public void TestWeight()
{
var classification =
SampleGenerator.MakeClassification(
nSamples: 200,
nFeatures: 100,
weights: new[] { 0.833, 0.167 }.ToList(),
randomState: new Random(0));
var classWeight = ClassWeightEstimator <int> .Explicit(new Dictionary <int, double> {
{ 0, 5 }
});
Matrix x = SparseMatrix.OfMatrix(classification.X);
foreach (var clf in new IClassifier <int>[]
{
new LogisticRegression <int>(classWeightEstimator: classWeight),
//new LinearSvc(classWeight:classWeight, random_state=0),
//new Svc<int>(classWeight: classWeight)
})
{
clf.Fit(x.SubMatrix(0, 180, 0, x.ColumnCount), classification.Y.Take(180).ToArray());
var yPred = clf.Predict(x.SubMatrix(180, x.RowCount - 180, 0, x.ColumnCount));
var matchingN =
yPred.Zip(classification.Y.Skip(180), Tuple.Create).Where(t => t.Item1 == t.Item2).Count();
Assert.IsTrue(matchingN >= 11);
}
}
/// <summary>
/// Test class weights.
/// </summary>
public void TestClassWeights()
{
Matrix x = DenseMatrix.OfArray(new[, ]
{
{ -1.0, -1.0 }, { -1.0, 0 }, { -.8, -1.0 },
{ 1.0, 1.0 }, { 1.0, 0.0 }
});
var y = new[] { 1, 1, 1, -1, -1 };
var clf = new RidgeClassifier <int>(classWeightEstimator: null);
clf.Fit(x, y);
Assert.AreEqual(
clf.Predict(DenseMatrix.OfArray(new[, ] {
{ 0.2, -1.0 }
})),
new DenseMatrix(1, 1, new double[] { 1 }));
// we give a small weights to class 1
clf = new RidgeClassifier <int>(
classWeightEstimator: ClassWeightEstimator <int> .Explicit(new Dictionary <int, double> {
{ 1, 0.001 }
}));
clf.Fit(x, y);
// now the hyperplane should rotate clock-wise and
// the prediction on this point should shift
Assert.AreEqual(
clf.Predict(DenseMatrix.OfArray(new[, ] {
{ 0.2, -1.0 }
})),
new DenseMatrix(1, 1, new double[] { -1 }));
}
public void test_weight()
{
var clf = new Svc <int>(classWeightEstimator: ClassWeightEstimator <int> .Explicit(new Dictionary <int, double> {
{ 1, 0.1 }
}));
// we give a small weights to class 1
clf.Fit(X, Y);
// so all predicted values belong to class 2
Assert.IsTrue(clf.Predict(X).SequenceEqual(Enumerable.Repeat(2, 6)));
/*
* X_, y_ = make_classification(n_samples=200, n_features=10,
* weights=[0.833, 0.167], random_state=2)
*
* for clf in (linear_model.LogisticRegression(),
* svm.LinearSVC(random_state=0), svm.SVC()):
* clf.set_params(class_weight={0: .1, 1: 10})
* clf.fit(X_[:100], y_[:100])
* y_pred = clf.predict(X_[100:])
* assert_true(f1_score(y_[100:], y_pred) > .3)
* */
}
