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

Example 1 with ThresholdedRandomCutForest

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

the class ThresholdedRandomCutForestMapperTest method testRoundTripTimeAugmentedNormalize.

@ParameterizedTest
@EnumSource(value = TransformMethod.class)
public void testRoundTripTimeAugmentedNormalize(TransformMethod method) {
    int sampleSize = 256;
    int baseDimensions = 2;
    int shingleSize = 4;
    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.TIME_AUGMENTED).normalizeTime(true).transformMethod(method).internalShinglingEnabled(true).shingleSize(shingleSize).anomalyRate(0.01).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).normalizeTime(true).internalShinglingEnabled(true).transformMethod(method).shingleSize(shingleSize).anomalyRate(0.01).weights(new double[] { 1.0, 2.0 }).build();
    Random r = new Random();
    long count = 0;
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(10 * sampleSize, 50, 100, 5, seed, baseDimensions);
    for (double[] point : dataWithKeys.data) {
        long stamp = 1000 * count + r.nextInt(10) - 5;
        AnomalyDescriptor firstResult = first.process(point, stamp);
        AnomalyDescriptor secondResult = second.process(point, stamp);
        ++count;
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
    }
    // 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 = 100 * 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 2 with ThresholdedRandomCutForest

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

the class ThresholdedRandomCutForestMapperTest method testRoundTripImputeInitial.

@ParameterizedTest
@MethodSource("args")
public void testRoundTripImputeInitial(TransformMethod transformMethod, ImputationMethod imputationMethod) {
    int sampleSize = 256;
    int baseDimensions = 2;
    int shingleSize = 4;
    int dimensions = baseDimensions * shingleSize;
    long seed = new Random().nextLong();
    System.out.println(seed);
    ThresholdedRandomCutForest first = 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, 2.0 }).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, 2.0 }).anomalyRate(0.01).build();
    Random r = new Random(0);
    long count = 0;
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(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();
        second = mapper.toModel(mapper.toState(second));
    }
}

Example 3 with ThresholdedRandomCutForest

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

the class ThresholdedRandomCutForestMapperTest method testConversions.

@Test
public void testConversions() {
    int dimensions = 10;
    for (int trials = 0; trials < 10; trials++) {
        long seed = new Random().nextLong();
        RandomCutForest forest = RandomCutForest.builder().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).internalShinglingEnabled(false).randomSeed(seed).build();
        // note shingleSize == 1
        ThresholdedRandomCutForest first = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).internalShinglingEnabled(false).anomalyRate(0.01).build();
        Random r = new Random();
        for (int i = 0; i < new Random().nextInt(1000); i++) {
            double[] point = r.ints(dimensions, 0, 50).asDoubleStream().toArray();
            first.process(point, 0L);
            forest.update(point);
        }
        RandomCutForestMapper mapper = new RandomCutForestMapper();
        mapper.setSaveExecutorContextEnabled(true);
        mapper.setSaveTreeStateEnabled(true);
        mapper.setPartialTreeStateEnabled(true);
        RandomCutForest copyForest = mapper.toModel(mapper.toState(forest));
        ThresholdedRandomCutForest second = new ThresholdedRandomCutForest(copyForest, 0.01, null);
        // 
        for (int i = 0; i < new Random().nextInt(1000); i++) {
            double[] point = r.ints(dimensions, 0, 50).asDoubleStream().toArray();
            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-10);
            forest.update(point);
        }
        // serialize + deserialize
        ThresholdedRandomCutForestMapper newMapper = new ThresholdedRandomCutForestMapper();
        ThresholdedRandomCutForest third = newMapper.toModel(newMapper.toState(second));
        // update re-instantiated forest
        for (int i = 0; i < 100; i++) {
            double[] point = r.ints(dimensions, 0, 50).asDoubleStream().toArray();
            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-10);
            assertEquals(score, secondResult.getRCFScore(), 1e-10);
            assertEquals(score, thirdResult.getRCFScore(), 1e-10);
            assertEquals(firstResult.getDataConfidence(), thirdResult.getDataConfidence(), 1e-10);
            forest.update(point);
        }
    }
}

Example 4 with ThresholdedRandomCutForest

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

the class ThresholdedRandomCutForestMapperTest method testRoundTripTimeAugmented.

@ParameterizedTest
@EnumSource(value = TransformMethod.class)
public void testRoundTripTimeAugmented(TransformMethod method) {
    int sampleSize = 256;
    int baseDimensions = 1;
    int shingleSize = 8;
    int dimensions = baseDimensions * shingleSize;
    long seed = new Random().nextLong();
    double value = 1.0 + 0.25 * new Random().nextDouble();
    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 }).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 }).build();
    first.setLowerThreshold(value);
    second.setLowerThreshold(value);
    Random r = new Random();
    long count = 0;
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(10 * sampleSize, 50, 100, 5, seed, baseDimensions);
    for (double[] point : dataWithKeys.data) {
        long stamp = 100 * count + r.nextInt(10) - 5;
        AnomalyDescriptor firstResult = first.process(point, stamp);
        AnomalyDescriptor secondResult = second.process(point, stamp);
        ++count;
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        if (firstResult.getAnomalyGrade() > 0) {
            assertEquals(secondResult.getAnomalyGrade(), firstResult.getAnomalyGrade(), 1e-10);
            assert (firstResult.getRCFScore() >= value);
        }
    }
    // 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 = 100 * count + r.nextInt(10) - 5;
        AnomalyDescriptor firstResult = first.process(point, 0L);
        AnomalyDescriptor secondResult = second.process(point, 0L);
        AnomalyDescriptor thirdResult = third.process(point, 0L);
        assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getRCFScore(), thirdResult.getRCFScore(), 1e-10);
        assertEquals(firstResult.getAnomalyGrade(), thirdResult.getAnomalyGrade(), 1e-10);
        ++count;
    }
}

Example 5 with ThresholdedRandomCutForest

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

the class ThresholdedRandomCutForestMapperTest method testRoundTripStandardShingleSizeOne.

@Test
public void testRoundTripStandardShingleSizeOne() {
    int dimensions = 10;
    for (int trials = 0; trials < 1; trials++) {
        long seed = new Random().nextLong();
        RandomCutForest.Builder<?> builder = RandomCutForest.builder().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed);
        // note shingleSize == 1
        ThresholdedRandomCutForest first = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).internalShinglingEnabled(true).anomalyRate(0.01).build();
        ThresholdedRandomCutForest second = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).anomalyRate(0.01).forestMode(ForestMode.STANDARD).internalShinglingEnabled(false).build();
        RandomCutForest forest = builder.build();
        Random r = new Random();
        for (int i = 0; i < 2000 + new Random().nextInt(1000); i++) {
            double[] point = r.ints(dimensions, 0, 50).asDoubleStream().toArray();
            AnomalyDescriptor firstResult = first.process(point, 0L);
            AnomalyDescriptor secondResult = second.process(point, 0L);
            assertEquals(firstResult.getDataConfidence(), secondResult.getDataConfidence(), 1e-10);
            assertEquals(firstResult.getRCFScore(), secondResult.getRCFScore(), 1e-10);
            assertEquals(firstResult.getRCFScore(), forest.getAnomalyScore(point), 1e-10);
            forest.update(point);
        }
        // serialize + deserialize
        ThresholdedRandomCutForestMapper mapper = new ThresholdedRandomCutForestMapper();
        ThresholdedRandomCutForest third = mapper.toModel(mapper.toState(second));
        // update re-instantiated forest
        for (int i = 0; i < 100; i++) {
            double[] point = r.ints(dimensions, 0, 50).asDoubleStream().toArray();
            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-10);
            assertEquals(score, secondResult.getRCFScore(), 1e-10);
            assertEquals(score, thirdResult.getRCFScore(), 1e-10);
            assertEquals(firstResult.getDataConfidence(), secondResult.getDataConfidence(), 1e-10);
            forest.update(point);
        }
    }
}