def test_Knn(self):
knn = Knn()
knnParameter = KnnParameter(1, 3, EuclidianDistance())
discreteToIndexed = LaryToBinary(self.car)
discreteToIndexed.convert()
knn.train(self.car.getInstanceList(), knnParameter)
self.assertAlmostEqual(20.31, 100 * knn.test(self.car.getInstanceList()).getErrorRate(), 2)
def test_Knn(self):
knn = Knn()
knnParameter = KnnParameter(1, 3, EuclidianDistance())
discreteToContinuous = DiscreteToContinuous(self.car)
discreteToContinuous.convert()
knn.train(self.car.getInstanceList(), knnParameter)
self.assertAlmostEqual(
20.31, 100 * knn.test(self.car.getInstanceList()).getErrorRate(),
2)
def test_Compare(self):
mxKFoldRun = MxKFoldRun(5, 2)
combined5x2t = Combined5x2t()
experimentPerformance1 = mxKFoldRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.iris))
experimentPerformance2 = mxKFoldRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.iris))
self.assertAlmostEqual(
0.186,
combined5x2t.compare(experimentPerformance1,
experimentPerformance2).getPValue(), 3)
experimentPerformance1 = mxKFoldRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.tictactoe))
experimentPerformance2 = mxKFoldRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.tictactoe))
self.assertAlmostEqual(
0.0000059,
combined5x2t.compare(experimentPerformance1,
experimentPerformance2).getPValue(), 7)
experimentPerformance1 = mxKFoldRun.execute(
Experiment(Lda(), Parameter(1), self.dermatology))
experimentPerformance2 = mxKFoldRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.dermatology))
self.assertAlmostEqual(
0.9819,
combined5x2t.compare(experimentPerformance1,
experimentPerformance2).getPValue(), 4)
experimentPerformance1 = mxKFoldRun.execute(
Experiment(Dummy(), Parameter(1), self.nursery))
experimentPerformance2 = mxKFoldRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.nursery))
self.assertAlmostEqual(
0.0,
combined5x2t.compare(experimentPerformance1,
experimentPerformance2).getPValue(), 4)
experimentPerformance1 = mxKFoldRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.car))
experimentPerformance2 = mxKFoldRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.car))
self.assertAlmostEqual(
0.00043,
combined5x2t.compare(experimentPerformance1,
experimentPerformance2).getPValue(), 5)
experimentPerformance1 = mxKFoldRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.bupa))
experimentPerformance2 = mxKFoldRun.execute(
Experiment(Lda(), Parameter(1), self.bupa))
self.assertAlmostEqual(
0.0663,
combined5x2t.compare(experimentPerformance1,
experimentPerformance2).getPValue(), 4)
def __init__(self, seed: int, distanceMetric=EuclidianDistance()):
"""
Parameters of the Rocchio classifier.
PARAMETERS
----------
seed : int
Seed is used for random number generation.
distanceMetric : DistanceMetric
distance metric used to calculate the distance between two instances.
"""
super().__init__(seed)
self.distanceMetric = distanceMetric
def test_Train(self):
knn = Knn()
knnParameter = KnnParameter(1, 3, EuclidianDistance())
knn.train(self.iris.getInstanceList(), knnParameter)
self.assertAlmostEqual(4.00, 100 * knn.test(self.iris.getInstanceList()).getErrorRate(), 2)
knn.train(self.bupa.getInstanceList(), knnParameter)
self.assertAlmostEqual(19.42, 100 * knn.test(self.bupa.getInstanceList()).getErrorRate(), 2)
knn.train(self.dermatology.getInstanceList(), knnParameter)
self.assertAlmostEqual(3.01, 100 * knn.test(self.dermatology.getInstanceList()).getErrorRate(), 2)
knn.train(self.car.getInstanceList(), knnParameter)
self.assertAlmostEqual(20.31, 100 * knn.test(self.car.getInstanceList()).getErrorRate(), 2)
knn.train(self.tictactoe.getInstanceList(), knnParameter)
self.assertAlmostEqual(32.57, 100 * knn.test(self.tictactoe.getInstanceList()).getErrorRate(), 2)
def test_Knn(self):
knn = Knn()
knnParameter = KnnParameter(1, 3, EuclidianDistance())
normalize = Normalize(self.iris)
normalize.convert()
knn.train(self.iris.getInstanceList(), knnParameter)
self.assertAlmostEqual(4.67, 100 * knn.test(self.iris.getInstanceList()).getErrorRate(), 2)
normalize = Normalize(self.bupa)
normalize.convert()
knn.train(self.bupa.getInstanceList(), knnParameter)
self.assertAlmostEqual(16.52, 100 * knn.test(self.bupa.getInstanceList()).getErrorRate(), 2)
normalize = Normalize(self.dermatology)
normalize.convert()
knn.train(self.dermatology.getInstanceList(), knnParameter)
self.assertAlmostEqual(1.91, 100 * knn.test(self.dermatology.getInstanceList()).getErrorRate(), 2)
def test_Knn(self):
knn = Knn()
knnParameter = KnnParameter(1, 3, EuclidianDistance())
pca = Pca(self.iris)
pca.convert()
knn.train(self.iris.getInstanceList(), knnParameter)
self.assertAlmostEqual(3.33, 100 * knn.test(self.iris.getInstanceList()).getErrorRate(), 2)
pca = Pca(self.bupa)
pca.convert()
knn.train(self.bupa.getInstanceList(), knnParameter)
self.assertAlmostEqual(19.13, 100 * knn.test(self.bupa.getInstanceList()).getErrorRate(), 2)
pca = Pca(self.dermatology)
pca.convert()
knn.train(self.dermatology.getInstanceList(), knnParameter)
self.assertAlmostEqual(2.73, 100 * knn.test(self.dermatology.getInstanceList()).getErrorRate(), 2)
def __init__(self, seed: int, k: int, distanceMetric=EuclidianDistance()):
"""
Parameters of the K-nearest neighbor classifier.
PARAMETERS
----------
seed : int
Seed is used for random number generation.
k : int
Parameter of the K-nearest neighbor algorithm.
distanceMetric : DistanceMetric
Used to calculate the distance between two instances.
"""
super().__init__(seed, distanceMetric)
self.__k = k
def test_Execute(self):
mxKFoldRun = MxKFoldRun(5, 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.iris))
self.assertAlmostEqual(
6.13, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.tictactoe))
self.assertAlmostEqual(
23.51,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.bupa))
self.assertAlmostEqual(
37.05,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.dermatology))
self.assertAlmostEqual(
15.41,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Lda(), Parameter(1), self.bupa))
self.assertAlmostEqual(
34.72,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Lda(), Parameter(1), self.dermatology))
self.assertAlmostEqual(
4.04, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.iris))
self.assertAlmostEqual(
5.2, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.dermatology))
self.assertAlmostEqual(
5.46, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.car))
self.assertAlmostEqual(
16.52,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.nursery))
self.assertAlmostEqual(
9.80, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.tictactoe))
self.assertAlmostEqual(
8.77, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.car))
self.assertAlmostEqual(
9.77, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Dummy(), Parameter(1), self.nursery))
self.assertAlmostEqual(
67.09,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = mxKFoldRun.execute(
Experiment(Dummy(), Parameter(1), self.iris))
self.assertAlmostEqual(
70.53,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
def test_Compare(self):
kFoldRun = KFoldRun(10)
pairedt = Pairedt()
experimentPerformance1 = kFoldRun.execute(Experiment(C45(), C45Parameter(1, True, 0.2), self.iris))
experimentPerformance2 = kFoldRun.execute(Experiment(LinearPerceptron(), LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100), self.iris))
self.assertAlmostEqual(0.379, pairedt.compare(experimentPerformance1, experimentPerformance2).getPValue(), 3)
experimentPerformance1 = kFoldRun.execute(Experiment(C45(), C45Parameter(1, True, 0.2), self.tictactoe))
experimentPerformance2 = kFoldRun.execute(Experiment(Bagging(), BaggingParameter(1, 50), self.tictactoe))
self.assertAlmostEqual(0.00000692, pairedt.compare(experimentPerformance1, experimentPerformance2).getPValue(), 7)
experimentPerformance1 = kFoldRun.execute(Experiment(Lda(), Parameter(1), self.dermatology))
experimentPerformance2 = kFoldRun.execute(Experiment(LinearPerceptron(), LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100), self.dermatology))
self.assertAlmostEqual(0.7842, pairedt.compare(experimentPerformance1, experimentPerformance2).getPValue(), 4)
experimentPerformance1 = kFoldRun.execute(Experiment(Dummy(), Parameter(1), self.nursery))
experimentPerformance2 = kFoldRun.execute(Experiment(NaiveBayes(), Parameter(1), self.nursery))
self.assertAlmostEqual(0.0, pairedt.compare(experimentPerformance1, experimentPerformance2).getPValue(), 4)
experimentPerformance1 = kFoldRun.execute(Experiment(NaiveBayes(), Parameter(1), self.car))
experimentPerformance2 = kFoldRun.execute(Experiment(Bagging(), BaggingParameter(1, 50), self.car))
self.assertAlmostEqual(0.00000336, pairedt.compare(experimentPerformance1, experimentPerformance2).getPValue(), 7)
experimentPerformance1 = kFoldRun.execute(Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()), self.bupa))
experimentPerformance2 = kFoldRun.execute(Experiment(Lda(), Parameter(1), self.bupa))
self.assertAlmostEqual(0.1640, pairedt.compare(experimentPerformance1, experimentPerformance2).getPValue(), 4)
def test_Execute(self):
kFoldRun = KFoldRun(10)
experimentPerformance = kFoldRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.iris))
self.assertAlmostEqual(
6.00, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.tictactoe))
self.assertAlmostEqual(
18.78,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = kFoldRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.bupa))
self.assertAlmostEqual(
36.85,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = kFoldRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.dermatology))
self.assertAlmostEqual(
10.92,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = kFoldRun.execute(
Experiment(Lda(), Parameter(1), self.bupa))
self.assertAlmostEqual(
31.61,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = kFoldRun.execute(
Experiment(Lda(), Parameter(1), self.dermatology))
self.assertAlmostEqual(
3.30, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.iris))
self.assertAlmostEqual(
5.33, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.dermatology))
self.assertAlmostEqual(
3.81, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.car))
self.assertAlmostEqual(
14.88,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = kFoldRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.nursery))
self.assertAlmostEqual(
9.71, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.tictactoe))
self.assertAlmostEqual(
3.55, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.car))
self.assertAlmostEqual(
6.77, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = kFoldRun.execute(
Experiment(Dummy(), Parameter(1), self.nursery))
self.assertAlmostEqual(
67.12,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = kFoldRun.execute(
Experiment(Dummy(), Parameter(1), self.iris))
self.assertAlmostEqual(
79.33,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
def test_Execute(self):
stratifiedMxKRun = StratifiedMxKFoldRun(5, 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.iris))
self.assertAlmostEqual(
8.00, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.tictactoe))
self.assertAlmostEqual(
22.03,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.bupa))
self.assertAlmostEqual(
33.33,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.dermatology))
self.assertAlmostEqual(
13.66,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Lda(), Parameter(1), self.bupa))
self.assertAlmostEqual(
33.05,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Lda(), Parameter(1), self.dermatology))
self.assertAlmostEqual(
3.55, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.iris))
self.assertAlmostEqual(
6.00, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.dermatology))
self.assertAlmostEqual(
4.66, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.car))
self.assertAlmostEqual(
15.11,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.nursery))
self.assertAlmostEqual(
9.68, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.tictactoe))
self.assertAlmostEqual(
9.29, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.car))
self.assertAlmostEqual(
9.20, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Dummy(), Parameter(1), self.nursery))
self.assertAlmostEqual(
66.67,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = stratifiedMxKRun.execute(
Experiment(Dummy(), Parameter(1), self.iris))
self.assertAlmostEqual(
66.67,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
def test_Execute(self):
bootstrapRun = BootstrapRun(10)
experimentPerformance = bootstrapRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.iris))
self.assertAlmostEqual(
4.33, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(C45(), C45Parameter(1, True, 0.2), self.tictactoe))
self.assertAlmostEqual(
13.16,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = bootstrapRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.bupa))
self.assertAlmostEqual(
24.84,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = bootstrapRun.execute(
Experiment(Knn(), KnnParameter(1, 3, EuclidianDistance()),
self.dermatology))
self.assertAlmostEqual(
8.01, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(Lda(), Parameter(1), self.bupa))
self.assertAlmostEqual(
32.03,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = bootstrapRun.execute(
Experiment(Lda(), Parameter(1), self.dermatology))
self.assertAlmostEqual(
2.95, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.iris))
self.assertAlmostEqual(
3.27, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(LinearPerceptron(),
LinearPerceptronParameter(1, 0.1, 0.99, 0.2, 100),
self.dermatology))
self.assertAlmostEqual(
2.65, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.car))
self.assertAlmostEqual(
14.75,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = bootstrapRun.execute(
Experiment(NaiveBayes(), Parameter(1), self.nursery))
self.assertAlmostEqual(
9.71, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.tictactoe))
self.assertAlmostEqual(
3.00, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(Bagging(), BaggingParameter(1, 50), self.car))
self.assertAlmostEqual(
3.44, 100 * experimentPerformance.meanPerformance().getErrorRate(),
2)
experimentPerformance = bootstrapRun.execute(
Experiment(Dummy(), Parameter(1), self.nursery))
self.assertAlmostEqual(
66.79,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)
experimentPerformance = bootstrapRun.execute(
Experiment(Dummy(), Parameter(1), self.iris))
self.assertAlmostEqual(
66.67,
100 * experimentPerformance.meanPerformance().getErrorRate(), 2)