Skip to content

Time Series samples for stateful prediction engine. #3213

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
codemzs merged 7 commits into from
Apr 11, 2019
Merged

Time Series samples for stateful prediction engine. #3213

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6e6b4e6
Add time series samples for stateful prediction engine.
codemzs Apr 5, 2019
28de467
PR feedback.
codemzs Apr 5, 2019
c668e07
PR feedback.
codemzs Apr 9, 2019
f81d115
PR feedback.
codemzs Apr 10, 2019
cab1b81
cleanup.
codemzs Apr 10, 2019
a98751a
PR feedback.
codemzs Apr 10, 2019
45acb31
cleanup.
codemzs Apr 10, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
160 changes: 103 additions & 57 deletions docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/TimeSeries/DetectChangePointBySsa.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,29 +1,16 @@
using System;
using System.Collections.Generic;
using System.IO;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Transforms.TimeSeries;

namespace Samples.Dynamic
{
public static class DetectChangePointBySsa
{
class ChangePointPrediction
{
[VectorType(4)]
public double[] Prediction { get; set; }
}

class SsaChangePointData
{
public float Value;

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

// This example creates a time series (list of Data with the i-th element corresponding to the i-th time slot).
// It demostrates stateful prediction engine that updates the state of the model and allows for saving/reloading.
// The estimator is applied then to identify points where data distribution changed.
// This estimator can account for temporal seasonality in the data.
public static void Example()
Expand All @@ -32,60 +19,119 @@ public static void Example()
// 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
// Generate sample series data with a recurring pattern
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));
var data = new List<TimeSeriesData>()
{
new TimeSeriesData(0),
new TimeSeriesData(1),
new TimeSeriesData(2),
new TimeSeriesData(3),
new TimeSeriesData(4),

new TimeSeriesData(0),
new TimeSeriesData(1),
new TimeSeriesData(2),
new TimeSeriesData(3),
new TimeSeriesData(4),

new TimeSeriesData(0),
new TimeSeriesData(1),
new TimeSeriesData(2),
new TimeSeriesData(3),
new TimeSeriesData(4),
};

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

// Setup estimator arguments
var inputColumnName = nameof(SsaChangePointData.Value);
// Setup SsaChangePointDetector arguments
var inputColumnName = nameof(TimeSeriesData.Value);
var outputColumnName = nameof(ChangePointPrediction.Prediction);

// The transformed data.
var transformedData = ml.Transforms.DetectChangePointBySsa(outputColumnName, inputColumnName, 95, 8, TrainingSize, SeasonalitySize + 1).Fit(dataView).Transform(dataView);
// Train the change point detector.
ITransformer model = ml.Transforms.DetectChangePointBySsa(outputColumnName, inputColumnName, 95, 8, TrainingSize, SeasonalitySize + 1).Fit(dataView);

// Getting the data of the newly created column as an IEnumerable of ChangePointPrediction.
var predictionColumn = ml.Data.CreateEnumerable<ChangePointPrediction>(transformedData, reuseRowObject: false);
// Create a prediction engine from the model for feeding new data.
var engine = model.CreateTimeSeriesPredictionFunction<TimeSeriesData, ChangePointPrediction>(ml);

Console.WriteLine($"{outputColumnName} column obtained post-transformation.");
// Start streaming new data points with no change point to the prediction engine.
Console.WriteLine($"Output from ChangePoint predictions on new data:");
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.

// Output from ChangePoint predictions on new data:
// 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

for (int i = 0; i < 5; i++)
PrintPrediction(i, engine.Predict(new TimeSeriesData(i)));

// 0 0 -1.01 0.50 0.00
// 1 0 -0.24 0.22 0.00
// 2 0 -0.31 0.30 0.00
// 3 0 0.44 0.01 0.00
// 4 0 2.16 0.00 0.24

// Now stream data points that reflect a change in trend.
for (int i = 0; i < 5; i++)
{
int value = (i + 1) * 100;
PrintPrediction(value, engine.Predict(new TimeSeriesData(value)));
}
// 100 0 86.23 0.00 2076098.24
// 200 0 171.38 0.00 809668524.21
// 300 1 256.83 0.01 22130423541.93 <-- alert is on, note that delay is expected
// 400 0 326.55 0.04 241162710263.29
// 500 0 364.82 0.08 597660527041.45 <-- saved to disk

// Now we demonstrate saving and loading the model.

// Save the model that exists within the prediction engine.
// The engine has been updating this model with every new data point.
var modelPath = "model.zip";
engine.CheckPoint(ml, modelPath);

// Load the model.
using (var file = File.OpenRead(modelPath))
model = ml.Model.Load(file, out DataViewSchema schema);

// We must create a new prediction engine from the persisted model.
engine = model.CreateTimeSeriesPredictionFunction<TimeSeriesData, ChangePointPrediction>(ml);

// Run predictions on the loaded model.
for (int i = 0; i < 5; i++)
{
int value = (i + 1) * 100;
PrintPrediction(value, engine.Predict(new TimeSeriesData(value)));
}

// 100 0 -58.58 0.15 1096021098844.34 <-- loaded from disk and running new predictions
// 200 0 -41.24 0.20 97579154688.98
// 300 0 -30.61 0.24 95319753.87
// 400 0 58.87 0.38 14.24
// 500 0 219.28 0.36 0.05

}

private static void PrintPrediction(float value, ChangePointPrediction prediction) =>
Console.WriteLine("{0}\t{1}\t{2:0.00}\t{3:0.00}\t{4:0.00}", value, prediction.Prediction[0],
prediction.Prediction[1], prediction.Prediction[2], prediction.Prediction[3]);

class ChangePointPrediction
{
[VectorType(4)]
public double[] Prediction { get; set; }
}

class TimeSeriesData
{
public float Value;

public TimeSeriesData(float value)
{
Value = value;
}
}
}
}
114 changes: 114 additions & 0 deletions ...crosoft.ML.Samples/Dynamic/Transforms/TimeSeries/DetectChangePointBySsaBatchPrediction.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,114 @@
using System;
using System.Collections.Generic;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic
{
public static class DetectChangePointBySsaBatchPrediction
{
// 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 points where data distribution changed.
// This estimator can account for temporal seasonality in the data.
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 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<TimeSeriesData>()
{
new TimeSeriesData(0),
new TimeSeriesData(1),
new TimeSeriesData(2),
new TimeSeriesData(3),
new TimeSeriesData(4),

new TimeSeriesData(0),
new TimeSeriesData(1),
new TimeSeriesData(2),
new TimeSeriesData(3),
new TimeSeriesData(4),

new TimeSeriesData(0),
new TimeSeriesData(1),
new TimeSeriesData(2),
new TimeSeriesData(3),
new TimeSeriesData(4),

//This is a change point
new TimeSeriesData(0),
new TimeSeriesData(100),
new TimeSeriesData(200),
new TimeSeriesData(300),
new TimeSeriesData(400),
};

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

// Setup estimator arguments
var inputColumnName = nameof(TimeSeriesData.Value);
var outputColumnName = nameof(ChangePointPrediction.Prediction);

// The transformed data.
var transformedData = ml.Transforms.DetectChangePointBySsa(outputColumnName, inputColumnName, 95, 8, TrainingSize, SeasonalitySize + 1).Fit(dataView).Transform(dataView);

// Getting the data of the newly created column as an IEnumerable of ChangePointPrediction.
var predictionColumn = ml.Data.CreateEnumerable<ChangePointPrediction>(transformedData, 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)
PrintPrediction(data[k++].Value, prediction);

// 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
}

private static void PrintPrediction(float value, ChangePointPrediction prediction) =>
Console.WriteLine("{0}\t{1}\t{2:0.00}\t{3:0.00}\t{4:0.00}", value, prediction.Prediction[0],
prediction.Prediction[1], prediction.Prediction[2], prediction.Prediction[3]);

class ChangePointPrediction
{
[VectorType(4)]
public double[] Prediction { get; set; }
}

class TimeSeriesData
{
public float Value;

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