Search in sources :

Example 1 with RandomCutForestMapper

use of com.amazon.randomcutforest.state.RandomCutForestMapper in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapper method toState.

@Override
public ThresholdedRandomCutForestState toState(ThresholdedRandomCutForest model) {
    ThresholdedRandomCutForestState state = new ThresholdedRandomCutForestState();
    RandomCutForestMapper randomCutForestMapper = new RandomCutForestMapper();
    randomCutForestMapper.setPartialTreeStateEnabled(true);
    randomCutForestMapper.setSaveTreeStateEnabled(true);
    randomCutForestMapper.setCompressionEnabled(true);
    randomCutForestMapper.setSaveCoordinatorStateEnabled(true);
    randomCutForestMapper.setSaveExecutorContextEnabled(true);
    state.setForestState(randomCutForestMapper.toState(model.getForest()));
    BasicThresholderMapper thresholderMapper = new BasicThresholderMapper();
    state.setThresholderState(thresholderMapper.toState(model.getThresholder()));
    PreprocessorMapper preprocessorMapper = new PreprocessorMapper();
    state.setPreprocessorStates(new PreprocessorState[] { preprocessorMapper.toState((Preprocessor) model.getPreprocessor()) });
    state.setTriggerFactor(model.getPredictorCorrector().getTriggerFactor());
    state.setIgnoreSimilar(model.getPredictorCorrector().isIgnoreSimilar());
    state.setIgnoreSimilarFactor(model.getPredictorCorrector().getIgnoreSimilarFactor());
    state.setNumberOfAttributors(model.getPredictorCorrector().getNumberOfAttributors());
    state.setForestMode(model.getForestMode().name());
    state.setTransformMethod(model.getTransformMethod().name());
    IRCFComputeDescriptor descriptor = model.getLastAnomalyDescriptor();
    state.setLastAnomalyTimeStamp(descriptor.getInternalTimeStamp());
    state.setLastAnomalyScore(descriptor.getRCFScore());
    state.setLastAnomalyAttribution(new DiVectorMapper().toState(descriptor.getAttribution()));
    state.setLastAnomalyPoint(descriptor.getRCFPoint());
    state.setLastExpectedPoint(descriptor.getExpectedRCFPoint());
    state.setLastRelativeIndex(descriptor.getRelativeIndex());
    return state;
}
Also used : IRCFComputeDescriptor(com.amazon.randomcutforest.parkservices.IRCFComputeDescriptor) BasicThresholderMapper(com.amazon.randomcutforest.parkservices.state.threshold.BasicThresholderMapper) RandomCutForestMapper(com.amazon.randomcutforest.state.RandomCutForestMapper) DiVectorMapper(com.amazon.randomcutforest.state.returntypes.DiVectorMapper) Preprocessor(com.amazon.randomcutforest.parkservices.preprocessor.Preprocessor) PreprocessorMapper(com.amazon.randomcutforest.parkservices.state.preprocessor.PreprocessorMapper)

Example 2 with RandomCutForestMapper

use of com.amazon.randomcutforest.state.RandomCutForestMapper 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);
        }
    }
}
Also used : Random(java.util.Random) AnomalyDescriptor(com.amazon.randomcutforest.parkservices.AnomalyDescriptor) RandomCutForest(com.amazon.randomcutforest.RandomCutForest) ThresholdedRandomCutForest(com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest) RandomCutForestMapper(com.amazon.randomcutforest.state.RandomCutForestMapper) ThresholdedRandomCutForest(com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest) Test(org.junit.jupiter.api.Test) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest)

Example 3 with RandomCutForestMapper

use of com.amazon.randomcutforest.state.RandomCutForestMapper in project random-cut-forest-by-aws by aws.

the class ProtostuffExampleWithDynamicLambda method run.

@Override
public void run() throws Exception {
    // Create and populate a random cut forest
    int dimensions = 4;
    int numberOfTrees = 50;
    int sampleSize = 256;
    Precision precision = Precision.FLOAT_64;
    RandomCutForest forest = RandomCutForest.builder().compact(true).dimensions(dimensions).numberOfTrees(numberOfTrees).sampleSize(sampleSize).precision(precision).build();
    int dataSize = 4 * sampleSize;
    NormalMixtureTestData testData = new NormalMixtureTestData();
    for (double[] point : testData.generateTestData(dataSize, dimensions)) {
        forest.update(point);
    }
    // Convert to an array of bytes and print the size
    RandomCutForestMapper mapper = new RandomCutForestMapper();
    mapper.setSaveExecutorContextEnabled(true);
    Schema<RandomCutForestState> schema = RuntimeSchema.getSchema(RandomCutForestState.class);
    LinkedBuffer buffer = LinkedBuffer.allocate(512);
    byte[] bytes;
    try {
        RandomCutForestState state = mapper.toState(forest);
        bytes = ProtostuffIOUtil.toByteArray(state, schema, buffer);
    } finally {
        buffer.clear();
    }
    System.out.printf("dimensions = %d, numberOfTrees = %d, sampleSize = %d, precision = %s%n", dimensions, numberOfTrees, sampleSize, precision);
    System.out.printf("protostuff size = %d bytes%n", bytes.length);
    // Restore from protostuff and compare anomaly scores produced by the two
    // forests
    RandomCutForestState state2 = schema.newMessage();
    ProtostuffIOUtil.mergeFrom(bytes, state2, schema);
    RandomCutForest forest2 = mapper.toModel(state2);
    double saveLambda = forest.getTimeDecay();
    forest.setTimeDecay(10 * forest.getTimeDecay());
    forest2.setTimeDecay(10 * forest2.getTimeDecay());
    for (int i = 0; i < numberOfTrees; i++) {
        CompactSampler sampler = (CompactSampler) ((SamplerPlusTree) forest.getComponents().get(i)).getSampler();
        CompactSampler sampler2 = (CompactSampler) ((SamplerPlusTree) forest2.getComponents().get(i)).getSampler();
        if (sampler.getMaxSequenceIndex() != sampler2.getMaxSequenceIndex()) {
            throw new IllegalStateException("Incorrect sampler state");
        }
        if (sampler.getMostRecentTimeDecayUpdate() != sampler2.getMostRecentTimeDecayUpdate()) {
            throw new IllegalStateException("Incorrect sampler state");
        }
        if (sampler2.getMostRecentTimeDecayUpdate() != dataSize - 1) {
            throw new IllegalStateException("Incorrect sampler state");
        }
    }
    int testSize = 100;
    double delta = Math.log(sampleSize) / Math.log(2) * 0.05;
    int differences = 0;
    int anomalies = 0;
    for (double[] point : testData.generateTestData(testSize, dimensions)) {
        double score = forest.getAnomalyScore(point);
        double score2 = forest2.getAnomalyScore(point);
        // also scored as an anomaly by the other forest
        if (score > 1 || score2 > 1) {
            anomalies++;
            if (Math.abs(score - score2) > delta) {
                differences++;
            }
        }
        forest.update(point);
        forest2.update(point);
    }
    // first validate that this was a nontrivial test
    if (anomalies == 0) {
        throw new IllegalStateException("test data did not produce any anomalies");
    }
    // validate that the two forests agree on anomaly scores
    if (differences >= 0.01 * testSize) {
        throw new IllegalStateException("restored forest does not agree with original forest");
    }
    System.out.println("Looks good!");
}
Also used : LinkedBuffer(io.protostuff.LinkedBuffer) CompactSampler(com.amazon.randomcutforest.sampler.CompactSampler) RandomCutForest(com.amazon.randomcutforest.RandomCutForest) RandomCutForestState(com.amazon.randomcutforest.state.RandomCutForestState) Precision(com.amazon.randomcutforest.config.Precision) RandomCutForestMapper(com.amazon.randomcutforest.state.RandomCutForestMapper) NormalMixtureTestData(com.amazon.randomcutforest.testutils.NormalMixtureTestData)

Example 4 with RandomCutForestMapper

use of com.amazon.randomcutforest.state.RandomCutForestMapper in project random-cut-forest-by-aws by aws.

the class JsonExample method run.

@Override
public void run() throws Exception {
    // Create and populate a random cut forest
    int dimensions = 4;
    int numberOfTrees = 50;
    int sampleSize = 256;
    Precision precision = Precision.FLOAT_64;
    RandomCutForest forest = RandomCutForest.builder().compact(true).dimensions(dimensions).numberOfTrees(numberOfTrees).sampleSize(sampleSize).precision(precision).build();
    int dataSize = 4 * sampleSize;
    NormalMixtureTestData testData = new NormalMixtureTestData();
    for (double[] point : testData.generateTestData(dataSize, dimensions)) {
        forest.update(point);
    }
    // Convert to JSON and print the number of bytes
    RandomCutForestMapper mapper = new RandomCutForestMapper();
    mapper.setSaveExecutorContextEnabled(true);
    ObjectMapper jsonMapper = new ObjectMapper();
    String json = jsonMapper.writeValueAsString(mapper.toState(forest));
    System.out.printf("dimensions = %d, numberOfTrees = %d, sampleSize = %d, precision = %s%n", dimensions, numberOfTrees, sampleSize, precision);
    System.out.printf("JSON size = %d bytes%n", json.getBytes().length);
    // Restore from JSON and compare anomaly scores produced by the two forests
    RandomCutForest forest2 = mapper.toModel(jsonMapper.readValue(json, RandomCutForestState.class));
    int testSize = 100;
    double delta = Math.log(sampleSize) / Math.log(2) * 0.05;
    int differences = 0;
    int anomalies = 0;
    for (double[] point : testData.generateTestData(testSize, dimensions)) {
        double score = forest.getAnomalyScore(point);
        double score2 = forest2.getAnomalyScore(point);
        // also scored as an anomaly by the other forest
        if (score > 1 || score2 > 1) {
            anomalies++;
            if (Math.abs(score - score2) > delta) {
                differences++;
            }
        }
        forest.update(point);
        forest2.update(point);
    }
    // first validate that this was a nontrivial test
    if (anomalies == 0) {
        throw new IllegalStateException("test data did not produce any anomalies");
    }
    // validate that the two forests agree on anomaly scores
    if (differences >= 0.01 * testSize) {
        throw new IllegalStateException("restored forest does not agree with original forest");
    }
    System.out.println("Looks good!");
}
Also used : Precision(com.amazon.randomcutforest.config.Precision) RandomCutForest(com.amazon.randomcutforest.RandomCutForest) RandomCutForestMapper(com.amazon.randomcutforest.state.RandomCutForestMapper) NormalMixtureTestData(com.amazon.randomcutforest.testutils.NormalMixtureTestData) RandomCutForestState(com.amazon.randomcutforest.state.RandomCutForestState) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper)

Example 5 with RandomCutForestMapper

use of com.amazon.randomcutforest.state.RandomCutForestMapper in project random-cut-forest-by-aws by aws.

the class ProtostuffExample method run.

@Override
public void run() throws Exception {
    // Create and populate a random cut forest
    int dimensions = 10;
    int numberOfTrees = 50;
    int sampleSize = 256;
    Precision precision = Precision.FLOAT_32;
    RandomCutForest forest = RandomCutForest.builder().compact(true).dimensions(dimensions).numberOfTrees(numberOfTrees).sampleSize(sampleSize).precision(precision).build();
    int dataSize = 1000 * sampleSize;
    NormalMixtureTestData testData = new NormalMixtureTestData();
    for (double[] point : testData.generateTestData(dataSize, dimensions)) {
        forest.update(point);
    }
    // Convert to an array of bytes and print the size
    RandomCutForestMapper mapper = new RandomCutForestMapper();
    mapper.setSaveExecutorContextEnabled(true);
    Schema<RandomCutForestState> schema = RuntimeSchema.getSchema(RandomCutForestState.class);
    LinkedBuffer buffer = LinkedBuffer.allocate(512);
    byte[] bytes;
    try {
        RandomCutForestState state = mapper.toState(forest);
        bytes = ProtostuffIOUtil.toByteArray(state, schema, buffer);
    } finally {
        buffer.clear();
    }
    System.out.printf("dimensions = %d, numberOfTrees = %d, sampleSize = %d, precision = %s%n", dimensions, numberOfTrees, sampleSize, precision);
    System.out.printf("protostuff size = %d bytes%n", bytes.length);
    // Restore from protostuff and compare anomaly scores produced by the two
    // forests
    RandomCutForestState state2 = schema.newMessage();
    ProtostuffIOUtil.mergeFrom(bytes, state2, schema);
    RandomCutForest forest2 = mapper.toModel(state2);
    int testSize = 100;
    double delta = Math.log(sampleSize) / Math.log(2) * 0.05;
    int differences = 0;
    int anomalies = 0;
    for (double[] point : testData.generateTestData(testSize, dimensions)) {
        double score = forest.getAnomalyScore(point);
        double score2 = forest2.getAnomalyScore(point);
        // also scored as an anomaly by the other forest
        if (score > 1 || score2 > 1) {
            anomalies++;
            if (Math.abs(score - score2) > delta) {
                differences++;
            }
        }
        forest.update(point);
        forest2.update(point);
    }
    // first validate that this was a nontrivial test
    if (anomalies == 0) {
        throw new IllegalStateException("test data did not produce any anomalies");
    }
    // validate that the two forests agree on anomaly scores
    if (differences >= 0.01 * testSize) {
        throw new IllegalStateException("restored forest does not agree with original forest");
    }
    System.out.println("Looks good!");
}
Also used : LinkedBuffer(io.protostuff.LinkedBuffer) Precision(com.amazon.randomcutforest.config.Precision) RandomCutForest(com.amazon.randomcutforest.RandomCutForest) RandomCutForestMapper(com.amazon.randomcutforest.state.RandomCutForestMapper) NormalMixtureTestData(com.amazon.randomcutforest.testutils.NormalMixtureTestData) RandomCutForestState(com.amazon.randomcutforest.state.RandomCutForestState)

Aggregations

RandomCutForestMapper (com.amazon.randomcutforest.state.RandomCutForestMapper)21 RandomCutForestState (com.amazon.randomcutforest.state.RandomCutForestState)15 RandomCutForest (com.amazon.randomcutforest.RandomCutForest)10 Precision (com.amazon.randomcutforest.config.Precision)6 Benchmark (org.openjdk.jmh.annotations.Benchmark)6 OperationsPerInvocation (org.openjdk.jmh.annotations.OperationsPerInvocation)6 NormalMixtureTestData (com.amazon.randomcutforest.testutils.NormalMixtureTestData)5 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)5 LinkedBuffer (io.protostuff.LinkedBuffer)5 Random (java.util.Random)5 Test (org.junit.jupiter.api.Test)4 ParameterizedTest (org.junit.jupiter.params.ParameterizedTest)4 IRCFComputeDescriptor (com.amazon.randomcutforest.parkservices.IRCFComputeDescriptor)2 ThresholdedRandomCutForest (com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest)2 Preprocessor (com.amazon.randomcutforest.parkservices.preprocessor.Preprocessor)2 PreprocessorMapper (com.amazon.randomcutforest.parkservices.state.preprocessor.PreprocessorMapper)2 BasicThresholderMapper (com.amazon.randomcutforest.parkservices.state.threshold.BasicThresholderMapper)2 DiVectorMapper (com.amazon.randomcutforest.state.returntypes.DiVectorMapper)2 BufferedReader (java.io.BufferedReader)2 IOException (java.io.IOException)2