def testNonExistingDataSet(self):
dataSetName = "not-existing-data-set"
fetcher = DataFetcher()
try:
fetcher.fetchDataSet(dataSetName)
except IOError:
pass
def testDataContainer(self):
dataSetName = 'buffer_dataset'
container = DataFetcher().fetchDataSet(dataSetName)
numberOfExamples = 2
dataVectorLength = 1
self.assertEqual(numberOfExamples, container.getDataSetSize())
self.assertEqual(dataVectorLength, container.getDataVectorLength())
def testDataContainer(self):
dataSetName = 'buffer_dataset'
container = DataFetcher().fetchDataSet(dataSetName)
numberOfExamples = 2
dataVectorLength = 1
self.assertEqual(numberOfExamples, container.getDataSetSize())
self.assertEqual(dataVectorLength, container.getDataVectorLength())
def testTrainBufferPerceptron(self):
dataSetName = 'buffer_dataset'
container = DataFetcher().fetchDataSet(dataSetName)
perceptron = Perceptron(container, 0.1, 15)
perceptron.train()
weightVector = perceptron.getWeightVector()
expectedLength = container.getDataVectorLength() + 1
self.assertEqual(len(weightVector), expectedLength)
def testTrainBufferPerceptron(self):
dataSetName = 'buffer_dataset'
container = DataFetcher().fetchDataSet(dataSetName)
perceptron = Perceptron(container, 0.1, 15)
perceptron.train()
weightVector = perceptron.getWeightVector()
expectedLength = container.getDataVectorLength() + 1
self.assertEqual(len(weightVector), expectedLength)
def classifyDataSet(self, dataSetName, perceptron):
self.log.info('Classifying dataset %s', dataSetName)
container = DataFetcher().fetchDataSet(dataSetName)
labels = container.getLabels()
samples = container.getDataVectors()
errors = 0
for i, sample in enumerate(samples):
cls = perceptron.classify(sample)
if cls != labels[i]:
errors += 1
self.log.info('Misclassified sample %s as %s', labels[i], cls)
setSize = container.getDataSetSize()
errorRate = errors * 1.0 / setSize * 100
self.log.info('Error rate while classifying was %s', errorRate)
def classifyDataSet(self, dataSetName, perceptron):
self.log.info('Classifying dataset %s', dataSetName)
container = DataFetcher().fetchDataSet(dataSetName)
labels = container.getLabels()
samples = container.getDataVectors()
errors = 0
for i, sample in enumerate(samples):
cls = perceptron.classify(sample)
if cls != labels[i]:
errors += 1
self.log.info('Misclassified sample %s as %s', labels[i], cls)
setSize = container.getDataSetSize()
errorRate = errors * 1.0 / setSize * 100
self.log.info('Error rate while classifying was %s', errorRate)
def trainPerceptron(self, dataSetName, alpha, iterations):
container = DataFetcher().fetchDataSet(dataSetName)
perceptron = Perceptron(container, 0.1, 15)
perceptron.train()
return perceptron
