public void learn_linear_multiclass()
{
#region doc_learn_multiclass
// In this example, we will learn a multi-class SVM using the one-vs-one (OvO)
// approach. The OvO approacbh can decompose decision problems involving multiple
// classes into a series of binary ones, which can then be solved using SVMs.
// Ensure we have reproducible results
Accord.Math.Random.Generator.Seed = 0;
// We will try to learn a classifier
// for the Fisher Iris Flower dataset
var iris = new Iris();
double[][] inputs = iris.Instances; // get the flower characteristics
int[] outputs = iris.ClassLabels; // get the expected flower classes
// We will use mini-batches of size 32 to learn a SVM using SGD
var batches = MiniBatches.Create(batchSize: 32, maxIterations: 1000,
shuffle: ShuffleMethod.EveryEpoch, input: inputs, output: outputs);
// Now, we can create a multi-class teaching algorithm for the SVMs
var teacher = new MulticlassSupportVectorLearning <Linear, double[]>
{
// We will use SGD to learn each of the binary problems in the multi-class problem
Learner = (p) => new StochasticGradientDescent <Linear, double[], LogisticLoss>()
{
LearningRate = 1e-3,
MaxIterations = 1 // so the gradient is only updated once after each mini-batch
}
};
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
teacher.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Now, we can start training the model on mini-batches:
foreach (var batch in batches)
{
teacher.Learn(batch.Inputs, batch.Outputs);
}
// Get the final model:
var svm = teacher.Model;
// Now, we should be able to use the model to predict
// the classes of all flowers in Fisher's Iris dataset:
int[] prediction = svm.Decide(inputs);
// And from those predictions, we can compute the model accuracy:
var cm = new GeneralConfusionMatrix(expected: outputs, predicted: prediction);
double accuracy = cm.Accuracy; // should be approximately 0.973
#endregion
Assert.AreEqual(0.97333333333333338, cm.Accuracy);
Assert.AreEqual(150, batches.NumberOfSamples);
Assert.AreEqual(32, batches.MiniBatchSize);
Assert.AreEqual(213, batches.CurrentEpoch);
Assert.AreEqual(1001, batches.CurrentIteration);
Assert.AreEqual(82, batches.CurrentSample);
}
public void learn_linear_nonlinear()
{
#region doc_learn_nonlinear
// In this example, we will show how its possible to learn a
// non-linear SVM using a linear algorithm by using a explicit
// expansion of the kernel function:
// Ensure we have reproducible results
Accord.Math.Random.Generator.Seed = 0;
// We will try to learn a classifier
// for the Fisher Iris Flower dataset
var iris = new WisconsinDiagnosticBreastCancer();
double[][] inputs = iris.Features; // get the flower characteristics
int[] outputs = iris.ClassLabels; // get the expected flower classes
// We will use mini-batches of size 32 to learn a SVM using SGD
var batches = MiniBatches.Create(batchSize: 32, maxIterations: 1000,
shuffle: ShuffleMethod.EveryEpoch, input: inputs, output: outputs);
// We will use an explicit Polynomial kernel expansion
var polynomial = new Polynomial(2);
// Now, we can create a multi-class teaching algorithm for the SVMs
var teacher = new MulticlassSupportVectorLearning <Linear, double[]>
{
// We will use SGD to learn each of the binary problems in the multi-class problem
Learner = (p) => new AveragedStochasticGradientDescent <Linear, double[], LogisticLoss>()
{
LearningRate = 1e-3,
MaxIterations = 1 // so the gradient is only updated once after each mini-batch
}
};
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
teacher.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Now, we can start training the model on mini-batches:
foreach (var batch in batches)
{
teacher.Learn(polynomial.Transform(batch.Inputs), batch.Outputs);
}
// Get the final model:
var svm = teacher.Model;
// The following line is only needed to ensure reproducible results. Please remove it to enable full parallelization
svm.ParallelOptions.MaxDegreeOfParallelism = 1; // (Remove, comment, or change this line to enable full parallelism)
// Now, we should be able to use the model to predict
// the classes of all flowers in Fisher's Iris dataset:
int[] prediction = svm.Decide(polynomial.Transform(inputs));
// And from those predictions, we can compute the model accuracy:
var cm = new GeneralConfusionMatrix(expected: outputs, predicted: prediction);
double accuracy = cm.Accuracy; // should be approximately 0.92
#endregion
Assert.AreEqual(0.92091388400702989, cm.Accuracy);
Assert.AreEqual(569, batches.NumberOfSamples);
Assert.AreEqual(32, batches.MiniBatchSize);
Assert.AreEqual(56, batches.CurrentEpoch);
Assert.AreEqual(1001, batches.CurrentIteration);
Assert.AreEqual(168, batches.CurrentSample);
}
