Examples with MultiDimDataWithKey com.amazon.randomcutforest.testutils.MultiDimDataWithKey used on opensource projects

Example 6 with MultiDimDataWithKey

use of com.amazon.randomcutforest.testutils.MultiDimDataWithKey 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 7 with MultiDimDataWithKey

use of com.amazon.randomcutforest.testutils.MultiDimDataWithKey in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapperTest method testRoundTripStandard.

@ParameterizedTest
@EnumSource(value = TransformMethod.class)
public void testRoundTripStandard(TransformMethod method) {
    int sampleSize = 256;
    int baseDimensions = 1;
    int shingleSize = 8;
    int dimensions = baseDimensions * shingleSize;
    long seed = 0;
    new Random().nextLong();
    ThresholdedRandomCutForest first = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).internalShinglingEnabled(true).shingleSize(shingleSize).anomalyRate(0.01).transformMethod(method).adjustThreshold(true).boundingBoxCacheFraction(0).weights(new double[] { 1.0 }).build();
    ThresholdedRandomCutForest second = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).precision(Precision.FLOAT_32).randomSeed(seed).internalShinglingEnabled(true).shingleSize(shingleSize).anomalyRate(0.01).transformMethod(method).adjustThreshold(true).weights(new double[] { 1.0 }).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);
        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) {
        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);
    }
}

Example 8 with MultiDimDataWithKey

use of com.amazon.randomcutforest.testutils.MultiDimDataWithKey in project random-cut-forest-by-aws by aws.

the class ThresholdedTime method run.

@Override
public void run() throws Exception {
    // Create and populate a random cut forest
    int shingleSize = 4;
    int numberOfTrees = 50;
    int sampleSize = 256;
    Precision precision = Precision.FLOAT_32;
    int dataSize = 4 * sampleSize;
    // change this to try different number of attributes,
    // this parameter is not expected to be larger than 5 for this example
    int baseDimensions = 1;
    int count = 0;
    int dimensions = baseDimensions * shingleSize;
    ThresholdedRandomCutForest forest = new ThresholdedRandomCutForest.Builder<>().compact(true).dimensions(dimensions).randomSeed(0).numberOfTrees(numberOfTrees).shingleSize(shingleSize).sampleSize(sampleSize).internalShinglingEnabled(true).precision(precision).anomalyRate(0.01).forestMode(ForestMode.TIME_AUGMENTED).normalizeTime(true).build();
    long seed = new Random().nextLong();
    double[] data = new double[] { 1.0 };
    System.out.println("seed = " + seed);
    NormalMixtureTestData normalMixtureTestData = new NormalMixtureTestData(10, 50);
    MultiDimDataWithKey dataWithKeys = normalMixtureTestData.generateTestDataWithKey(dataSize, 1, 0);
    /**
     * the anomalies will move from normal -> anomalous -> normal starts from normal
     */
    boolean anomalyState = false;
    int keyCounter = 0;
    for (double[] point : dataWithKeys.data) {
        long time = (long) (1000L * count + Math.floor(10 * point[0]));
        AnomalyDescriptor result = forest.process(data, time);
        if (keyCounter < dataWithKeys.changeIndices.length && count == dataWithKeys.changeIndices[keyCounter]) {
            System.out.print("Sequence " + count + " stamp " + (result.getInternalTimeStamp()) + " CHANGE ");
            if (!anomalyState) {
                System.out.println(" to Distribution 1 ");
            } else {
                System.out.println(" to Distribution 0 ");
            }
            anomalyState = !anomalyState;
            ++keyCounter;
        }
        if (result.getAnomalyGrade() != 0) {
            System.out.print("Sequence " + count + " stamp " + (result.getInternalTimeStamp()) + " RESULT ");
            System.out.print("score " + result.getRCFScore() + ", grade " + result.getAnomalyGrade() + ", ");
            if (result.isExpectedValuesPresent()) {
                if (result.getRelativeIndex() != 0 && result.isStartOfAnomaly()) {
                    System.out.print(-result.getRelativeIndex() + " steps ago, instead of stamp " + result.getPastTimeStamp());
                    System.out.print(", expected timestamp " + result.getExpectedTimeStamp() + " ( " + (result.getPastTimeStamp() - result.getExpectedTimeStamp() + ")"));
                } else {
                    System.out.print("expected " + result.getExpectedTimeStamp() + " ( " + (result.getInternalTimeStamp() - result.getExpectedTimeStamp() + ")"));
                }
            }
            System.out.println();
        }
        ++count;
    }
}

Example 9 with MultiDimDataWithKey

use of com.amazon.randomcutforest.testutils.MultiDimDataWithKey in project random-cut-forest-by-aws by aws.

the class ThresholdedInternalShinglingExample method run.

@Override
public void run() throws Exception {
    // Create and populate a random cut forest
    int shingleSize = 4;
    int numberOfTrees = 50;
    int sampleSize = 256;
    Precision precision = Precision.FLOAT_32;
    int dataSize = 4 * sampleSize;
    // change this to try different number of attributes,
    // this parameter is not expected to be larger than 5 for this example
    int baseDimensions = 1;
    long count = 0;
    int dimensions = baseDimensions * shingleSize;
    TransformMethod transformMethod = TransformMethod.NORMALIZE_DIFFERENCE;
    ThresholdedRandomCutForest forest = ThresholdedRandomCutForest.builder().compact(true).dimensions(dimensions).randomSeed(0).numberOfTrees(numberOfTrees).shingleSize(shingleSize).sampleSize(sampleSize).internalShinglingEnabled(true).precision(precision).anomalyRate(0.01).forestMode(ForestMode.STANDARD).weightTime(0).transformMethod(transformMethod).normalizeTime(true).outputAfter(32).initialAcceptFraction(0.125).build();
    ThresholdedRandomCutForest second = ThresholdedRandomCutForest.builder().compact(true).dimensions(dimensions).randomSeed(0).numberOfTrees(numberOfTrees).shingleSize(shingleSize).sampleSize(sampleSize).internalShinglingEnabled(true).precision(precision).anomalyRate(0.01).forestMode(ForestMode.TIME_AUGMENTED).weightTime(0).transformMethod(transformMethod).normalizeTime(true).outputAfter(32).initialAcceptFraction(0.125).build();
    // ensuring that the parameters are the same; otherwise the grades/scores cannot
    // be the same
    // weighTime has to be 0
    forest.setLowerThreshold(1.1);
    second.setLowerThreshold(1.1);
    forest.setHorizon(0.75);
    second.setHorizon(0.75);
    long seed = new Random().nextLong();
    Random noise = new Random(0);
    System.out.println("seed = " + seed);
    // change the last argument seed for a different run
    MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(dataSize + shingleSize - 1, 50, 100, 5, seed, baseDimensions);
    int keyCounter = 0;
    for (double[] point : dataWithKeys.data) {
        // idea is that we expect the arrival order to be roughly 100 apart (say
        // seconds)
        // then the noise corresponds to a jitter; one can try TIME_AUGMENTED and
        // .normalizeTime(true)
        long timestamp = 100 * count + noise.nextInt(10) - 5;
        AnomalyDescriptor result = forest.process(point, timestamp);
        AnomalyDescriptor test = second.process(point, timestamp);
        checkArgument(Math.abs(result.getRCFScore() - test.getRCFScore()) < 1e-10, " error");
        checkArgument(Math.abs(result.getAnomalyGrade() - test.getAnomalyGrade()) < 1e-10, " error");
        if (keyCounter < dataWithKeys.changeIndices.length && count == dataWithKeys.changeIndices[keyCounter]) {
            System.out.println("timestamp " + count + " CHANGE " + Arrays.toString(dataWithKeys.changes[keyCounter]));
            ++keyCounter;
        }
        if (result.getAnomalyGrade() != 0) {
            System.out.print("timestamp " + count + " RESULT value " + result.getInternalTimeStamp() + " ");
            for (int i = 0; i < baseDimensions; i++) {
                System.out.print(result.getCurrentInput()[i] + ", ");
            }
            System.out.print("score " + result.getRCFScore() + ", grade " + result.getAnomalyGrade() + ", ");
            if (result.getRelativeIndex() != 0 && result.isStartOfAnomaly()) {
                System.out.print(-result.getRelativeIndex() + " steps ago, ");
            }
            if (result.isExpectedValuesPresent()) {
                if (result.getRelativeIndex() != 0 && result.isStartOfAnomaly()) {
                    System.out.print("instead of ");
                    for (int i = 0; i < baseDimensions; i++) {
                        System.out.print(result.getPastValues()[i] + ", ");
                    }
                    System.out.print("expected ");
                    for (int i = 0; i < baseDimensions; i++) {
                        System.out.print(result.getExpectedValuesList()[0][i] + ", ");
                        if (result.getPastValues()[i] != result.getExpectedValuesList()[0][i]) {
                            System.out.print("( " + (result.getPastValues()[i] - result.getExpectedValuesList()[0][i]) + " ) ");
                        }
                    }
                } else {
                    System.out.print("expected ");
                    for (int i = 0; i < baseDimensions; i++) {
                        System.out.print(result.getExpectedValuesList()[0][i] + ", ");
                        if (result.getCurrentInput()[i] != result.getExpectedValuesList()[0][i]) {
                            System.out.print("( " + (result.getCurrentInput()[i] - result.getExpectedValuesList()[0][i]) + " ) ");
                        }
                    }
                }
            } else {
                System.out.print("insufficient data to provide expected values");
            }
            System.out.println();
        }
        ++count;
    }
}

Example 10 with MultiDimDataWithKey

use of com.amazon.randomcutforest.testutils.MultiDimDataWithKey in project random-cut-forest-by-aws by aws.

the class ConsistencyTest method ImputeTest.

@ParameterizedTest
@EnumSource(TransformMethod.class)
public void ImputeTest(TransformMethod transformMethod) {
    int sampleSize = 256;
    int baseDimensions = 1;
    int shingleSize = 4;
    int dimensions = baseDimensions * shingleSize;
    // test is exact equality, reducing the number of trials
    int numTrials = 1;
    // and using fewer trees to speed up test
    int numberOfTrees = 30;
    int length = 10 * sampleSize;
    int dataSize = 2 * length;
    for (int i = 0; i < numTrials; i++) {
        Precision precision = Precision.FLOAT_32;
        long seed = new Random().nextLong();
        System.out.println("seed = " + seed);
        double[] weights = new double[] { 1.7, 4.2 };
        ThresholdedRandomCutForest first = ThresholdedRandomCutForest.builder().compact(true).dimensions(dimensions).randomSeed(0).numberOfTrees(numberOfTrees).shingleSize(shingleSize).sampleSize(sampleSize).internalShinglingEnabled(true).precision(precision).anomalyRate(0.01).forestMode(ForestMode.STANDARD).weightTime(0).transformMethod(transformMethod).normalizeTime(true).outputAfter(32).initialAcceptFraction(0.125).weights(weights).build();
        ThresholdedRandomCutForest second = ThresholdedRandomCutForest.builder().compact(true).dimensions(dimensions).randomSeed(0).numberOfTrees(numberOfTrees).shingleSize(shingleSize).sampleSize(sampleSize).internalShinglingEnabled(true).precision(precision).anomalyRate(0.01).forestMode(ForestMode.STREAMING_IMPUTE).weightTime(0).transformMethod(transformMethod).normalizeTime(true).outputAfter(32).initialAcceptFraction(0.125).weights(weights).build();
        // ensuring that the parameters are the same; otherwise the grades/scores cannot
        // be the same
        // weighTime has to be 0 in the above
        first.setLowerThreshold(1.1);
        second.setLowerThreshold(1.1);
        first.setHorizon(0.75);
        second.setHorizon(0.75);
        Random noise = new Random(0);
        // change the last argument seed for a different run
        MultiDimDataWithKey dataWithKeys = ShingledMultiDimDataWithKeys.getMultiDimData(dataSize + shingleSize - 1, 50, 100, 5, seed, baseDimensions);
        for (int j = 0; j < length; j++) {
            // gap has to be asymptotically same
            long timestamp = 100 * j + noise.nextInt(10) - 5;
            AnomalyDescriptor result = first.process(dataWithKeys.data[j], 0L);
            AnomalyDescriptor test = second.process(dataWithKeys.data[j], timestamp);
            assertEquals(result.getRCFScore(), test.getRCFScore(), 1e-6);
            assertEquals(result.getAnomalyGrade(), test.getAnomalyGrade(), 1e-6);
        }
        ThresholdedRandomCutForestMapper mapper = new ThresholdedRandomCutForestMapper();
        ThresholdedRandomCutForest third = mapper.toModel(mapper.toState(second));
        for (int j = length; j < 2 * length; j++) {
            // has to be the same gap
            long timestamp = 100 * j + noise.nextInt(10) - 5;
            AnomalyDescriptor firstResult = first.process(dataWithKeys.data[j], 0L);
            AnomalyDescriptor thirdResult = third.process(dataWithKeys.data[j], timestamp);
            assertEquals(firstResult.getRCFScore(), thirdResult.getRCFScore(), 1e-6);
            assertEquals(firstResult.getAnomalyGrade(), thirdResult.getAnomalyGrade(), 1e-6);
        }
    }
}