public void TestLoad()
{
var res = IrisDataset.Load();
Assert.AreEqual(res.Data.Shape(), Tuple.Create(150, 4));
Assert.AreEqual(res.Target.Length, 150);
}
/// <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 TestInitialize()
{
var diabetes = DiabetesDataset.Load();
xDiabetes = diabetes.Data.SubMatrix(0, 200, 0, diabetes.Data.ColumnCount);
yDiabetes = MatrixExtensions.ToColumnMatrix(diabetes.Target.SubVector(0, 200));
//ind = np.arange(X_diabetes.shape[0])
//Random rng = new Random(0);
//rng.shuffle(ind)
//ind = ind[:200]
//X_diabetes, y_diabetes = X_diabetes[ind], y_diabetes[ind]
var iris = IrisDataset.Load();
xIris = SparseMatrix.OfMatrix(iris.Data);
yIris = iris.Target;
}
public Iris()
{
this.iris = new IrisDataset();
}