public SrCnnEntireModeler(double threshold, double sensitivity, SrCnnDetectMode detectMode)
{
_threshold = threshold;
_sensitivity = sensitivity;
_detectMode = detectMode;
_predictArray = new double[_lookaheadWindowSize + 1];
}
public SrCnnEntireAnomalyDetector(IHostEnvironment env, IDataView input, string inputColumnName, string outputColumnName, double threshold, int batchSize, double sensitivity, SrCnnDetectMode detectMode)
: base(env, nameof(SrCnnEntireAnomalyDetector), input)
{
Host.CheckValue(inputColumnName, nameof(inputColumnName));
_inputColumnName = inputColumnName;
Host.CheckUserArg(batchSize == -1 || batchSize >= MinBatchSize, nameof(batchSize), "BatchSize must be -1 or no less than 12.");
_batchSize = batchSize;
Host.CheckUserArg(threshold >= 0 && threshold <= 1, nameof(threshold), "Must be in [0,1].");
Host.CheckUserArg(detectMode == SrCnnDetectMode.AnomalyOnly ||
detectMode == SrCnnDetectMode.AnomalyAndExpectedValue ||
detectMode == SrCnnDetectMode.AnomalyAndMargin, nameof(detectMode), "Invalid detectMode");
Host.CheckUserArg(sensitivity >= 0 && sensitivity <= 100, nameof(sensitivity), "Must be in [0,100].");
_outputLength = _outputLengthArray[(int)detectMode];
_threshold = threshold;
_sensitivity = sensitivity;
_detectMode = detectMode;
_bindings = new Bindings(input.Schema, inputColumnName, outputColumnName, new VectorDataViewType(NumberDataViewType.Double, _outputLength));
}
public SrCnnEntireModeler(double threshold, double sensitivity, SrCnnDetectMode detectMode, int period, SrCnnDeseasonalityMode deseasonalityMode)
{
_threshold = threshold;
_sensitivity = sensitivity;
_detectMode = detectMode;
_period = period;
_predictArray = new double[_lookaheadWindowSize + 1];
switch (deseasonalityMode)
{
case SrCnnDeseasonalityMode.Stl:
_deseasonalityFunction = new StlDeseasonality();
break;
case SrCnnDeseasonalityMode.Mean:
_deseasonalityFunction = new MeanDeseasonality();
break;
default:
Contracts.Assert(deseasonalityMode == SrCnnDeseasonalityMode.Median);
_deseasonalityFunction = new MedianDeseasonality();
break;
}
}
public void TestSrCnnBatchAnomalyDetector(
[CombinatorialValues(SrCnnDetectMode.AnomalyOnly, SrCnnDetectMode.AnomalyAndExpectedValue, SrCnnDetectMode.AnomalyAndMargin)] SrCnnDetectMode mode,
[CombinatorialValues(true, false)] bool loadDataFromFile,
[CombinatorialValues(-1, 24, 26, 512)] int batchSize)
{
var ml = new MLContext(1);
IDataView dataView;
if (loadDataFromFile)
{
var dataPath = GetDataPath("Timeseries", "anomaly_detection.csv");
// Load data from file into the dataView
dataView = ml.Data.LoadFromTextFile <TimeSeriesDataDouble>(dataPath, hasHeader: true);
}
else
{
// Generate sample series data with an anomaly
var data = new List <TimeSeriesDataDouble>();
for (int index = 0; index < 20; index++)
{
data.Add(new TimeSeriesDataDouble {
Value = 5
});
}
data.Add(new TimeSeriesDataDouble {
Value = 10
});
for (int index = 0; index < 5; index++)
{
data.Add(new TimeSeriesDataDouble {
Value = 5
});
}
// Convert data to IDataView.
dataView = ml.Data.LoadFromEnumerable(data);
}
// Setup the detection arguments
string outputColumnName = nameof(SrCnnAnomalyDetection.Prediction);
string inputColumnName = nameof(TimeSeriesDataDouble.Value);
// Do batch anomaly detection
var outputDataView = ml.AnomalyDetection.DetectEntireAnomalyBySrCnn(dataView, outputColumnName, inputColumnName,
threshold: 0.35, batchSize: batchSize, sensitivity: 90.0, mode);
// Getting the data of the newly created column as an IEnumerable of
// SrCnnAnomalyDetection.
var predictionColumn = ml.Data.CreateEnumerable <SrCnnAnomalyDetection>(
outputDataView, reuseRowObject: false);
int k = 0;
foreach (var prediction in predictionColumn)
{
switch (mode)
{
case SrCnnDetectMode.AnomalyOnly:
Assert.Equal(3, prediction.Prediction.Length);
if (k == 20)
{
Assert.Equal(1, prediction.Prediction[0]);
}
else
{
Assert.Equal(0, prediction.Prediction[0]);
}
break;
case SrCnnDetectMode.AnomalyAndExpectedValue:
Assert.Equal(4, prediction.Prediction.Length);
if (k == 20)
{
Assert.Equal(1, prediction.Prediction[0]);
Assert.Equal(5.00, prediction.Prediction[3], 2);
}
else
{
Assert.Equal(0, prediction.Prediction[0]);
}
break;
case SrCnnDetectMode.AnomalyAndMargin:
Assert.Equal(7, prediction.Prediction.Length);
if (k == 20)
{
Assert.Equal(1, prediction.Prediction[0]);
Assert.Equal(5.00, prediction.Prediction[3], 2);
Assert.Equal(5.00, prediction.Prediction[4], 2);
Assert.Equal(5.01, prediction.Prediction[5], 2);
Assert.Equal(4.99, prediction.Prediction[6], 2);
}
else
{
Assert.Equal(0, prediction.Prediction[0]);
}
break;
}
k += 1;
}
}
public Batch(int batchSize, int outputLength, double threshold, double sensitivity, SrCnnDetectMode detectMode)
{
_batchSize = batchSize;
_outputLength = outputLength;
if (batchSize == -1)
{
_previousBatch = new List <double>();
_batch = new List <double>();
}
else
{
_previousBatch = new List <double>(batchSize);
_batch = new List <double>(batchSize);
}
_modeler = new SrCnnEntireModeler(threshold, sensitivity, detectMode);
}
/// <summary>
/// Create <see cref="SrCnnEntireAnomalyDetector"/>, which detects timeseries anomalies for entire input using SRCNN algorithm.
/// </summary>
/// <param name="catalog">The AnomalyDetectionCatalog.</param>
/// <param name="input">Input DataView.</param>
/// <param name="outputColumnName">Name of the column resulting from data processing of <paramref name="inputColumnName"/>.
/// The column data is a vector of <see cref="System.Double"/>. The length of this vector varies depending on <paramref name="detectMode"/>.</param>
/// <param name="inputColumnName">Name of column to process. The column data must be <see cref="System.Double"/>.</param>
/// <param name="threshold">The threshold to determine an anomaly. An anomaly is detected when the calculated SR raw score for a given point is more than the set threshold. This threshold must fall between [0,1], and its default value is 0.3.</param>
/// <param name="batchSize">Divide the input data into batches to fit srcnn model.
/// When set to -1, use the whole input to fit model instead of batch by batch, when set to a positive integer, use this number as batch size.
/// Must be -1 or a positive integer no less than 12. Default value is 1024.</param>
/// <param name="sensitivity">Sensitivity of boundaries, only useful when srCnnDetectMode is AnomalyAndMargin. Must be in [0,100]. Default value is 99.</param>
/// <param name="detectMode">An enum type of <see cref="SrCnnDetectMode"/>.
/// When set to AnomalyOnly, the output vector would be a 3-element Double vector of (IsAnomaly, RawScore, Mag).
/// When set to AnomalyAndExpectedValue, the output vector would be a 4-element Double vector of (IsAnomaly, RawScore, Mag, ExpectedValue).
/// When set to AnomalyAndMargin, the output vector would be a 7-element Double vector of (IsAnomaly, AnomalyScore, Mag, ExpectedValue, BoundaryUnit, UpperBoundary, LowerBoundary).
/// The RawScore is output by SR to determine whether a point is an anomaly or not, under AnomalyAndMargin mode, when a point is an anomaly, an AnomalyScore will be calculated according to sensitivity setting.
/// Default value is AnomalyOnly.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static IDataView DetectEntireAnomalyBySrCnn(this AnomalyDetectionCatalog catalog, IDataView input, string outputColumnName, string inputColumnName,
double threshold = 0.3, int batchSize = 1024, double sensitivity = 99, SrCnnDetectMode detectMode = SrCnnDetectMode.AnomalyOnly)
{
var options = new SrCnnEntireAnomalyDetectorOptions()
{
Threshold = threshold,
BatchSize = batchSize,
Sensitivity = sensitivity,
DetectMode = detectMode,
};
return(DetectEntireAnomalyBySrCnn(catalog, input, outputColumnName, inputColumnName, options));
}
/// <summary>
/// Create <see cref="SrCnnEntireAnomalyDetector"/>, which detects timeseries anomalies for entire input using SRCNN algorithm.
/// </summary>
/// <param name="catalog">The AnomalyDetectionCatalog.</param>
/// <param name="input">Input DataView.</param>
/// <param name="outputColumnName">Name of the column resulting from data processing of <paramref name="inputColumnName"/>.
/// The column data is a vector of <see cref="System.Double"/>. The length of this vector varies depending on <paramref name="detectMode"/>.</param>
/// <param name="inputColumnName">Name of column to process. The column data must be <see cref="System.Double"/>.</param>
/// <param name="threshold">The threshold to determine an anomaly. An anomaly is detected when the calculated SR raw score for a given point is more than the set threshold. This threshold must fall between [0,1], and its default value is 0.3.</param>
/// <param name="batchSize">Divide the input data into batches to fit srcnn model.
/// When set to -1, use the whole input to fit model instead of batch by batch, when set to a positive integer, use this number as batch size.
/// Must be -1 or a positive integer no less than 12. Default value is 1024.</param>
/// <param name="sensitivity">Sensitivity of boundaries, only useful when srCnnDetectMode is AnomalyAndMargin. Must be in [0,100]. Default value is 99.</param>
/// <param name="detectMode">An enum type of <see cref="SrCnnDetectMode"/>.
/// When set to AnomalyOnly, the output vector would be a 3-element Double vector of (IsAnomaly, RawScore, Mag).
/// When set to AnomalyAndExpectedValue, the output vector would be a 4-element Double vector of (IsAnomaly, RawScore, Mag, ExpectedValue).
/// When set to AnomalyAndMargin, the output vector would be a 7-element Double vector of (IsAnomaly, AnomalyScore, Mag, ExpectedValue, BoundaryUnit, UpperBoundary, LowerBoundary).
/// The RawScore is output by SR to determine whether a point is an anomaly or not, under AnomalyAndMargin mode, when a point is an anomaly, an AnomalyScore will be calculated according to sensitivity setting.
/// Default value is AnomalyOnly.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static IDataView DetectEntireAnomalyBySrCnn(this AnomalyDetectionCatalog catalog, IDataView input, string outputColumnName, string inputColumnName,
double threshold = 0.3, int batchSize = 1024, double sensitivity = 99, SrCnnDetectMode detectMode = SrCnnDetectMode.AnomalyOnly)
=> new SrCnnEntireAnomalyDetector(CatalogUtils.GetEnvironment(catalog), input, inputColumnName, outputColumnName, threshold, batchSize, sensitivity, detectMode);
