TimeSeriesCatalog.DetectIidSpike 方法

定義

命名空間:: Microsoft.ML

組件:: Microsoft.ML.TimeSeries.dll

套件:: Microsoft.ML.TimeSeries v4.0.1

套件:: Microsoft.ML.TimeSeries v1.5.5

套件:: Microsoft.ML.TimeSeries v1.6.0

套件:: Microsoft.ML.TimeSeries v1.7.0

套件:: Microsoft.ML.TimeSeries v2.0.1

套件:: Microsoft.ML.TimeSeries v3.0.1

套件:: Microsoft.ML.TimeSeries v5.0.0-preview.1.25125.4

套件:: Microsoft.ML.TimeSeries v1.2.0

套件:: Microsoft.ML.TimeSeries v1.3.1

套件:: Microsoft.ML.TimeSeries v1.4.0

重要

部分資訊涉及發行前產品，在發行之前可能會有大幅修改。 Microsoft 對此處提供的資訊，不做任何明確或隱含的瑕疵擔保。

多載

名稱	Description
DetectIidSpike(TransformsCatalog, String, String, Double, Int32, AnomalySide)	Create IidSpikeEstimator，根據自適應核密度估計與馬丁格爾分數，預測獨立同分布（i.i.d.）時間序列中的尖峰。
DetectIidSpike(TransformsCatalog, String, String, Int32, Int32, AnomalySide)	已淘汰. Create IidSpikeEstimator，根據自適應核密度估計與馬丁格爾分數，預測獨立同分布（i.i.d.）時間序列中的尖峰。

DetectIidSpike(TransformsCatalog, String, String, Double, Int32, AnomalySide)

來源:: ExtensionsCatalog.cs

來源:: ExtensionsCatalog.cs

來源:: ExtensionsCatalog.cs

Create IidSpikeEstimator，根據自適應核密度估計與馬丁格爾分數，預測獨立同分布（i.i.d.）時間序列中的尖峰。

public static Microsoft.ML.Transforms.TimeSeries.IidSpikeEstimator DetectIidSpike(this Microsoft.ML.TransformsCatalog catalog, string outputColumnName, string inputColumnName, double confidence, int pvalueHistoryLength, Microsoft.ML.Transforms.TimeSeries.AnomalySide side = Microsoft.ML.Transforms.TimeSeries.AnomalySide.TwoSided);

static member DetectIidSpike : Microsoft.ML.TransformsCatalog * string * string * double * int * Microsoft.ML.Transforms.TimeSeries.AnomalySide -> Microsoft.ML.Transforms.TimeSeries.IidSpikeEstimator

<Extension()>
Public Function DetectIidSpike (catalog As TransformsCatalog, outputColumnName As String, inputColumnName As String, confidence As Double, pvalueHistoryLength As Integer, Optional side As AnomalySide = Microsoft.ML.Transforms.TimeSeries.AnomalySide.TwoSided) As IidSpikeEstimator

參數

catalog: TransformsCatalog

變身者的目錄。

outputColumnName: String

由轉換 inputColumnName所得欄位名稱。欄位資料是的 Double向量。向量包含三個元素：警示（非零值表示峰值）、原始分數和 p 值。

inputColumnName: String

要變換的欄位名稱。欄位資料必須為 Single。若設為 null，則的值 outputColumnName 將作為來源。

confidence: Double

在 [0， 100] 範圍內偵測尖峰的信心度。

pvalueHistoryLength: Int32

計算 p 值的滑動視窗大小。

side: AnomalySide

決定是偵測正面或負面異常，或兩者兼具的論證。

傳回

IidSpikeEstimator

範例

using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic
{
    public static class DetectIidSpikeBatchPrediction
    {
        // This example creates a time series (list of Data with the i-th element
        // corresponding to the i-th time slot). The estimator is applied then to
        // identify spiking points in the series.
        public static void Example()
        {
            // Create a new ML context, for ML.NET operations. It can be used for
            // exception tracking and logging, as well as the source of randomness.
            var ml = new MLContext();

            // Generate sample series data with a spike
            const int Size = 10;
            var data = new List<TimeSeriesData>(Size + 1)
            {
                new TimeSeriesData(5),
                new TimeSeriesData(5),
                new TimeSeriesData(5),
                new TimeSeriesData(5),
                new TimeSeriesData(5),

                // This is a spike.
                new TimeSeriesData(10),

                new TimeSeriesData(5),
                new TimeSeriesData(5),
                new TimeSeriesData(5),
                new TimeSeriesData(5),
                new TimeSeriesData(5),
            };

            // Convert data to IDataView.
            var dataView = ml.Data.LoadFromEnumerable(data);

            // Setup the estimator arguments
            string outputColumnName = nameof(IidSpikePrediction.Prediction);
            string inputColumnName = nameof(TimeSeriesData.Value);

            // The transformed data.
            var transformedData = ml.Transforms.DetectIidSpike(outputColumnName,
                inputColumnName, 95.0d, Size / 4).Fit(dataView).Transform(dataView);

            // Getting the data of the newly created column as an IEnumerable of
            // IidSpikePrediction.
            var predictionColumn = ml.Data.CreateEnumerable<IidSpikePrediction>(
                transformedData, reuseRowObject: false);

            Console.WriteLine($"{outputColumnName} column obtained " +
                $"post-transformation.");

            Console.WriteLine("Data\tAlert\tScore\tP-Value");

            int k = 0;
            foreach (var prediction in predictionColumn)
                PrintPrediction(data[k++].Value, prediction);

            // Prediction column obtained post-transformation.
            // Data    Alert   Score P-Value
            // 5       0       5.00    0.50
            // 5       0       5.00    0.50
            // 5       0       5.00    0.50
            // 5       0       5.00    0.50
            // 5       0       5.00    0.50
            // 10      1       10.00   0.00   <-- alert is on, predicted spike
            // 5       0       5.00    0.26
            // 5       0       5.00    0.26
            // 5       0       5.00    0.50
            // 5       0       5.00    0.50
            // 5       0       5.00    0.50
        }

        private static void PrintPrediction(float value, IidSpikePrediction
            prediction) =>
            Console.WriteLine("{0}\t{1}\t{2:0.00}\t{3:0.00}", value,
            prediction.Prediction[0], prediction.Prediction[1],
            prediction.Prediction[2]);

        class TimeSeriesData
        {
            public float Value;

            public TimeSeriesData(float value)
            {
                Value = value;
            }
        }

        class IidSpikePrediction
        {
            [VectorType(3)]
            public double[] Prediction { get; set; }
        }
    }
}

適用於

DetectIidSpike(TransformsCatalog, String, String, Int32, Int32, AnomalySide)

來源:: ExtensionsCatalog.cs

來源:: ExtensionsCatalog.cs

來源:: ExtensionsCatalog.cs

警告

This API method is deprecated, please use the overload with confidence parameter of type double.