult *= feature.getValue().asNumber();
                break;
            case "/":
                opResult /= feature.getValue().asNumber();
                break;
        }
    }
    final double epsilon = 0.1;
    assertFalse(result.isValid());
    assertTrue(opResult <= 25.0 + epsilon);
    assertTrue(opResult >= 25.0 - epsilon);
}