public void Train(int[] y, double[][] x, CancellationToken token)
{
log.LogInformation("Training SVM...");
var gridsearch = new GridSearch <SupportVectorMachine, double[], int>
{
ParameterRanges =
new GridSearchRangeCollection
{
//new GridSearchRange("complexity", new[] { 0.001, 0.01, 0.1, 1, 10, 100, 1000 }),
new GridSearchRange("C", new[] { 0.001, 0.01, 0.1, 1, 10 }),
},
Learner = p => new LinearDualCoordinateDescent
{
//Complexity = p["complexity"],
Loss = Loss.L2,
Kernel = new Linear(p["C"])
},
Loss = (actual, expected, m) => new ZeroOneLoss(expected).Loss(actual)
};
gridsearch.Token = token;
if (ParallelHelper.Options != null)
{
gridsearch.ParallelOptions = ParallelHelper.Options;
}
GridSearchResult <SupportVectorMachine, double[], int> result = gridsearch.Learn(x, y);
Model = result.BestModel;
GridSearchParameterCollection parameters = result.BestParameters;
var error = result.BestModelError;
log.LogInformation("SVM Trained. Threshold: {0} Constant: {1} Error: {2} ...", Model.Threshold, parameters[0].Value, error);
}
public void learn_test()
{
#region doc_learn
// Ensure results are reproducible
Accord.Math.Random.Generator.Seed = 0;
// Example binary data
double[][] inputs =
{
new double[] { -1, -1 },
new double[] { -1, 1 },
new double[] { 1, -1 },
new double[] { 1, 1 }
};
int[] xor = // xor labels
{
-1, 1, 1, -1
};
// Instantiate a new Grid Search algorithm for Kernel Support Vector Machines
var gridsearch = new GridSearch <SupportVectorMachine <Polynomial>, double[], int>()
{
// Here we can specify the range of the parameters to be included in the search
ParameterRanges = new GridSearchRangeCollection()
{
new GridSearchRange("complexity", new double[] { 0.00000001, 5.20, 0.30, 0.50 }),
new GridSearchRange("degree", new double[] { 1, 10, 2, 3, 4, 5 }),
new GridSearchRange("constant", new double[] { 0, 1, 2 })
},
// Indicate how learning algorithms for the models should be created
Learner = (p) => new SequentialMinimalOptimization <Polynomial>
{
Complexity = p["complexity"],
Kernel = new Polynomial((int)p["degree"], p["constant"])
},
// Define how the performance of the models should be measured
Loss = (actual, expected, m) => new ZeroOneLoss(expected).Loss(actual)
};
// If needed, control the degree of CPU parallelization
gridsearch.ParallelOptions.MaxDegreeOfParallelism = 1;
// Search for the best model parameters
var result = gridsearch.Learn(inputs, xor);
// Get the best SVM found during the parameter search
SupportVectorMachine <Polynomial> svm = result.BestModel;
// Get an estimate for its error:
double bestError = result.BestModelError;
// Get the best values found for the model parameters:
double bestC = result.BestParameters["complexity"].Value;
double bestDegree = result.BestParameters["degree"].Value;
double bestConstant = result.BestParameters["constant"].Value;
#endregion
Assert.IsNotNull(svm);
Assert.AreEqual(1e-8, bestC, 1e-10);
Assert.AreEqual(0, bestError, 1e-8);
Assert.AreEqual(1, bestDegree, 1e-8);
Assert.AreEqual(1, bestConstant, 1e-8);
Assert.AreEqual(1, svm.Kernel.Degree);
Assert.AreEqual(1, svm.Kernel.Constant);
}
public void Train(DataPackage data, CancellationToken token)
{
if (data is null)
{
throw new ArgumentNullException(nameof(data));
}
log.Debug("Training with {0} records", data.Y.Length);
standardizer = Standardizer.GetNumericStandardizer(data.X);
var xTraining = data.X;
var yTraining = data.Y;
var xTesting = xTraining;
var yTesting = yTraining;
int testSize = 100;
if (xTraining.Length > testSize * 4)
{
var training = xTraining.Length - testSize;
xTesting = xTraining.Skip(training).ToArray();
yTesting = yTraining.Skip(training).ToArray();
xTraining = xTraining.Take(training).ToArray();
yTraining = yTraining.Take(training).ToArray();
}
xTraining = standardizer.StandardizeAll(xTraining);
// Instantiate a new Grid Search algorithm for Kernel Support Vector Machines
var gridsearch = new GridSearch <SupportVectorMachine <Gaussian>, double[], int>()
{
// Here we can specify the range of the parameters to be included in the search
ParameterRanges = new GridSearchRangeCollection
{
new GridSearchRange("complexity", new [] { 0.001, 0.01, 0.1, 1, 10 }),
new GridSearchRange("gamma", new [] { 0.001, 0.01, 0.1, 1 })
},
// Indicate how learning algorithms for the models should be created
Learner = p => new SequentialMinimalOptimization <Gaussian>
{
Complexity = p["complexity"],
Kernel = new Gaussian
{
Gamma = p["gamma"]
}
},
// Define how the performance of the models should be measured
Loss = (actual, expected, m) => new ZeroOneLoss(expected).Loss(actual)
};
gridsearch.Token = token;
var randomized = new Random().Shuffle(xTraining, yTraining).ToArray();
yTraining = randomized[1].Cast <int>().ToArray();
xTraining = randomized[0].Cast <double[]>().ToArray();
var result = gridsearch.Learn(xTraining, yTraining);
// Get the best SVM found during the parameter search
SupportVectorMachine <Gaussian> svm = result.BestModel;
// Instantiate the probabilistic calibration (using Platt's scaling)
var calibration = new ProbabilisticOutputCalibration <Gaussian>(svm);
// Run the calibration algorithm
calibration.Learn(xTraining, yTraining); // returns the same machine
model = calibration.Model;
var predicted = ClassifyInternal(xTraining);
var confusionMatrix = new GeneralConfusionMatrix(classes: 2, expected: yTraining, predicted: predicted);
log.Debug("Performance on training dataset . F1(0):{0} F1(1):{1}", confusionMatrix.PerClassMatrices[0].FScore, confusionMatrix.PerClassMatrices[1].FScore);
predicted = Classify(xTesting);
confusionMatrix = new GeneralConfusionMatrix(classes: 2, expected: yTesting, predicted: predicted);
TestSetPerformance = confusionMatrix;
log.Debug("Performance on testing dataset . F1(0):{0} F1(1):{1}", confusionMatrix.PerClassMatrices[0].FScore, confusionMatrix.PerClassMatrices[1].FScore);
}
public async Task Train(DataSet dataset, CancellationToken token)
{
logger.LogDebug("Train");
IProcessingTextBlock[] data = dataset.Positive.Concat(dataset.Negative).ToArray();
int[] yData = dataset.Positive.Select(item => 1).Concat(dataset.Negative.Select(item => - 1)).ToArray();
double[][] xData = vectorSource.GetVectors(data, NormalizationType.None);
Array[] randomized = GlobalSettings.Random.Shuffle(yData, xData).ToArray();
//standardizer = Standardizer.GetNumericStandardizer(data);
GridSearch <SupportVectorMachine <Linear>, double[], int> gridsearch = new GridSearch <SupportVectorMachine <Linear>, double[], int>
{
ParameterRanges =
new GridSearchRangeCollection
{
new GridSearchRange("complexity", new[] { 0.001, 0.01, 0.1, 1, 10 }),
},
Learner = p => new LinearDualCoordinateDescent {
Complexity = p["complexity"], Loss = Loss.L2
},
Loss = (actual, expected, m) => new ZeroOneLoss(expected).Loss(actual)
};
gridsearch.Token = token;
GridSearchResult <SupportVectorMachine <Linear>, double[], int> result = await Task.Run(() => gridsearch.Learn(randomized[1].Cast <double[]>().ToArray(), randomized[0].Cast <int>().ToArray()), token).ConfigureAwait(false);
Model = result.BestModel;
}