public void TestSvc()
{
var clf = new Svc <int>(kernel: Kernel.Linear, probability: true);
clf.Fit(X, Y);
var spClf = new Svc <int>(kernel: Kernel.Linear, probability: true);
spClf.Fit(SparseMatrix.OfMatrix(X), Y);
Assert.IsTrue(spClf.Predict(T).SequenceEqual(true_result));
Assert.IsTrue(spClf.SupportVectors is SparseMatrix);
Assert.IsTrue(clf.SupportVectors.AlmostEquals(spClf.SupportVectors));
Assert.IsTrue(spClf.DualCoef is SparseMatrix);
Assert.IsTrue(clf.DualCoef.AlmostEquals(spClf.DualCoef));
Assert.IsTrue(spClf.Coef is SparseMatrix);
Assert.IsTrue(clf.Coef.AlmostEquals(spClf.Coef));
Assert.IsTrue(clf.Support.SequenceEqual(spClf.Support));
Assert.IsTrue(clf.Predict(T).SequenceEqual(spClf.Predict(T)));
// refit with a different dataset
clf.Fit(X2, Y2);
spClf.Fit(SparseMatrix.OfMatrix(X2), Y2);
Assert.IsTrue(clf.SupportVectors.AlmostEquals(spClf.SupportVectors));
Assert.IsTrue(clf.DualCoef.AlmostEquals(spClf.DualCoef));
Assert.IsTrue(clf.Coef.AlmostEquals(spClf.Coef));
Assert.IsTrue(clf.Support.SequenceEqual(spClf.Support));
Assert.IsTrue(clf.Predict(T2).SequenceEqual(spClf.Predict(T2)));
Assert.IsTrue(clf.PredictProba(T2).AlmostEquals(spClf.PredictProba(T2), 0.001));
}
/// <summary>
/// Make some classification predictions on a toy dataset using a SVC
///
/// If binary is True restrict to a binary classification problem instead of a
/// multiclass classification problem
/// </summary>
/// <param name="x"></param>
/// <param name="y"></param>
/// <param name="binary"></param>
private static Tuple <int[], int[], Matrix <double> > MakePrediction(
Matrix <double> x = null,
int[] y = null,
bool binary = false)
{
if (x == null && y == null)
{
// import some data to play with
var dataset = IrisDataset.Load();
x = dataset.Data;
y = dataset.Target;
}
if (binary)
{
// restrict to a binary classification task
x = x.RowsAt(y.Indices(v => v < 2));
y = y.Where(v => v < 2).ToArray();
}
int nSamples = x.RowCount;
int nFeatures = x.ColumnCount;
var rng = new Random(37);
int[] p = Shuffle(rng, Enumerable.Range(0, nSamples).ToArray());
x = x.RowsAt(p);
y = y.ElementsAt(p);
var half = nSamples / 2;
// add noisy features to make the problem harder and avoid perfect results
rng = new Random(0);
x = x.HStack(DenseMatrix.CreateRandom(nSamples, 200, new Normal {
RandomSource = rng
}));
// run classifier, get class probabilities and label predictions
var clf = new Svc <int>(kernel: Kernel.Linear, probability: true);
clf.Fit(x.SubMatrix(0, half, 0, x.ColumnCount), y.Take(half).ToArray());
Matrix <double> probasPred = clf.PredictProba(x.SubMatrix(half, x.RowCount - half, 0, x.ColumnCount));
if (binary)
{
// only interested in probabilities of the positive case
// XXX: do we really want a special API for the binary case?
probasPred = probasPred.SubMatrix(0, probasPred.RowCount, 1, 1);
}
var yPred = clf.Predict(x.SubMatrix(half, x.RowCount - half, 0, x.ColumnCount));
var yTrue = y.Skip(half).ToArray();
return(Tuple.Create(yTrue, yPred, probasPred));
}
/// <summary>
/// Make some classification predictions on a toy dataset using a SVC
///
/// If binary is True restrict to a binary classification problem instead of a
/// multiclass classification problem
/// </summary>
/// <param name="x"></param>
/// <param name="y"></param>
/// <param name="binary"></param>
private static Tuple<int[], int[], Matrix<double>> MakePrediction(
Matrix<double> x = null,
int[] y = null,
bool binary = false)
{
if (x == null && y == null)
{
// import some data to play with
var dataset = IrisDataset.Load();
x = dataset.Data;
y = dataset.Target;
}
if (binary)
{
// restrict to a binary classification task
x = x.RowsAt(y.Indices(v => v < 2));
y = y.Where(v => v < 2).ToArray();
}
int nSamples = x.RowCount;
int nFeatures = x.ColumnCount;
var rng = new Random(37);
int[] p = Shuffle(rng, Enumerable.Range(0, nSamples).ToArray());
x = x.RowsAt(p);
y = y.ElementsAt(p);
var half = nSamples/2;
// add noisy features to make the problem harder and avoid perfect results
rng = new Random(0);
x = x.HStack(DenseMatrix.CreateRandom(nSamples, 200, new Normal{RandomSource = rng}));
// run classifier, get class probabilities and label predictions
var clf = new Svc<int>(kernel: Kernel.Linear, probability: true);
clf.Fit(x.SubMatrix(0, half, 0, x.ColumnCount), y.Take(half).ToArray());
Matrix<double> probasPred = clf.PredictProba(x.SubMatrix(half, x.RowCount - half, 0, x.ColumnCount));
if (binary)
{
// only interested in probabilities of the positive case
// XXX: do we really want a special API for the binary case?
probasPred = probasPred.SubMatrix(0, probasPred.RowCount, 1, 1);
}
var yPred = clf.Predict(x.SubMatrix(half, x.RowCount - half, 0, x.ColumnCount));
var yTrue = y.Skip(half).ToArray();
return Tuple.Create(yTrue, yPred, probasPred);
}
public void TestSvcWithCallableKernel()
{
// create SVM with callable linear kernel, check that results are the same
// as with built-in linear kernel
var svmCallable = new Svc <int>(kernel: Kernel.FromFunction((x, y) => x * (y.Transpose())),
probability: true);
svmCallable.Fit(X, Y);
var svmBuiltin = new Svc <int>(kernel: Kernel.Linear, probability: true);
svmBuiltin.Fit(X, Y);
Assert.IsTrue(svmCallable.DualCoef.AlmostEquals(svmBuiltin.DualCoef));
Assert.IsTrue(svmCallable.Intercept.AlmostEquals(svmBuiltin.Intercept));
Assert.IsTrue(svmCallable.Predict(X).SequenceEqual(svmBuiltin.Predict(X)));
Assert.IsTrue(svmCallable.PredictProba(X).AlmostEquals(svmBuiltin.PredictProba(X), 1));
Assert.IsTrue(svmCallable.DecisionFunction(X).AlmostEquals(svmBuiltin.DecisionFunction(X), 2));
}
public void TestSvc()
{
var clf = new Svc<int>(kernel: Kernel.Linear, probability: true);
clf.Fit(X, Y);
var spClf = new Svc<int>(kernel: Kernel.Linear, probability: true);
spClf.Fit(SparseMatrix.OfMatrix(X), Y);
Assert.IsTrue(spClf.Predict(T).SequenceEqual(true_result));
Assert.IsTrue(spClf.SupportVectors is SparseMatrix);
Assert.IsTrue(clf.SupportVectors.AlmostEquals(spClf.SupportVectors));
Assert.IsTrue(spClf.DualCoef is SparseMatrix);
Assert.IsTrue(clf.DualCoef.AlmostEquals(spClf.DualCoef));
Assert.IsTrue(spClf.Coef is SparseMatrix);
Assert.IsTrue(clf.Coef.AlmostEquals(spClf.Coef));
Assert.IsTrue(clf.Support.SequenceEqual(spClf.Support));
Assert.IsTrue(clf.Predict(T).SequenceEqual(spClf.Predict(T)));
// refit with a different dataset
clf.Fit(X2, Y2);
spClf.Fit(SparseMatrix.OfMatrix(X2), Y2);
Assert.IsTrue(clf.SupportVectors.AlmostEquals(spClf.SupportVectors));
Assert.IsTrue(clf.DualCoef.AlmostEquals(spClf.DualCoef));
Assert.IsTrue(clf.Coef.AlmostEquals(spClf.Coef));
Assert.IsTrue(clf.Support.SequenceEqual(spClf.Support));
Assert.IsTrue(clf.Predict(T2).SequenceEqual(spClf.Predict(T2)));
Assert.IsTrue(clf.PredictProba(T2).AlmostEquals(spClf.PredictProba(T2), 0.001));
}
public void TestSvcWithCallableKernel()
{
// create SVM with callable linear kernel, check that results are the same
// as with built-in linear kernel
var svmCallable = new Svc<int>(kernel: Kernel.FromFunction((x, y) => x*(y.Transpose())),
probability: true);
svmCallable.Fit(X, Y);
var svmBuiltin = new Svc<int>(kernel: Kernel.Linear, probability: true);
svmBuiltin.Fit(X, Y);
Assert.IsTrue(svmCallable.DualCoef.AlmostEquals(svmBuiltin.DualCoef));
Assert.IsTrue(svmCallable.Intercept.AlmostEquals(svmBuiltin.Intercept));
Assert.IsTrue(svmCallable.Predict(X).SequenceEqual(svmBuiltin.Predict(X)));
Assert.IsTrue(svmCallable.PredictProba(X).AlmostEquals(svmBuiltin.PredictProba(X), 1));
Assert.IsTrue(svmCallable.DecisionFunction(X).AlmostEquals(svmBuiltin.DecisionFunction(X), 2));
}
