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

Example 31 with PredictionOutput

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

the class FraudScoringDmnLimeExplainerTest method testExplanationImpactScoreWithOptimization.

@Test
void testExplanationImpactScoreWithOptimization() throws ExecutionException, InterruptedException, TimeoutException {
    PredictionProvider model = getModel();
    List<PredictionInput> samples = DmnTestUtils.randomFraudScoringInputs();
    List<PredictionOutput> predictionOutputs = model.predictAsync(samples.subList(0, 10)).get();
    List<Prediction> predictions = DataUtils.getPredictions(samples, predictionOutputs);
    long seed = 0;
    LimeConfigOptimizer limeConfigOptimizer = new LimeConfigOptimizer().withDeterministicExecution(true).forImpactScore().withSampling(false).withStepCountLimit(20);
    Random random = new Random();
    PerturbationContext perturbationContext = new PerturbationContext(seed, random, 1);
    LimeConfig initialConfig = new LimeConfig().withSamples(10).withPerturbationContext(perturbationContext);
    LimeConfig optimizedConfig = limeConfigOptimizer.optimize(initialConfig, predictions, model);
    assertThat(optimizedConfig).isNotSameAs(initialConfig);
}

Example 32 with PredictionOutput

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

the class FraudScoringDmnLimeExplainerTest method testExplanationStabilityWithOptimization.

@Test
void testExplanationStabilityWithOptimization() throws ExecutionException, InterruptedException, TimeoutException {
    PredictionProvider model = getModel();
    List<PredictionInput> samples = DmnTestUtils.randomFraudScoringInputs();
    List<PredictionOutput> predictionOutputs = model.predictAsync(samples.subList(0, 5)).get();
    List<Prediction> predictions = DataUtils.getPredictions(samples, predictionOutputs);
    long seed = 0;
    LimeConfigOptimizer limeConfigOptimizer = new LimeConfigOptimizer().withDeterministicExecution(true).withStepCountLimit(20);
    Random random = new Random();
    PerturbationContext perturbationContext = new PerturbationContext(seed, random, 1);
    LimeConfig initialConfig = new LimeConfig().withSamples(10).withPerturbationContext(perturbationContext);
    LimeConfig optimizedConfig = limeConfigOptimizer.optimize(initialConfig, predictions, model);
    assertThat(optimizedConfig).isNotSameAs(initialConfig);
    LimeExplainer limeExplainer = new LimeExplainer(optimizedConfig);
    PredictionInput testPredictionInput = getTestInput();
    List<PredictionOutput> testPredictionOutputs = model.predictAsync(List.of(testPredictionInput)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    Prediction instance = new SimplePrediction(testPredictionInput, testPredictionOutputs.get(0));
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, instance, limeExplainer, 1, 0.5, 0.5));
}

Example 33 with PredictionOutput

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

the class FraudScoringDmnLimeExplainerTest method testExplanationWeightedStabilityWithOptimization.

@Test
void testExplanationWeightedStabilityWithOptimization() throws ExecutionException, InterruptedException, TimeoutException {
    PredictionProvider model = getModel();
    List<PredictionInput> samples = DmnTestUtils.randomFraudScoringInputs();
    List<PredictionOutput> predictionOutputs = model.predictAsync(samples.subList(0, 5)).get();
    List<Prediction> predictions = DataUtils.getPredictions(samples, predictionOutputs);
    long seed = 0;
    LimeConfigOptimizer limeConfigOptimizer = new LimeConfigOptimizer().withDeterministicExecution(true).withWeightedStability(0.4, 0.6).withStepCountLimit(10);
    Random random = new Random();
    PerturbationContext perturbationContext = new PerturbationContext(seed, random, 1);
    LimeConfig initialConfig = new LimeConfig().withSamples(10).withPerturbationContext(perturbationContext);
    LimeConfig optimizedConfig = limeConfigOptimizer.optimize(initialConfig, predictions, model);
    assertThat(optimizedConfig).isNotSameAs(initialConfig);
    LimeExplainer limeExplainer = new LimeExplainer(optimizedConfig);
    PredictionInput testPredictionInput = getTestInput();
    List<PredictionOutput> testPredictionOutputs = model.predictAsync(List.of(testPredictionInput)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    Prediction instance = new SimplePrediction(testPredictionInput, testPredictionOutputs.get(0));
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, instance, limeExplainer, 1, 0.6, 0.4));
}

Example 34 with PredictionOutput

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

the class FraudScoringDmnLimeExplainerTest method testFraudScoringDMNExplanation.

@Test
void testFraudScoringDMNExplanation() throws ExecutionException, InterruptedException, TimeoutException {
    PredictionProvider model = getModel();
    PredictionInput predictionInput = getTestInput();
    List<PredictionOutput> predictionOutputs = model.predictAsync(List.of(predictionInput)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    Prediction prediction = new SimplePrediction(predictionInput, predictionOutputs.get(0));
    Random random = new Random();
    PerturbationContext perturbationContext = new PerturbationContext(0L, random, 1);
    LimeConfig limeConfig = new LimeConfig().withSamples(10).withPerturbationContext(perturbationContext);
    LimeExplainer limeExplainer = new LimeExplainer(limeConfig);
    Map<String, Saliency> saliencyMap = limeExplainer.explainAsync(prediction, model).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    for (Saliency saliency : saliencyMap.values()) {
        assertNotNull(saliency);
        List<FeatureImportance> topFeatures = saliency.getTopFeatures(4);
        double topScore = Math.abs(topFeatures.stream().map(FeatureImportance::getScore).findFirst().orElse(0d));
        if (!topFeatures.isEmpty() && topScore > 0) {
            double v = ExplainabilityMetrics.impactScore(model, prediction, topFeatures);
            // checks the drop of important features triggers a flipped prediction (or a significant drop in the output score).
            assertThat(v).isPositive();
        }
    }
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, prediction, limeExplainer, 1, 0.4, // set to 0.4 since "Last Transaction" is inherently unstable output
    0.4));
    String decision = "Risk Score";
    List<PredictionInput> inputs = new ArrayList<>();
    for (int n = 0; n < 10; n++) {
        inputs.add(new PredictionInput(DataUtils.perturbFeatures(predictionInput.getFeatures(), perturbationContext)));
    }
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    int k = 2;
    int chunkSize = 2;
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    AssertionsForClassTypes.assertThat(f1).isBetween(0.5d, 1d);
}

Example 35 with PredictionOutput

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

the class FraudScoringDmnPDPExplainerTest method testFraudScoringDMNExplanation.

@Test
void testFraudScoringDMNExplanation() throws ExecutionException, InterruptedException, TimeoutException {
    DMNRuntime dmnRuntime = DMNKogito.createGenericDMNRuntime(new InputStreamReader(getClass().getResourceAsStream("/dmn/fraud.dmn")));
    assertEquals(1, dmnRuntime.getModels().size());
    final String FRAUD_NS = "http://www.redhat.com/dmn/definitions/_81556584-7d78-4f8c-9d5f-b3cddb9b5c73";
    final String FRAUD_NAME = "fraud-scoring";
    DecisionModel decisionModel = new DmnDecisionModel(dmnRuntime, FRAUD_NS, FRAUD_NAME);
    PredictionProvider model = new DecisionModelWrapper(decisionModel);
    List<PredictionInput> inputs = DmnTestUtils.randomFraudScoringInputs();
    List<PredictionOutput> predictionOutputs = model.predictAsync(inputs).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    List<Prediction> predictions = new ArrayList<>();
    for (int i = 0; i < predictionOutputs.size(); i++) {
        predictions.add(new SimplePrediction(inputs.get(i), predictionOutputs.get(i)));
    }
    PartialDependencePlotExplainer partialDependencePlotExplainer = new PartialDependencePlotExplainer();
    List<PartialDependenceGraph> pdps = partialDependencePlotExplainer.explainFromPredictions(model, predictions);
    assertThat(pdps).isNotNull();
    Assertions.assertThat(pdps).hasSize(32);
}