/**
* <summary> Constructor that takes {@link InstanceList}s as trainsSet and validationSet. Initially it allocates layer weights,
* then creates an input vector by using given trainSet and finds error. Via the validationSet it finds the classification
* performance and at the end it reassigns the allocated weight Matrix with the matrix that has the best accuracy.</summary>
*
* <param name="trainSet"> InstanceList that is used to train.</param>
* <param name="validationSet">InstanceList that is used to validate.</param>
* <param name="parameters"> Linear perceptron parameters; learningRate, etaDecrease, crossValidationRatio, epoch.</param>
*/
public LinearPerceptronModel(InstanceList.InstanceList trainSet, InstanceList.InstanceList validationSet,
LinearPerceptronParameter parameters) : base(trainSet)
{
W = AllocateLayerWeights(K, d + 1, new Random(parameters.GetSeed()));
var bestW = (Matrix)W.Clone();
var bestClassificationPerformance = new ClassificationPerformance(0.0);
var epoch = parameters.GetEpoch();
var learningRate = parameters.GetLearningRate();
for (var i = 0; i < epoch; i++)
{
trainSet.Shuffle(parameters.GetSeed());
for (var j = 0; j < trainSet.Size(); j++)
{
CreateInputVector(trainSet.Get(j));
var rMinusY = CalculateRMinusY(trainSet.Get(j), x, W);
var deltaW = rMinusY.Multiply(x);
deltaW.MultiplyWithConstant(learningRate);
W.Add(deltaW);
}
var currentClassificationPerformance = TestClassifier(validationSet);
if (currentClassificationPerformance.GetAccuracy() > bestClassificationPerformance.GetAccuracy())
{
bestClassificationPerformance = currentClassificationPerformance;
bestW = (Matrix)W.Clone();
}
learningRate *= parameters.GetEtaDecrease();
}
W = bestW;
}
public void TestLinearPerceptron()
{
var linearPerceptron = new LinearPerceptron();
var linearPerceptronParameter = new LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100);
var discreteToIndexed = new DiscreteToIndexed(car);
discreteToIndexed.Convert();
linearPerceptron.Train(car.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(8.80, 100 * linearPerceptron.Test(car.GetInstanceList()).GetErrorRate(), 0.01);
discreteToIndexed = new DiscreteToIndexed(tictactoe);
discreteToIndexed.Convert();
linearPerceptron.Train(tictactoe.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(1.67, 100 * linearPerceptron.Test(tictactoe.GetInstanceList()).GetErrorRate(), 0.01);
}
public void TestTrain()
{
var linearPerceptron = new LinearPerceptron();
var linearPerceptronParameter = new LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100);
linearPerceptron.Train(iris.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(8.67, 100 * linearPerceptron.Test(iris.GetInstanceList()).GetErrorRate(), 0.01);
linearPerceptronParameter = new LinearPerceptronParameter(1, 0.001, 0.99, 0.2, 100);
linearPerceptron.Train(bupa.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(31.88, 100 * linearPerceptron.Test(bupa.GetInstanceList()).GetErrorRate(), 0.01);
linearPerceptronParameter = new LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100);
linearPerceptron.Train(dermatology.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(3.28, 100 * linearPerceptron.Test(dermatology.GetInstanceList()).GetErrorRate(), 0.01);
}
public void TestLinearPerceptron()
{
var linearPerceptron = new LinearPerceptron();
var linearPerceptronParameter = new LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100);
var normalize = new Normalize(iris);
normalize.Convert();
linearPerceptron.Train(iris.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(2.67, 100 * linearPerceptron.Test(iris.GetInstanceList()).GetErrorRate(), 0.01);
normalize = new Normalize(bupa);
normalize.Convert();
linearPerceptron.Train(bupa.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(31.59, 100 * linearPerceptron.Test(bupa.GetInstanceList()).GetErrorRate(), 0.01);
normalize = new Normalize(dermatology);
normalize.Convert();
linearPerceptron.Train(dermatology.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(1.09, 100 * linearPerceptron.Test(dermatology.GetInstanceList()).GetErrorRate(), 0.01);
}
public void TestLinearPerceptron()
{
var linearPerceptron = new LinearPerceptron();
var linearPerceptronParameter = new LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100);
var pca = new Pca(iris);
pca.Convert();
linearPerceptron.Train(iris.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(8.67, 100 * linearPerceptron.Test(iris.GetInstanceList()).GetErrorRate(), 0.01);
linearPerceptronParameter = new LinearPerceptronParameter(1, 0.01, 0.99, 0.2, 100);
pca = new Pca(bupa);
pca.Convert();
linearPerceptron.Train(bupa.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(42.03, 100 * linearPerceptron.Test(bupa.GetInstanceList()).GetErrorRate(), 0.01);
pca = new Pca(dermatology);
pca.Convert();
linearPerceptron.Train(dermatology.GetInstanceList(), linearPerceptronParameter);
Assert.AreEqual(1.64, 100 * linearPerceptron.Test(dermatology.GetInstanceList()).GetErrorRate(), 0.01);
}
