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

Example 46 with Saliency

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

the class LimeExplainer method getSaliencies.

private Map<String, Saliency> getSaliencies(List<Feature> linearizedTargetInputFeatures, List<Output> actualOutputs, List<LimeInputs> limeInputsList, LimeConfig executionConfig) {
    Map<String, Saliency> result = new HashMap<>();
    for (int o = 0; o < actualOutputs.size(); o++) {
        LimeInputs limeInputs = limeInputsList.get(o);
        Output originalOutput = actualOutputs.get(o);
        getSaliency(linearizedTargetInputFeatures, result, limeInputs, originalOutput, executionConfig);
        LOGGER.debug("weights set for output {}", originalOutput);
    }
    return result;
}

Example 47 with Saliency

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

the class ShapKernelExplainer method saliencyFromMatrix.

/**
 * Given an n x m matrix of n outputs and m feature importances, return an array of Saliencies
 *
 * @param m: The n x m matrix
 * @param pi: The prediction input
 * @param po: The prediction output
 *
 * @return an array of n saliencies, one for each output of the model. Each Saliency lists the feature
 *         importances of each input feature to that particular output
 */
public static Saliency[] saliencyFromMatrix(RealMatrix m, PredictionInput pi, PredictionOutput po) {
    Saliency[] saliencies = new Saliency[m.getRowDimension()];
    for (int i = 0; i < m.getRowDimension(); i++) {
        List<FeatureImportance> fis = new ArrayList<>();
        for (int j = 0; j < m.getColumnDimension(); j++) {
            fis.add(new FeatureImportance(pi.getFeatures().get(j), m.getEntry(i, j)));
        }
        saliencies[i] = new Saliency(po.getOutputs().get(i), fis);
    }
    return saliencies;
}

Example 48 with Saliency

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

the class TrafficViolationDmnLimeExplainerTest method testTrafficViolationDMNExplanation.

@Test
void testTrafficViolationDMNExplanation() 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<String> strings = saliency.getTopFeatures(3).stream().map(f -> f.getFeature().getName()).collect(Collectors.toList());
        assertTrue(strings.contains("Actual Speed") || strings.contains("Speed Limit"));
    }
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, prediction, limeExplainer, 1, 0.3, 0.3));
    String decision = "Fine";
    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 = 5;
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    AssertionsForClassTypes.assertThat(f1).isBetween(0.5d, 1d);
}

Example 49 with Saliency

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

the class PmmlRegressionCategoricalLimeExplainerTest method testPMMLRegressionCategorical.

@Disabled("See KOGITO-6154")
@Test
void testPMMLRegressionCategorical() throws Exception {
    PredictionInput input = getTestInput();
    Random random = new Random();
    LimeConfig limeConfig = new LimeConfig().withSamples(10).withAdaptiveVariance(true).withPerturbationContext(new PerturbationContext(0L, random, 1));
    LimeExplainer limeExplainer = new LimeExplainer(limeConfig);
    PredictionProvider model = getModel();
    List<PredictionOutput> predictionOutputs = model.predictAsync(List.of(input)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    assertThat(predictionOutputs).isNotNull().isNotEmpty();
    PredictionOutput output = predictionOutputs.get(0);
    assertThat(output).isNotNull();
    Prediction prediction = new SimplePrediction(input, output);
    Map<String, Saliency> saliencyMap = limeExplainer.explainAsync(prediction, model).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    for (Saliency saliency : saliencyMap.values()) {
        assertThat(saliency).isNotNull();
        double v = ExplainabilityMetrics.impactScore(model, prediction, saliency.getTopFeatures(2));
        assertThat(v).isEqualTo(1d);
    }
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, prediction, limeExplainer, 1, 0.5, 0.5));
    List<PredictionInput> inputs = getSamples();
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    String decision = "result";
    int k = 1;
    int chunkSize = 2;
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    AssertionsForClassTypes.assertThat(f1).isBetween(0d, 1d);
}

Example 50 with Saliency

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

the class PmmlRegressionLimeExplainerTest method testPMMLRegression.

@Test
void testPMMLRegression() throws Exception {
    Random random = new Random();
    PerturbationContext perturbationContext = new PerturbationContext(0L, random, 1);
    LimeConfig limeConfig = new LimeConfig().withSamples(100).withPerturbationContext(perturbationContext);
    LimeExplainer limeExplainer = new LimeExplainer(limeConfig);
    PredictionInput input = getTestInput();
    PredictionProvider model = getModel();
    List<PredictionOutput> predictionOutputs = model.predictAsync(List.of(input)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    assertThat(predictionOutputs).isNotNull();
    assertThat(predictionOutputs).isNotEmpty();
    PredictionOutput output = predictionOutputs.get(0);
    assertThat(output).isNotNull();
    Prediction prediction = new SimplePrediction(input, output);
    Map<String, Saliency> saliencyMap = limeExplainer.explainAsync(prediction, model).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    for (Saliency saliency : saliencyMap.values()) {
        assertThat(saliency).isNotNull();
        double v = ExplainabilityMetrics.impactScore(model, prediction, saliency.getTopFeatures(2));
        assertThat(v).isEqualTo(1d);
    }
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, prediction, limeExplainer, 1, 0.1, 0.1));
    List<PredictionInput> inputs = getSamples();
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    String decision = "species";
    int k = 2;
    int chunkSize = 5;
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    AssertionsForClassTypes.assertThat(f1).isBetween(0d, 1d);
}