// This example creates a time series (list of Data with the i-th element corresponding to the i-th time slot).
// SsaChangePointDetector is applied then to identify points where data distribution changed.
// SsaChangePointDetector differs from IidChangePointDetector in that it can account for temporal seasonality
// in the data.
public static void SsaChangePointDetectorTransform()
{
// 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 recurring pattern and then a change in trend
const int SeasonalitySize = 5;
const int TrainingSeasons = 3;
const int TrainingSize = SeasonalitySize * TrainingSeasons;
var data = new List <SsaChangePointData>();
for (int i = 0; i < TrainingSeasons; i++)
{
for (int j = 0; j < SeasonalitySize; j++)
{
data.Add(new SsaChangePointData(j));
}
}
// This is a change point
for (int i = 0; i < SeasonalitySize; i++)
{
data.Add(new SsaChangePointData(i * 100));
}
// Convert data to IDataView.
var dataView = ml.CreateStreamingDataView(data);
// Setup SsaChangePointDetector arguments
var inputColumnName = nameof(SsaChangePointData.Value);
var outputColumnName = nameof(ChangePointPrediction.Prediction);
var args = new SsaChangePointDetector.Arguments()
{
Source = inputColumnName,
Name = outputColumnName,
Confidence = 95, // The confidence for spike detection in the range [0, 100]
ChangeHistoryLength = 8, // The length of the window for detecting a change in trend; shorter windows are more sensitive to spikes.
TrainingWindowSize = TrainingSize, // The number of points from the beginning of the sequence used for training.
SeasonalWindowSize = SeasonalitySize + 1 // An upper bound on the largest relevant seasonality in the input time series."
};
// The transformed data.
var transformedData = new SsaChangePointEstimator(ml, args).Fit(dataView).Transform(dataView);
// Getting the data of the newly created column as an IEnumerable of ChangePointPrediction.
var predictionColumn = transformedData.AsEnumerable <ChangePointPrediction>(ml, reuseRowObject: false);
Console.WriteLine($"{outputColumnName} column obtained post-transformation.");
Console.WriteLine("Data\tAlert\tScore\tP-Value\tMartingale value");
int k = 0;
foreach (var prediction in predictionColumn)
{
Console.WriteLine("{0}\t{1}\t{2:0.00}\t{3:0.00}\t{4:0.00}", data[k++].Value, prediction.Prediction[0], prediction.Prediction[1], prediction.Prediction[2], prediction.Prediction[3]);
}
Console.WriteLine("");
// Prediction column obtained post-transformation.
// Data Alert Score P-Value Martingale value
// 0 0 - 2.53 0.50 0.00
// 1 0 - 0.01 0.01 0.00
// 2 0 0.76 0.14 0.00
// 3 0 0.69 0.28 0.00
// 4 0 1.44 0.18 0.00
// 0 0 - 1.84 0.17 0.00
// 1 0 0.22 0.44 0.00
// 2 0 0.20 0.45 0.00
// 3 0 0.16 0.47 0.00
// 4 0 1.33 0.18 0.00
// 0 0 - 1.79 0.07 0.00
// 1 0 0.16 0.50 0.00
// 2 0 0.09 0.50 0.00
// 3 0 0.08 0.45 0.00
// 4 0 1.31 0.12 0.00
// 0 0 - 1.79 0.07 0.00
// 100 1 99.16 0.00 4031.94 <-- alert is on, predicted changepoint
// 200 0 185.23 0.00 731260.87
// 300 0 270.40 0.01 3578470.47
// 400 0 357.11 0.03 45298370.86
}
// This example creates a time series (list of Data with the i-th element corresponding to the i-th time slot).
// SsaChangePointDetector is applied then to identify points where data distribution changed.
public static void SsaChangePointDetectorTransform()
{
// 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 change
const int size = 16;
var data = new List <Data>(size);
for (int i = 0; i < size / 2; i++)
{
data.Add(new Data(5));
}
// This is a change point
for (int i = 0; i < size / 2; i++)
{
data.Add(new Data(7));
}
// Convert data to IDataView.
var dataView = ml.CreateStreamingDataView(data);
// Setup IidSpikeDetector arguments
string outputColumnName = "Prediction";
string inputColumnName = "Value";
var args = new SsaChangePointDetector.Arguments()
{
Source = inputColumnName,
Name = outputColumnName,
Confidence = 95, // The confidence for spike detection in the range [0, 100]
ChangeHistoryLength = size / 4, // The length of the sliding window on p-values for computing the martingale score.
TrainingWindowSize = size / 2, // The number of points from the beginning of the sequence used for training.
SeasonalWindowSize = size / 8, // An upper bound on the largest relevant seasonality in the input time - series."
};
// The transformed data.
var transformedData = new SsaChangePointEstimator(ml, args).Fit(dataView).Transform(dataView);
// Getting the data of the newly created column as an IEnumerable of ChangePointPrediction.
var predictionColumn = transformedData.AsEnumerable <ChangePointPrediction>(ml, reuseRowObject: false);
Console.WriteLine($"{outputColumnName} column obtained post-transformation.");
Console.WriteLine("Data\tAlert\tScore\tP-Value\tMartingale value");
int k = 0;
foreach (var prediction in predictionColumn)
{
Console.WriteLine("{0}\t{1}\t{2:0.00}\t{3:0.00}\t{4:0.00}", data[k++].Value, prediction.Prediction[0], prediction.Prediction[1], prediction.Prediction[2], prediction.Prediction[3]);
}
Console.WriteLine("");
// Prediction column obtained post-transformation.
// Data Alert Score P-Value Martingale value
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 5 0 0.00 0.50 0.00
// 7 1 2.00 0.00 10298.67 <-- alert is on, predicted changepoint
// 7 0 1.00 0.31 15741.58
// 7 0 0.00 0.28 26487.48
// 7 0 0.00 0.28 44569.02
// 7 0 0.00 0.28 0.01
// 7 0 0.00 0.38 0.01
// 7 0 0.00 0.50 0.00
// 7 0 0.00 0.50 0.00
}
