/// <summary>
/// Check that the model is able to fit the classification data
/// </summary>
private void check_predictions(LogisticRegression<int> clf, Matrix<double> X, int[] y)
{
int nSamples = y.Length;
int[] classes = y.Distinct().OrderBy(v => v).ToArray();
int nClasses = classes.Length;
clf.Fit(X, y);
var predicted = clf.Predict(X);
Assert.IsTrue(classes.SequenceEqual(clf.Classes));
Assert.AreEqual(nSamples, predicted.Length);
Assert.IsTrue(y.SequenceEqual(predicted));
Matrix<double> probabilities = clf.PredictProba(X);
Assert.AreEqual(Tuple.Create(nSamples, nClasses), probabilities.Shape());
Assert.IsTrue(probabilities.SumOfEveryRow().AlmostEquals(DenseVector.Create(probabilities.RowCount, i => 1.0)));
Assert.IsTrue(y.SequenceEqual(probabilities.ArgmaxColumns()));
}
/// <summary>
/// Check that the model is able to fit the classification data
/// </summary>
private void check_predictions(LogisticRegression <int> clf, Matrix <double> X, int[] y)
{
int nSamples = y.Length;
int[] classes = y.Distinct().OrderBy(v => v).ToArray();
int nClasses = classes.Length;
clf.Fit(X, y);
var predicted = clf.Predict(X);
Assert.IsTrue(classes.SequenceEqual(clf.Classes));
Assert.AreEqual(nSamples, predicted.Length);
Assert.IsTrue(y.SequenceEqual(predicted));
Matrix <double> probabilities = clf.PredictProba(X);
Assert.AreEqual(Tuple.Create(nSamples, nClasses), probabilities.Shape());
Assert.IsTrue(probabilities.SumOfEveryRow().AlmostEquals(DenseVector.Create(probabilities.RowCount, i => 1.0)));
Assert.IsTrue(y.SequenceEqual(probabilities.ArgmaxColumns()));
}
public void TestPredictIris()
{
int nSamples = iris.Data.RowCount;
string[] target = iris.Target.Select(v => iris.TargetNames[v]).ToArray();
var clf = new LogisticRegression <string>(c: iris.Data.RowCount);
clf.Fit(iris.Data, target);
Assert.IsTrue(target.Distinct().OrderBy(t => t).SequenceEqual(clf.Classes));
var pred = clf.Predict(iris.Data);
var matchingN = pred.Zip(target, Tuple.Create).Where(t => t.Item1 == t.Item2).Count();
Assert.IsTrue(1.0 * matchingN / pred.Length > 0.95);
var probabilities = clf.PredictProba(iris.Data);
Assert.IsTrue(probabilities.SumOfEveryRow().AlmostEquals(DenseVector.Create(nSamples, i => 1.0)));
pred = probabilities.RowEnumerator().Select(r => iris.TargetNames[r.Item2.MaximumIndex()]).ToArray();
matchingN = pred.Zip(target, Tuple.Create).Where(t => t.Item1 == t.Item2).Count();
Assert.IsTrue(1.0 * matchingN / pred.Length > 0.95);
}
public void TestPredictIris()
{
int nSamples = iris.Data.RowCount;
string[] target = iris.Target.Select(v => iris.TargetNames[v]).ToArray();
var clf = new LogisticRegression<string>(c: iris.Data.RowCount);
clf.Fit(iris.Data, target);
Assert.IsTrue(target.Distinct().OrderBy(t => t).SequenceEqual(clf.Classes));
var pred = clf.Predict(iris.Data);
var matchingN = pred.Zip(target, Tuple.Create).Where(t => t.Item1 == t.Item2).Count();
Assert.IsTrue(1.0*matchingN/pred.Length > 0.95);
var probabilities = clf.PredictProba(iris.Data);
Assert.IsTrue(probabilities.SumOfEveryRow().AlmostEquals(DenseVector.Create(nSamples, i => 1.0)));
pred = probabilities.RowEnumerator().Select(r => iris.TargetNames[r.Item2.MaximumIndex()]).ToArray();
matchingN = pred.Zip(target, Tuple.Create).Where(t => t.Item1 == t.Item2).Count();
Assert.IsTrue(1.0 * matchingN / pred.Length > 0.95);
}
