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

Example 16 with FeatureImportance

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

the class DummyModelsLimeExplainerTest method testMapOneFeatureToOutputClassification.

@ParameterizedTest
@ValueSource(longs = { 0 })
void testMapOneFeatureToOutputClassification(long seed) throws Exception {
    Random random = new Random();
    int idx = 1;
    List<Feature> features = new LinkedList<>();
    features.add(FeatureFactory.newNumericalFeature("f1", 1));
    features.add(FeatureFactory.newNumericalFeature("f2", 1));
    features.add(FeatureFactory.newNumericalFeature("f3", 3));
    PredictionInput input = new PredictionInput(features);
    PredictionProvider model = TestUtils.getEvenFeatureModel(idx);
    List<PredictionOutput> outputs = model.predictAsync(List.of(input)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    Prediction prediction = new SimplePrediction(input, outputs.get(0));
    LimeConfig limeConfig = new LimeConfig().withSamples(100).withPerturbationContext(new PerturbationContext(seed, random, 2));
    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(3);
        assertEquals(3, topFeatures.size());
        assertEquals(1d, ExplainabilityMetrics.impactScore(model, prediction, topFeatures));
    }
    double minimumPositiveStabilityRate = 0.5;
    double minimumNegativeStabilityRate = 0.5;
    int topK = 1;
    TestUtils.assertLimeStability(model, prediction, limeExplainer, topK, minimumPositiveStabilityRate, minimumNegativeStabilityRate);
    List<PredictionInput> inputs = new ArrayList<>();
    for (int i = 0; i < 100; i++) {
        List<Feature> fs = new LinkedList<>();
        fs.add(TestUtils.getMockedNumericFeature());
        fs.add(TestUtils.getMockedNumericFeature());
        fs.add(TestUtils.getMockedNumericFeature());
        inputs.add(new PredictionInput(fs));
    }
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    int k = 2;
    int chunkSize = 10;
    String decision = "feature-" + idx;
    double precision = ExplainabilityMetrics.getLocalSaliencyPrecision(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(precision).isEqualTo(1);
    double recall = ExplainabilityMetrics.getLocalSaliencyRecall(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(recall).isEqualTo(1);
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(f1).isEqualTo(1);
}

Example 17 with FeatureImportance

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

the class DummyModelsLimeExplainerTest method testUnusedFeatureRegression.

@ParameterizedTest
@ValueSource(longs = { 0 })
void testUnusedFeatureRegression(long seed) throws Exception {
    Random random = new Random();
    int idx = 2;
    List<Feature> features = new LinkedList<>();
    features.add(TestUtils.getMockedNumericFeature(100));
    features.add(TestUtils.getMockedNumericFeature(20));
    features.add(TestUtils.getMockedNumericFeature(10));
    PredictionProvider model = TestUtils.getSumSkipModel(idx);
    PredictionInput input = new PredictionInput(features);
    List<PredictionOutput> outputs = model.predictAsync(List.of(input)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    Prediction prediction = new SimplePrediction(input, outputs.get(0));
    LimeConfig limeConfig = new LimeConfig().withSamples(10).withPerturbationContext(new PerturbationContext(seed, random, 1));
    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(3);
        assertEquals(3, topFeatures.size());
        assertEquals(1d, ExplainabilityMetrics.impactScore(model, prediction, topFeatures));
    }
    int topK = 1;
    double minimumPositiveStabilityRate = 0.5;
    double minimumNegativeStabilityRate = 0.5;
    TestUtils.assertLimeStability(model, prediction, limeExplainer, topK, minimumPositiveStabilityRate, minimumNegativeStabilityRate);
    List<PredictionInput> inputs = new ArrayList<>();
    for (int i = 0; i < 100; i++) {
        List<Feature> fs = new LinkedList<>();
        fs.add(TestUtils.getMockedNumericFeature());
        fs.add(TestUtils.getMockedNumericFeature());
        fs.add(TestUtils.getMockedNumericFeature());
        inputs.add(new PredictionInput(fs));
    }
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    int k = 2;
    int chunkSize = 10;
    String decision = "sum-but" + idx;
    double precision = ExplainabilityMetrics.getLocalSaliencyPrecision(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(precision).isEqualTo(1);
    double recall = ExplainabilityMetrics.getLocalSaliencyRecall(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(recall).isEqualTo(1);
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(f1).isEqualTo(1);
}

Example 18 with FeatureImportance

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

the class DummyModelsLimeExplainerTest method testMapOneFeatureToOutputRegression.

@ParameterizedTest
@ValueSource(longs = { 0 })
void testMapOneFeatureToOutputRegression(long seed) throws Exception {
    Random random = new Random();
    int idx = 1;
    List<Feature> features = new LinkedList<>();
    features.add(TestUtils.getMockedNumericFeature(100));
    features.add(TestUtils.getMockedNumericFeature(20));
    features.add(TestUtils.getMockedNumericFeature(0.1));
    PredictionInput input = new PredictionInput(features);
    PredictionProvider model = TestUtils.getFeaturePassModel(idx);
    List<PredictionOutput> outputs = model.predictAsync(List.of(input)).get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    Prediction prediction = new SimplePrediction(input, outputs.get(0));
    LimeConfig limeConfig = new LimeConfig().withSamples(100).withPerturbationContext(new PerturbationContext(seed, random, 1));
    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(3);
        assertEquals(3, topFeatures.size());
        assertEquals(1d, ExplainabilityMetrics.impactScore(model, prediction, topFeatures));
    }
    int topK = 1;
    double minimumPositiveStabilityRate = 0.5;
    double minimumNegativeStabilityRate = 0.5;
    TestUtils.assertLimeStability(model, prediction, limeExplainer, topK, minimumPositiveStabilityRate, minimumNegativeStabilityRate);
    List<PredictionInput> inputs = new ArrayList<>();
    for (int i = 0; i < 100; i++) {
        List<Feature> fs = new LinkedList<>();
        fs.add(TestUtils.getMockedNumericFeature());
        fs.add(TestUtils.getMockedNumericFeature());
        fs.add(TestUtils.getMockedNumericFeature());
        inputs.add(new PredictionInput(fs));
    }
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    int k = 2;
    int chunkSize = 10;
    String decision = "feature-" + idx;
    double precision = ExplainabilityMetrics.getLocalSaliencyPrecision(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(precision).isZero();
    double recall = ExplainabilityMetrics.getLocalSaliencyRecall(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(recall).isEqualTo(1);
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    assertThat(f1).isZero();
}

Example 19 with FeatureImportance

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

the class ExplainabilityMetricsTest method testBrokenPredict.

@Test
void testBrokenPredict() {
    Config.INSTANCE.setAsyncTimeout(1);
    Config.INSTANCE.setAsyncTimeUnit(TimeUnit.MILLISECONDS);
    Prediction emptyPrediction = new SimplePrediction(new PredictionInput(emptyList()), new PredictionOutput(emptyList()));
    PredictionProvider brokenProvider = inputs -> supplyAsync(() -> {
        await().atLeast(1, TimeUnit.SECONDS).until(() -> false);
        throw new RuntimeException("this should never happen");
    });
    List<FeatureImportance> emptyFeatures = emptyList();
    try {
        Assertions.assertThrows(IllegalStateException.class, () -> ExplainabilityMetrics.impactScore(brokenProvider, emptyPrediction, emptyFeatures));
    } finally {
        Config.INSTANCE.setAsyncTimeout(Config.DEFAULT_ASYNC_TIMEOUT);
        Config.INSTANCE.setAsyncTimeUnit(Config.DEFAULT_ASYNC_TIMEUNIT);
    }
}

Example 20 with FeatureImportance

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

the class LimeExplainerTest method testDeterministic.

@ParameterizedTest
@ValueSource(longs = { 0, 1, 2, 3, 4 })
void testDeterministic(long seed) throws ExecutionException, InterruptedException, TimeoutException {
    List<Saliency> saliencies = new ArrayList<>();
    for (int j = 0; j < 2; j++) {
        Random random = new Random();
        LimeConfig limeConfig = new LimeConfig().withPerturbationContext(new PerturbationContext(seed, random, DEFAULT_NO_OF_PERTURBATIONS)).withSamples(10);
        LimeExplainer limeExplainer = new LimeExplainer(limeConfig);
        List<Feature> features = new ArrayList<>();
        for (int i = 0; i < 4; i++) {
            features.add(TestUtils.getMockedNumericFeature(i));
        }
        PredictionInput input = new PredictionInput(features);
        PredictionProvider model = TestUtils.getSumSkipModel(0);
        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());
        saliencies.add(saliencyMap.get("sum-but0"));
    }
    assertThat(saliencies.get(0).getPerFeatureImportance().stream().map(FeatureImportance::getScore).collect(Collectors.toList())).isEqualTo(saliencies.get(1).getPerFeatureImportance().stream().map(FeatureImportance::getScore).collect(Collectors.toList()));
}