def test_LargeSample5Fold(self):
stratifiedKFoldCrossValidation = StratifiedKFoldCrossValidation(
self.largeSample, 5, 1)
for i in range(5):
items = set()
trainFold = stratifiedKFoldCrossValidation.getTrainFold(i)
testFold = stratifiedKFoldCrossValidation.getTestFold(i)
items.update(trainFold)
items.update(testFold)
self.assertEquals(1800, len(testFold))
self.assertEquals(7200, len(trainFold))
self.assertEquals(9000, len(items))
trainCounts = [0, 0, 0]
for integer in trainFold:
if integer < 1000:
trainCounts[0] = trainCounts[0] + 1
elif integer < 4000:
trainCounts[1] = trainCounts[1] + 1
else:
trainCounts[2] = trainCounts[2] + 1
self.assertEquals(800, trainCounts[0])
self.assertEquals(2400, trainCounts[1])
self.assertEquals(4000, trainCounts[2])
testCounts = [0, 0, 0]
for integer in testFold:
if integer < 1000:
testCounts[0] = testCounts[0] + 1
elif integer < 4000:
testCounts[1] = testCounts[1] + 1
else:
testCounts[2] = testCounts[2] + 1
self.assertEquals(200, testCounts[0])
self.assertEquals(600, testCounts[1])
self.assertEquals(1000, testCounts[2])
def test_SmallSample2Fold(self):
stratifiedKFoldCrossValidation = StratifiedKFoldCrossValidation(
self.smallSample, 2, 1)
expected3 = [
"7", "9", "10", "8", "6", "22", "16", "28", "30", "20", "11", "27",
"12", "26", "17"
]
self.assertEquals(expected3,
stratifiedKFoldCrossValidation.getTestFold(0))
def execute(self, experiment: Experiment) -> ExperimentPerformance:
result = ExperimentPerformance()
for j in range(self.M):
instanceList = experiment.getDataSet().getInstanceList()
partition = Partition(instanceList, 0.25,
experiment.getParameter().getSeed(), True)
crossValidation = StratifiedKFoldCrossValidation(
Partition(partition.get(1)).getLists(), self.K,
experiment.getParameter().getSeed())
self.runExperiment(experiment.getClassifier(),
experiment.getParameter(), result,
crossValidation, partition.get(0))
return result
def execute(self, experiment: Experiment) -> Performance:
"""
Execute Stratified Single K-fold cross-validation with the given classifier on the given data set using the
given parameters.
PARAMETERS
----------
experiment : Experiment
Experiment to be run.
RETURNS
-------
Performance
A Performance instance.
"""
crossValidation = StratifiedKFoldCrossValidation(
experiment.getDataSet().getClassInstances(), self.__K,
experiment.getParameter().getSeed())
trainSet = InstanceList(crossValidation.getTrainFold(0))
testSet = InstanceList(crossValidation.getTestFold(0))
return experiment.getClassifier().singleRun(experiment.getParameter(),
trainSet, testSet)
def execute(self, experiment: Experiment) -> ExperimentPerformance:
"""
Execute Stratified K-fold cross-validation with the given classifier on the given data set using the given
parameters.
PARAMETERS
----------
experiment : Experiment
Experiment to be run.
RETURNS
-------
ExperimentPerformance
An ExperimentPerformance instance.
"""
result = ExperimentPerformance()
crossValidation = StratifiedKFoldCrossValidation(experiment.getDataSet().getClassInstances(), self.K,
experiment.getParameter().getSeed())
self.runExperiment(experiment.getClassifier(), experiment.getParameter(), result, crossValidation)
return result
def test_SmallSample5Fold(self):
stratifiedKFoldCrossValidation = StratifiedKFoldCrossValidation(
self.smallSample, 5, 1)
expected2 = ["7", "9", "22", "16", "28", "30"]
self.assertEquals(expected2,
stratifiedKFoldCrossValidation.getTestFold(0))
def test_SmallSample10Fold(self):
stratifiedKFoldCrossValidation = StratifiedKFoldCrossValidation(
self.smallSample, 10, 1)
expected1 = ["7", "22", "16"]
self.assertEquals(expected1,
stratifiedKFoldCrossValidation.getTestFold(0))