Search in sources :

Example 1 with TransformMethod

use of com.amazon.randomcutforest.config.TransformMethod 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;
    }
}
Also used : Random(java.util.Random) Precision(com.amazon.randomcutforest.config.Precision) AnomalyDescriptor(com.amazon.randomcutforest.parkservices.AnomalyDescriptor) MultiDimDataWithKey(com.amazon.randomcutforest.testutils.MultiDimDataWithKey) TransformMethod(com.amazon.randomcutforest.config.TransformMethod) ThresholdedRandomCutForest(com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest)

Example 2 with TransformMethod

use of com.amazon.randomcutforest.config.TransformMethod in project random-cut-forest-by-aws by aws.

the class ThresholdedRandomCutForestMapper method toModel.

@Override
public ThresholdedRandomCutForest toModel(ThresholdedRandomCutForestState state, long seed) {
    RandomCutForestMapper randomCutForestMapper = new RandomCutForestMapper();
    BasicThresholderMapper thresholderMapper = new BasicThresholderMapper();
    PreprocessorMapper preprocessorMapper = new PreprocessorMapper();
    RandomCutForest forest = randomCutForestMapper.toModel(state.getForestState());
    BasicThresholder thresholder = thresholderMapper.toModel(state.getThresholderState());
    Preprocessor preprocessor = preprocessorMapper.toModel(state.getPreprocessorStates()[0]);
    ForestMode forestMode = ForestMode.valueOf(state.getForestMode());
    TransformMethod transformMethod = TransformMethod.valueOf(state.getTransformMethod());
    RCFComputeDescriptor descriptor = new RCFComputeDescriptor(null, 0L);
    descriptor.setRCFScore(state.getLastAnomalyScore());
    descriptor.setInternalTimeStamp(state.getLastAnomalyTimeStamp());
    descriptor.setAttribution(new DiVectorMapper().toModel(state.getLastAnomalyAttribution()));
    descriptor.setRCFPoint(state.getLastAnomalyPoint());
    descriptor.setExpectedRCFPoint(state.getLastExpectedPoint());
    descriptor.setRelativeIndex(state.getLastRelativeIndex());
    descriptor.setForestMode(forestMode);
    descriptor.setTransformMethod(transformMethod);
    descriptor.setImputationMethod(ImputationMethod.valueOf(state.getPreprocessorStates()[0].getImputationMethod()));
    PredictorCorrector predictorCorrector = new PredictorCorrector(thresholder);
    predictorCorrector.setIgnoreSimilar(state.isIgnoreSimilar());
    predictorCorrector.setIgnoreSimilarFactor(state.getIgnoreSimilarFactor());
    predictorCorrector.setTriggerFactor(state.getTriggerFactor());
    predictorCorrector.setNumberOfAttributors(state.getNumberOfAttributors());
    return new ThresholdedRandomCutForest(forestMode, transformMethod, forest, predictorCorrector, preprocessor, descriptor);
}
Also used : ForestMode(com.amazon.randomcutforest.config.ForestMode) BasicThresholderMapper(com.amazon.randomcutforest.parkservices.state.threshold.BasicThresholderMapper) PredictorCorrector(com.amazon.randomcutforest.parkservices.PredictorCorrector) RandomCutForestMapper(com.amazon.randomcutforest.state.RandomCutForestMapper) RandomCutForest(com.amazon.randomcutforest.RandomCutForest) ThresholdedRandomCutForest(com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest) DiVectorMapper(com.amazon.randomcutforest.state.returntypes.DiVectorMapper) Preprocessor(com.amazon.randomcutforest.parkservices.preprocessor.Preprocessor) PreprocessorMapper(com.amazon.randomcutforest.parkservices.state.preprocessor.PreprocessorMapper) TransformMethod(com.amazon.randomcutforest.config.TransformMethod) IRCFComputeDescriptor(com.amazon.randomcutforest.parkservices.IRCFComputeDescriptor) RCFComputeDescriptor(com.amazon.randomcutforest.parkservices.RCFComputeDescriptor) BasicThresholder(com.amazon.randomcutforest.parkservices.threshold.BasicThresholder) ThresholdedRandomCutForest(com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest)

Example 3 with TransformMethod

use of com.amazon.randomcutforest.config.TransformMethod in project random-cut-forest-by-aws by aws.

the class PredictorCorrector method applyBasicCorrector.

/**
 * a first stage corrector that attempts to fix the after effects of a previous
 * anomaly which may be in the shingle, or just preceding the shingle
 *
 * @param point          the current (transformed) point under evaluation
 * @param gap            the relative position of the previous anomaly being
 *                       corrected
 * @param shingleSize    size of the shingle
 * @param baseDimensions number of dimensions in each shingle
 * @return the score of the corrected point
 */
double[] applyBasicCorrector(double[] point, int gap, int shingleSize, int baseDimensions, IRCFComputeDescriptor lastAnomalyDescriptor) {
    checkArgument(gap >= 0 && gap <= shingleSize, "incorrect invocation");
    double[] correctedPoint = Arrays.copyOf(point, point.length);
    double[] lastExpectedPoint = lastAnomalyDescriptor.getExpectedRCFPoint();
    double[] lastAnomalyPoint = lastAnomalyDescriptor.getRCFPoint();
    int lastRelativeIndex = lastAnomalyDescriptor.getRelativeIndex();
    if (gap < shingleSize) {
        System.arraycopy(lastExpectedPoint, gap * baseDimensions, correctedPoint, 0, point.length - gap * baseDimensions);
    }
    if (lastRelativeIndex == 0) {
        // is is possible to fix other cases, but is more complicated
        TransformMethod transformMethod = lastAnomalyDescriptor.getTransformMethod();
        if (transformMethod == TransformMethod.DIFFERENCE || transformMethod == TransformMethod.NORMALIZE_DIFFERENCE) {
            for (int y = 0; y < baseDimensions; y++) {
                correctedPoint[point.length - gap * baseDimensions + y] += lastAnomalyPoint[point.length - baseDimensions + y] - lastExpectedPoint[point.length - baseDimensions + y];
            }
        } else if (lastAnomalyDescriptor.getForestMode() == ForestMode.TIME_AUGMENTED) {
            // definitely correct the time dimension which is always differenced
            // this applies to the non-differenced cases
            correctedPoint[point.length - (gap - 1) * baseDimensions - 1] += lastAnomalyPoint[point.length - 1] - lastExpectedPoint[point.length - 1];
        }
    }
    return correctedPoint;
}
Also used : TransformMethod(com.amazon.randomcutforest.config.TransformMethod)

Aggregations

TransformMethod (com.amazon.randomcutforest.config.TransformMethod)3 ThresholdedRandomCutForest (com.amazon.randomcutforest.parkservices.ThresholdedRandomCutForest)2 RandomCutForest (com.amazon.randomcutforest.RandomCutForest)1 ForestMode (com.amazon.randomcutforest.config.ForestMode)1 Precision (com.amazon.randomcutforest.config.Precision)1 AnomalyDescriptor (com.amazon.randomcutforest.parkservices.AnomalyDescriptor)1 IRCFComputeDescriptor (com.amazon.randomcutforest.parkservices.IRCFComputeDescriptor)1 PredictorCorrector (com.amazon.randomcutforest.parkservices.PredictorCorrector)1 RCFComputeDescriptor (com.amazon.randomcutforest.parkservices.RCFComputeDescriptor)1 Preprocessor (com.amazon.randomcutforest.parkservices.preprocessor.Preprocessor)1 PreprocessorMapper (com.amazon.randomcutforest.parkservices.state.preprocessor.PreprocessorMapper)1 BasicThresholderMapper (com.amazon.randomcutforest.parkservices.state.threshold.BasicThresholderMapper)1 BasicThresholder (com.amazon.randomcutforest.parkservices.threshold.BasicThresholder)1 RandomCutForestMapper (com.amazon.randomcutforest.state.RandomCutForestMapper)1 DiVectorMapper (com.amazon.randomcutforest.state.returntypes.DiVectorMapper)1 MultiDimDataWithKey (com.amazon.randomcutforest.testutils.MultiDimDataWithKey)1 Random (java.util.Random)1