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

Example 11 with PredictionInputsDataDistribution

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

the class DummyModelsLimeExplainerTest method testTextSpamClassification.

@ParameterizedTest
@ValueSource(longs = { 0 })
void testTextSpamClassification(long seed) throws Exception {
    Random random = new Random();
    List<Feature> features = new LinkedList<>();
    Function<String, List<String>> tokenizer = s -> Arrays.asList(s.split(" ").clone());
    features.add(FeatureFactory.newFulltextFeature("f1", "we go here and there", tokenizer));
    features.add(FeatureFactory.newFulltextFeature("f2", "please give me some money", tokenizer));
    features.add(FeatureFactory.newFulltextFeature("f3", "dear friend, please reply", tokenizer));
    PredictionInput input = new PredictionInput(features);
    PredictionProvider model = TestUtils.getDummyTextClassifier();
    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).toCompletableFuture().get(Config.INSTANCE.getAsyncTimeout(), Config.INSTANCE.getAsyncTimeUnit());
    for (Saliency saliency : saliencyMap.values()) {
        assertNotNull(saliency);
        List<FeatureImportance> topFeatures = saliency.getPositiveFeatures(1);
        assertEquals(1, topFeatures.size());
        assertEquals(1d, ExplainabilityMetrics.impactScore(model, prediction, topFeatures));
    }
    int topK = 1;
    double minimumPositiveStabilityRate = 0.5;
    double minimumNegativeStabilityRate = 0.2;
    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 = "spam";
    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 12 with PredictionInputsDataDistribution

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

the class PmmlScorecardCategoricalLimeExplainerTest method testPMMLScorecardCategorical.

@Test
void testPMMLScorecardCategorical() throws Exception {
    PredictionInput input = getTestInput();
    Random random = new Random();
    LimeConfig limeConfig = new LimeConfig().withSamples(10).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).isGreaterThan(0d);
    }
    assertDoesNotThrow(() -> ValidationUtils.validateLocalSaliencyStability(model, prediction, limeExplainer, 1, 0.4, 0.4));
    List<PredictionInput> inputs = getSamples();
    DataDistribution distribution = new PredictionInputsDataDistribution(inputs);
    String decision = "score";
    int k = 1;
    int chunkSize = 2;
    double f1 = ExplainabilityMetrics.getLocalSaliencyF1(decision, model, limeExplainer, distribution, k, chunkSize);
    AssertionsForClassTypes.assertThat(f1).isBetween(0d, 1d);
}

Example 13 with PredictionInputsDataDistribution

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

the class DummyModelsLimeExplainerTest method testFixedOutput.

@ParameterizedTest
@ValueSource(longs = { 0 })
void testFixedOutput(long seed) throws Exception {
    Random random = new Random();
    List<Feature> features = new LinkedList<>();
    features.add(FeatureFactory.newNumericalFeature("f1", 6));
    features.add(FeatureFactory.newNumericalFeature("f2", 3));
    features.add(FeatureFactory.newNumericalFeature("f3", 5));
    PredictionProvider model = TestUtils.getFixedOutputClassifier();
    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());
        for (FeatureImportance featureImportance : topFeatures) {
            assertEquals(0, featureImportance.getScore());
        }
        assertEquals(0d, 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 = "class";
    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 14 with PredictionInputsDataDistribution

use of org.kie.kogito.explainability.model.PredictionInputsDataDistribution 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 15 with PredictionInputsDataDistribution

use of org.kie.kogito.explainability.model.PredictionInputsDataDistribution 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);
}