public OutColumn(Scalar <float> input, int confidence, int pvalueHistoryLength, AnomalySide side) : base(new Reconciler(confidence, pvalueHistoryLength, side), input) { Input = input; }
public Reconciler( int confidence, int pvalueHistoryLength, AnomalySide side) { _confidence = confidence; _pvalueHistoryLength = pvalueHistoryLength; _side = side; }
/// <summary> /// Perform SSA spike detection over a column of time series data. See <see cref="SsaSpikeEstimator"/>. /// </summary> public static Vector <double> SsaSpikeDetect( this Scalar <float> input, int confidence, int changeHistoryLength, int trainingWindowSize, int seasonalityWindowSize, AnomalySide side = AnomalySide.TwoSided, ErrorFunction errorFunction = ErrorFunction.SignedDifference ) => new OutColumn(input, confidence, changeHistoryLength, trainingWindowSize, seasonalityWindowSize, side, errorFunction);
public static IEstimator <ITransformer> _DetectIidSpike(this MLContext MLContext, JToken componentObject) { string outputColumn = componentObject.Value <string>("OutputColumnName"); string inputColumn = componentObject.Value <string>("InputColumnName"); int confidence = componentObject.Value <int>("Confidence"); int pValueHistory = componentObject.Value <int>("PvalueHistoryLength"); AnomalySide side = Enum.Parse <AnomalySide>(componentObject.Value <string>("AnomalySide")); return(MLContext.Transforms.DetectIidSpike(outputColumn, inputColumn, confidence, pValueHistory, side)); }
public OutColumn(Scalar <float> input, int confidence, int pvalueHistoryLength, int trainingWindowSize, int seasonalityWindowSize, AnomalySide side, ErrorFunction errorFunction) : base(new Reconciler(confidence, pvalueHistoryLength, trainingWindowSize, seasonalityWindowSize, side, errorFunction), input) { Input = input; }
public static IEstimator <ITransformer> _DetectSpikeBySsa(this MLContext MLContext, JToken componentObject) { string outputColumn = componentObject.Value <string>("OutputColumnName"); string inputColumn = componentObject.Value <string>("InputColumnName"); int confidence = componentObject.Value <int>("Confidence"); int pValueHistory = componentObject.Value <int>("PvalueHistoryLength"); int trainingWindow = componentObject.Value <int>("TrainingWindowSize"); int seasonalityWindow = componentObject.Value <int>("SeasonalityWindowSize"); AnomalySide side = Enum.Parse <AnomalySide>(componentObject.Value <string>("AnomalySide")); ErrorFunction errorFunction = Enum.Parse <ErrorFunction>(componentObject.Value <string>("ErrorFunction")); return(MLContext.Transforms.DetectSpikeBySsa(outputColumn, inputColumn, confidence, pValueHistory, trainingWindow, seasonalityWindow, side, errorFunction)); }
public Reconciler( int confidence, int pvalueHistoryLength, int trainingWindowSize, int seasonalityWindowSize, AnomalySide side, ErrorFunction errorFunction) { _confidence = confidence; _pvalueHistoryLength = pvalueHistoryLength; _trainingWindowSize = trainingWindowSize; _seasonalityWindowSize = seasonalityWindowSize; _side = side; _errorFunction = errorFunction; }
/// <summary> /// Create a new instance of <see cref="SsaSpikeEstimator"/> /// </summary> /// <param name="env">Host Environment.</param> /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param> /// <param name="confidence">The confidence for spike detection in the range [0, 100].</param> /// <param name="pvalueHistoryLength">The size of the sliding window for computing the p-value.</param> /// <param name="trainingWindowSize">The number of points from the beginning of the sequence used for training.</param> /// <param name="seasonalityWindowSize">An upper bound on the largest relevant seasonality in the input time-series.</param> /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source. /// The vector contains Alert, Raw Score, P-Value as first three values.</param> /// <param name="side">The argument that determines whether to detect positive or negative anomalies, or both.</param> /// <param name="errorFunction">The function used to compute the error between the expected and the observed value.</param> internal SsaSpikeEstimator(IHostEnvironment env, string outputColumnName, int confidence, int pvalueHistoryLength, int trainingWindowSize, int seasonalityWindowSize, string inputColumnName = null, AnomalySide side = AnomalySide.TwoSided, ErrorFunction errorFunction = ErrorFunction.SignedDifference) : this(env, new SsaSpikeDetector.Options { Source = inputColumnName ?? outputColumnName, Name = outputColumnName, Confidence = confidence, PvalueHistoryLength = pvalueHistoryLength, TrainingWindowSize = trainingWindowSize, SeasonalWindowSize = seasonalityWindowSize, Side = side, ErrorFunction = errorFunction }) { }
protected SequentialAnomalyDetectionTransformBase(IHostEnvironment env, ModelLoadContext ctx, string name, IDataView input) : base(env, ctx, name, input) { // *** Binary format *** // <base> // byte: _martingale // byte: _alertingScore // byte: _anomalySide // Double: _powerMartingaleEpsilon // Double: _alertThreshold byte temp; temp = ctx.Reader.ReadByte(); Host.CheckDecode(Enum.IsDefined(typeof(MartingaleType), temp)); Martingale = (MartingaleType)temp; temp = ctx.Reader.ReadByte(); Host.CheckDecode(Enum.IsDefined(typeof(AlertingScore), temp)); ThresholdScore = (AlertingScore)temp; Host.CheckDecode(Martingale != MartingaleType.None || ThresholdScore != AlertingScore.MartingaleScore); Host.CheckDecode(WindowSize > 0 || ThresholdScore == AlertingScore.RawScore); temp = ctx.Reader.ReadByte(); Host.CheckDecode(Enum.IsDefined(typeof(AnomalySide), temp)); Side = (AnomalySide)temp; PowerMartingaleEpsilon = ctx.Reader.ReadDouble(); Host.CheckDecode(0 < PowerMartingaleEpsilon && PowerMartingaleEpsilon < 1); AlertThreshold = ctx.Reader.ReadDouble(); Host.CheckDecode(AlertThreshold >= 0); Host.CheckDecode(ThresholdScore != AlertingScore.PValueScore || (0 <= AlertThreshold && AlertThreshold <= 1)); _outputLength = GetOutputLength(ThresholdScore, Host); _wrappedSchema = CreateSchema(base.Schema, OutputColumnName, _outputLength); }
private protected SequentialAnomalyDetectionTransformBase(int windowSize, int initialWindowSize, string inputColumnName, string outputColumnName, string name, IHostEnvironment env, AnomalySide anomalySide, MartingaleType martingale, AlertingScore alertingScore, Double powerMartingaleEpsilon, Double alertThreshold) : base(Contracts.CheckRef(env, nameof(env)).Register(name), windowSize, initialWindowSize, outputColumnName, inputColumnName, new VectorType(NumberDataViewType.Double, GetOutputLength(alertingScore, env))) { Host.CheckUserArg(Enum.IsDefined(typeof(MartingaleType), martingale), nameof(ArgumentsBase.Martingale), "Value is undefined."); Host.CheckUserArg(Enum.IsDefined(typeof(AnomalySide), anomalySide), nameof(ArgumentsBase.Side), "Value is undefined."); Host.CheckUserArg(Enum.IsDefined(typeof(AlertingScore), alertingScore), nameof(ArgumentsBase.AlertOn), "Value is undefined."); Host.CheckUserArg(martingale != MartingaleType.None || alertingScore != AlertingScore.MartingaleScore, nameof(ArgumentsBase.Martingale), "A martingale type should be specified if alerting is based on the martingale score."); Host.CheckUserArg(windowSize > 0 || alertingScore == AlertingScore.RawScore, nameof(ArgumentsBase.AlertOn), "When there is no windowed buffering (i.e., " + nameof(ArgumentsBase.WindowSize) + " = 0), the alert can be generated only based on the raw score (i.e., " + nameof(ArgumentsBase.AlertOn) + " = " + nameof(AlertingScore.RawScore) + ")"); Host.CheckUserArg(0 < powerMartingaleEpsilon && powerMartingaleEpsilon < 1, nameof(ArgumentsBase.PowerMartingaleEpsilon), "Should be in (0,1)."); Host.CheckUserArg(alertThreshold >= 0, nameof(ArgumentsBase.AlertThreshold), "Must be non-negative."); Host.CheckUserArg(alertingScore != AlertingScore.PValueScore || (0 <= alertThreshold && alertThreshold <= 1), nameof(ArgumentsBase.AlertThreshold), "Must be in [0,1]."); ThresholdScore = alertingScore; Side = anomalySide; Martingale = martingale; PowerMartingaleEpsilon = powerMartingaleEpsilon; AlertThreshold = alertThreshold; OutputLength = GetOutputLength(ThresholdScore, Host); }
private protected SequentialAnomalyDetectionTransformBase(IHostEnvironment env, ModelLoadContext ctx, string name) : base(Contracts.CheckRef(env, nameof(env)).Register(name), ctx) { // *** Binary format *** // <base> // byte: _martingale // byte: _alertingScore // byte: _anomalySide // Double: _powerMartingaleEpsilon // Double: _alertThreshold byte temp; temp = ctx.Reader.ReadByte(); Host.CheckDecode(Enum.IsDefined(typeof(MartingaleType), temp)); Martingale = (MartingaleType)temp; temp = ctx.Reader.ReadByte(); Host.CheckDecode(Enum.IsDefined(typeof(AlertingScore), temp)); ThresholdScore = (AlertingScore)temp; Host.CheckDecode(Martingale != MartingaleType.None || ThresholdScore != AlertingScore.MartingaleScore); Host.CheckDecode(WindowSize > 0 || ThresholdScore == AlertingScore.RawScore); temp = ctx.Reader.ReadByte(); Host.CheckDecode(Enum.IsDefined(typeof(AnomalySide), temp)); Side = (AnomalySide)temp; PowerMartingaleEpsilon = ctx.Reader.ReadDouble(); Host.CheckDecode(0 < PowerMartingaleEpsilon && PowerMartingaleEpsilon < 1); AlertThreshold = ctx.Reader.ReadDouble(); Host.CheckDecode(AlertThreshold >= 0); Host.CheckDecode(ThresholdScore != AlertingScore.PValueScore || (0 <= AlertThreshold && AlertThreshold <= 1)); OutputLength = GetOutputLength(ThresholdScore, Host); }
/// <summary> /// Create a new instance of <see cref="IidSpikeEstimator"/> /// </summary> /// <param name="env">Host Environment.</param> /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>. /// Column is a vector of type double and size 4. The vector contains Alert, Raw Score, P-Value as first three values.</param> /// <param name="confidence">The confidence for spike detection in the range [0, 100].</param> /// <param name="pvalueHistoryLength">The size of the sliding window for computing the p-value.</param> /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param> /// <param name="side">The argument that determines whether to detect positive or negative anomalies, or both.</param> internal IidSpikeEstimator(IHostEnvironment env, string outputColumnName, int confidence, int pvalueHistoryLength, string inputColumnName, AnomalySide side = AnomalySide.TwoSided) : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(IidSpikeDetector)), new IidSpikeDetector(env, new IidSpikeDetector.Options { Name = outputColumnName, Source = inputColumnName, Confidence = confidence, PvalueHistoryLength = pvalueHistoryLength, Side = side })) { }
/// <summary> /// Perform IID spike detection over a column of time series data. See <see cref="IidSpikeEstimator"/>. /// </summary> public static Vector <double> IidSpikeDetect( this Scalar <float> input, int confidence, int pvalueHistoryLength, AnomalySide side = AnomalySide.TwoSided ) => new OutColumn(input, confidence, pvalueHistoryLength, side);
/// <summary> /// Create <see cref="IidSpikeEstimator"/>, which predicts spikes in /// <a href="https://en.wikipedia.org/wiki/Independent_and_identically_distributed_random_variables"> independent identically distributed (i.i.d.)</a> /// time series based on adaptive kernel density estimations and martingale scores. /// </summary> /// <param name="catalog">The transform's catalog.</param> /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>. /// The column data is a vector of <see cref="System.Double"/>. The vector contains 3 elements: alert (non-zero value means a spike), raw score, and p-value.</param> /// <param name="inputColumnName">Name of column to transform. The column data must be <see cref="System.Single"/>. /// If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param> /// <param name="confidence">The confidence for spike detection in the range [0, 100].</param> /// <param name="pvalueHistoryLength">The size of the sliding window for computing the p-value.</param> /// <param name="side">The argument that determines whether to detect positive or negative anomalies, or both.</param> /// <example> /// <format type="text/markdown"> /// <![CDATA[ /// [!code-csharp[DetectIidSpike](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/TimeSeries/DetectIidSpikeBatchPrediction.cs)] /// ]]> /// </format> /// </example> public static IidSpikeEstimator DetectIidSpike(this TransformsCatalog catalog, string outputColumnName, string inputColumnName, int confidence, int pvalueHistoryLength, AnomalySide side = AnomalySide.TwoSided) => new IidSpikeEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, confidence, pvalueHistoryLength, inputColumnName, side);
/// <summary> /// Create <see cref="SsaSpikeEstimator"/>, which predicts spikes in time series /// using <a href="https://en.wikipedia.org/wiki/Singular_spectrum_analysis">Singular Spectrum Analysis (SSA)</a>. /// </summary> /// <param name="catalog">The transform's catalog.</param> /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>. /// The column data is a vector of <see cref="System.Double"/>. The vector contains 3 elements: alert (non-zero value means a spike), raw score, and p-value.</param> /// <param name="inputColumnName">Name of column to transform. The column data must be <see cref="System.Single"/>. /// If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param> /// <param name="confidence">The confidence for spike detection in the range [0, 100].</param> /// <param name="pvalueHistoryLength">The size of the sliding window for computing the p-value.</param> /// <param name="trainingWindowSize">The number of points from the beginning of the sequence used for training.</param> /// <param name="seasonalityWindowSize">An upper bound on the largest relevant seasonality in the input time-series.</param> /// <param name="side">The argument that determines whether to detect positive or negative anomalies, or both.</param> /// <param name="errorFunction">The function used to compute the error between the expected and the observed value.</param> /// <example> /// <format type="text/markdown"> /// <![CDATA[ /// [!code-csharp[DetectSpikeBySsa](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/TimeSeries/DetectSpikeBySsaBatchPrediction.cs)] /// ]]> /// </format> /// </example> public static SsaSpikeEstimator DetectSpikeBySsa(this TransformsCatalog catalog, string outputColumnName, string inputColumnName, int confidence, int pvalueHistoryLength, int trainingWindowSize, int seasonalityWindowSize, AnomalySide side = AnomalySide.TwoSided, ErrorFunction errorFunction = ErrorFunction.SignedDifference) => new SsaSpikeEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, confidence, pvalueHistoryLength, trainingWindowSize, seasonalityWindowSize, inputColumnName, side, errorFunction);
public static IidSpikeEstimator DetectIidSpike(this TransformsCatalog catalog, string outputColumnName, string inputColumnName, int confidence, int pvalueHistoryLength, AnomalySide side = AnomalySide.TwoSided) => DetectIidSpike(catalog, outputColumnName, inputColumnName, (double)confidence, pvalueHistoryLength, side);