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

Example 16 with Output

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

the class CounterfactualScoreCalculatorTest method IntegerDistanceDifferentValue.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2, 3, 4 })
void IntegerDistanceDifferentValue(int seed) {
    final Random random = new Random(seed);
    int value = random.nextInt(1000);
    Feature x = FeatureFactory.newNumericalFeature("x", value);
    Feature y = FeatureFactory.newNumericalFeature("y", value + 100);
    Output ox = outputFromFeature(x);
    Output oy = outputFromFeature(y);
    double distance = CounterFactualScoreCalculator.outputDistance(ox, oy);
    assertEquals(Type.NUMBER, ox.getType());
    assertEquals(Type.NUMBER, oy.getType());
    assertTrue(distance * distance > 0);
    y = FeatureFactory.newNumericalFeature("y", value - 100);
    oy = outputFromFeature(y);
    distance = CounterFactualScoreCalculator.outputDistance(ox, oy);
    assertTrue(distance * distance > 0);
}

Example 17 with Output

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

the class CounterfactualScoreCalculatorTest method IntegerDistanceNull.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2, 3, 4 })
void IntegerDistanceNull(int seed) {
    final Random random = new Random(seed);
    final int value = random.nextInt(1000);
    // Null as a goal
    IllegalArgumentException exception = assertThrows(IllegalArgumentException.class, () -> {
        Feature predictionFeature = FeatureFactory.newNumericalFeature("x", value);
        Feature goalFeature = FeatureFactory.newNumericalFeature("x", null);
        Output predictionOutput = outputFromFeature(predictionFeature);
        Output goalOutput = outputFromFeature(goalFeature);
        CounterFactualScoreCalculator.outputDistance(predictionOutput, goalOutput);
    });
    assertEquals("Unsupported NaN or NULL for numeric feature 'x'", exception.getMessage());
    // Null as a prediction
    exception = assertThrows(IllegalArgumentException.class, () -> {
        Feature predictionFeature = FeatureFactory.newNumericalFeature("x", null);
        Feature goalFeature = FeatureFactory.newNumericalFeature("x", value);
        Output predictionOutput = outputFromFeature(predictionFeature);
        Output goalOutput = outputFromFeature(goalFeature);
        CounterFactualScoreCalculator.outputDistance(predictionOutput, goalOutput);
    });
    assertEquals("Unsupported NaN or NULL for numeric feature 'x'", exception.getMessage());
    // Null as both prediction and goal
    exception = assertThrows(IllegalArgumentException.class, () -> {
        Feature predictionFeature = FeatureFactory.newNumericalFeature("x", null);
        Feature goalFeature = FeatureFactory.newNumericalFeature("x", null);
        Output predictionOutput = outputFromFeature(predictionFeature);
        Output goalOutput = outputFromFeature(goalFeature);
        CounterFactualScoreCalculator.outputDistance(predictionOutput, goalOutput);
    });
    assertEquals("Unsupported NaN or NULL for numeric feature 'x'", exception.getMessage());
}

Example 18 with Output

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

the class CounterfactualScoreCalculatorTest method DoubleDistanceDifferentValueThresholdMet.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2, 3, 4 })
void DoubleDistanceDifferentValueThresholdMet(int seed) {
    final double value = 100.0;
    Feature x = FeatureFactory.newNumericalFeature("x", value);
    Feature y = FeatureFactory.newNumericalFeature("y", value - 20.0);
    Output ox = outputFromFeature(x);
    Output oy = outputFromFeature(y);
    double distance = CounterFactualScoreCalculator.outputDistance(ox, oy);
    assertEquals(Type.NUMBER, ox.getType());
    assertEquals(Type.NUMBER, oy.getType());
    assertTrue(distance * distance > 0);
    distance = CounterFactualScoreCalculator.outputDistance(ox, oy, 0.1);
    assertTrue(distance * distance > 0);
    distance = CounterFactualScoreCalculator.outputDistance(ox, oy, 0.2);
    assertTrue(distance * distance > 0);
    distance = CounterFactualScoreCalculator.outputDistance(ox, oy, 0.3);
    assertFalse(distance * distance > 0);
}

Example 19 with Output

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

the class CounterfactualScoreCalculatorTest method DoubleDistanceSameValueZero.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2, 3, 4 })
void DoubleDistanceSameValueZero(int seed) {
    final Random random = new Random(seed);
    final double value = 0.0;
    Feature x = FeatureFactory.newNumericalFeature("x", value);
    Feature y = FeatureFactory.newNumericalFeature("y", value);
    Output ox = outputFromFeature(x);
    Output oy = outputFromFeature(y);
    // Use a random threshold, mustn't make a difference
    final double distance = CounterFactualScoreCalculator.outputDistance(ox, oy, random.nextDouble());
    assertEquals(Type.NUMBER, ox.getType());
    assertEquals(0.0, distance);
}

Example 20 with Output

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

the class CounterfactualScoreCalculatorTest method currencyDistanceSameValue.

@ParameterizedTest
@ValueSource(ints = { 0, 1, 2, 3, 4 })
void currencyDistanceSameValue(int seed) {
    final Random random = new Random(seed);
    final Currency value = Currency.getInstance(Locale.US);
    Feature x = FeatureFactory.newCurrencyFeature("x", value);
    Feature y = FeatureFactory.newCurrencyFeature("y", value);
    Output ox = outputFromFeature(x);
    Output oy = outputFromFeature(y);
    double distance = CounterFactualScoreCalculator.outputDistance(ox, oy);
    assertEquals(Type.CURRENCY, ox.getType());
    assertEquals(0.0, distance);
    // Use a random threshold, mustn't make a difference
    distance = CounterFactualScoreCalculator.outputDistance(ox, oy, random.nextDouble());
    assertEquals(0.0, distance);
}