Examples with ThresholdedRandomCutForest com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest used on opensource projects

Example 11 with ThresholdedRandomCutForest

use of com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest in project ml-commons by opensearch-project.

the class FixedInTimeRandomCutForest method trainAndPredict.

@Override
public MLOutput trainAndPredict(DataFrame dataFrame) {
    ThresholdedRandomCutForest forest = createThresholdedRandomCutForest(dataFrame);
    List<Map<String, Object>> predictResult = process(dataFrame, forest);
    return MLPredictionOutput.builder().predictionResult(DataFrameBuilder.load(predictResult)).build();
}

Example 12 with ThresholdedRandomCutForest

use of com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapperTest method testRoundTripStandardShingled.

@Test
public void testRoundTripStandardShingled() {
    int sampleSize = 256;
    int baseDimensions = 2;
    int shingleSize = 4;
    int dimensions = baseDimensions * shingleSize;
    long seed = new Random().nextLong();
    RandomCutForest.Builder<?> builder = RandomCutForest.builder().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed);
    ThresholdedRandomCutForest first = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).shingleSize(shingleSize).anomalyRate(0.01).build();
    ThresholdedRandomCutForest second = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).shingleSize(shingleSize).anomalyRate(0.01).build();
    RandomCutForest forest = builder.build();
    // thresholds should not affect scores
    double value = 0.75 + 0.5 * new Random().nextDouble();
    first.setLowerThreshold(value);
    second.setLowerThreshold(value);
    Random r = new Random();
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.generateShingledDataWithKey(10 * sampleSize, 50, shingleSize, baseDimensions, seed);
    for (double[] point : dataWithKeys.data) {
        AnomalyDescriptor firstResult = first.process(point, 0L);
        AnomalyDescriptor secondResult = second.process(point, 0L);
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getRCFScore(), forest.getAnomalyScore(point), 1e-4);
        forest.update(point);
    }
    // serialize + deserialize
    ThresholdedRandomCutForestMapper mapper = new ThresholdedRandomCutForestMapper();
    ThresholdedRandomCutForest third = mapper.toModel(mapper.toState(second));
    MultiDimDataWithKey testData = ShingledMultiDimDataWithKeys.generateShingledDataWithKey(100, 50, shingleSize, baseDimensions, seed);
    // update re-instantiated forest
    for (double[] point : testData.data) {
        AnomalyDescriptor firstResult = first.process(point, 0L);
        AnomalyDescriptor secondResult = second.process(point, 0L);
        AnomalyDescriptor thirdResult = third.process(point, 0L);
        double score = forest.getAnomalyScore(point);
        assertEquals(score, firstResult.getRCFScore(), 1e-4);
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getRCFScore(), thirdResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getDataConfidence(), thirdResult.getDataConfidence(), 1e-10);
        forest.update(point);
    }
}

Example 13 with ThresholdedRandomCutForest

use of com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapperTest method testRoundTripImpute.

@ParameterizedTest
@MethodSource("args")
public void testRoundTripImpute(TransformMethod transformMethod, ImputationMethod imputationMethod) {
    int sampleSize = 256;
    int baseDimensions = 1;
    int shingleSize = 8;
    int dimensions = baseDimensions * shingleSize;
    long seed = new Random().nextLong();
    ThresholdedRandomCutForest first = ThresholdedRandomCutForest.builder().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).forestMode(ForestMode.STREAMING_IMPUTE).internalShinglingEnabled(true).shingleSize(shingleSize).transformMethod(transformMethod).imputationMethod(imputationMethod).fillValues(new double[] { 1.0 }).anomalyRate(0.01).build();
    ThresholdedRandomCutForest second = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).forestMode(ForestMode.STREAMING_IMPUTE).internalShinglingEnabled(true).shingleSize(shingleSize).transformMethod(transformMethod).imputationMethod(imputationMethod).fillValues(new double[] { 1.0 }).anomalyRate(0.01).build();
    Random r = new Random();
    long count = 0;
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(10 * sampleSize, 50, 100, 5, seed, baseDimensions);
    for (double[] point : dataWithKeys.data) {
        if (r.nextDouble() > 0.1) {
            long stamp = 1000 * count + r.nextInt(10) - 5;
            AnomalyDescriptor firstResult = first.process(point, stamp);
            AnomalyDescriptor secondResult = second.process(point, stamp);
            assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        }
        ++count;
    }
    ;
    // serialize + deserialize
    ThresholdedRandomCutForestMapper mapper = new ThresholdedRandomCutForestMapper();
    ThresholdedRandomCutForest third = mapper.toModel(mapper.toState(second));
    MultiDimDataWithKey testData = ShingledMultiDimDataWithKeys.getMultiDimData(100, 50, 100, 5, seed, baseDimensions);
    // update re-instantiated forest
    for (double[] point : testData.data) {
        long stamp = 1000 * count + r.nextInt(10) - 5;
        AnomalyDescriptor firstResult = first.process(point, stamp);
        // AnomalyDescriptor secondResult = second.process(point, stamp);
        AnomalyDescriptor thirdResult = third.process(point, stamp);
        // assertEquals(firstResult.getRcfScore(), secondResult.getRcfScore(), 1e-10);
        assertEquals(firstResult.getRCFScore(), thirdResult.getRCFScore(), 1e-10);
        ++count;
    }
}

Example 14 with ThresholdedRandomCutForest

use of com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapperTest method testRoundTripStandardShingledInternal.

@Test
public void testRoundTripStandardShingledInternal() {
    int sampleSize = 256;
    int baseDimensions = 2;
    int shingleSize = 8;
    int dimensions = baseDimensions * shingleSize;
    long seed = new Random().nextLong();
    RandomCutForest forest = RandomCutForest.builder().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).internalShinglingEnabled(true).shingleSize(shingleSize).randomSeed(seed).build();
    ThresholdedRandomCutForest first = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).internalShinglingEnabled(true).shingleSize(shingleSize).anomalyRate(0.01).adjustThreshold(true).boundingBoxCacheFraction(0).build();
    ThresholdedRandomCutForest second = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).internalShinglingEnabled(true).shingleSize(shingleSize).anomalyRate(0.01).adjustThreshold(true).build();
    double value = 0.75 + 0.5 * new Random().nextDouble();
    first.setLowerThreshold(value);
    second.setLowerThreshold(value);
    Random r = new Random();
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(10 * sampleSize, 50, 100, 5, seed, baseDimensions);
    for (double[] point : dataWithKeys.data) {
        AnomalyDescriptor firstResult = first.process(point, 0L);
        AnomalyDescriptor secondResult = second.process(point, 0L);
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getRCFScore(), forest.getAnomalyScore(point), 1e-4);
        if (firstResult.getAnomalyGrade() > 0) {
            assertEquals(secondResult.getAnomalyGrade(), firstResult.getAnomalyGrade(), 1e-10);
            assert (firstResult.getRCFScore() >= value);
        }
        forest.update(point);
    }
    // serialize + deserialize
    ThresholdedRandomCutForestMapper mapper = new ThresholdedRandomCutForestMapper();
    ThresholdedRandomCutForest third = mapper.toModel(mapper.toState(second));
    MultiDimDataWithKey testData = ShingledMultiDimDataWithKeys.getMultiDimData(100, 50, 100, 5, seed, baseDimensions);
    // update re-instantiated forest
    for (double[] point : testData.data) {
        AnomalyDescriptor firstResult = first.process(point, 0L);
        AnomalyDescriptor secondResult = second.process(point, 0L);
        AnomalyDescriptor thirdResult = third.process(point, 0L);
        double score = forest.getAnomalyScore(point);
        assertEquals(score, firstResult.getRCFScore(), 1e-4);
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getRCFScore(), thirdResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getDataConfidence(), thirdResult.getDataConfidence(), 1e-10);
        forest.update(point);
    }
}

Example 15 with ThresholdedRandomCutForest

use of com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapperTest method testRoundTripAugmentedInitial.

@ParameterizedTest
@EnumSource(value = TransformMethod.class)
public void testRoundTripAugmentedInitial(TransformMethod method) {
    int sampleSize = 256;
    int baseDimensions = 2;
    int shingleSize = 8;
    int dimensions = baseDimensions * shingleSize;
    long seed = new Random().nextLong();
    // 0.25 * new Random().nextDouble();
    double value = 1.0;
    ThresholdedRandomCutForest first = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).forestMode(ForestMode.TIME_AUGMENTED).internalShinglingEnabled(true).shingleSize(shingleSize).transformMethod(method).anomalyRate(0.01).adjustThreshold(true).weights(new double[] { 1.0, 2.0 }).build();
    ThresholdedRandomCutForest second = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).forestMode(ForestMode.TIME_AUGMENTED).internalShinglingEnabled(true).shingleSize(shingleSize).transformMethod(method).anomalyRate(0.01).adjustThreshold(true).weights(new double[] { 1.0, 2.0 }).build();
    first.setLowerThreshold(value);
    second.setLowerThreshold(value);
    int count = 0;
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(sampleSize, 50, 100, 5, seed, baseDimensions);
    for (double[] point : dataWithKeys.data) {
        AnomalyDescriptor firstResult = first.process(point, 0L);
        AnomalyDescriptor secondResult = second.process(point, 0L);
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        assertEquals(secondResult.getAnomalyGrade(), firstResult.getAnomalyGrade(), 1e-10);
        // serialize + deserialize
        ThresholdedRandomCutForestMapper mapper = new ThresholdedRandomCutForestMapper();
        second = mapper.toModel(mapper.toState(second));
    }
}