tree_algorithms.append(linear_manhattan)
kdtree_euclid = KDTree()
kdtree_euclid.setDistanceFunction(EuclideanDistance()) # only Euclidean Distance function
tree_algorithms.append(kdtree_euclid)
ball = BallTree()
ball.setDistanceFunction(EuclideanDistance()) # only Euclidean Distance function
tree_algorithms.append(ball)
cover = CoverTree()
cover.setDistanceFunction(EuclideanDistance()) # only Euclidean Distance function
tree_algorithms.append(cover)
data.setClassIndex(data.numAttributes() - 1)
for num in range(1,30,2):
file.write(str(num))
for algoknn in tree_algorithms :
log.write("---------------------------------\nK: " + str(num) + ", Search Algorithm: " + algoknn.__class__.__name__ + "\n")
algo = IBk()
algo.setNearestNeighbourSearchAlgorithm(algoknn)
algo.setKNN(num)
x = time.time()
algo.buildClassifier(data)
log.write("Time to build classifier: " + str(time.time() - x) + "\n")
evaluation = Evaluation(data)
output = PlainText() # plain text output for predictions
output.setHeader(data)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
x = time.time()
#evaluation.evaluateModel(algo, data, [output, attRange, outputDistribution])
evaluation.crossValidateModel(algo, data, 10, rand, [output, attRange, outputDistribution])
tree_algorithms.append(kdtree_euclid)
ball = BallTree()
ball.setDistanceFunction(
EuclideanDistance()) # only Euclidean Distance function
tree_algorithms.append(ball)
cover = CoverTree()
cover.setDistanceFunction(
EuclideanDistance()) # only Euclidean Distance function
tree_algorithms.append(cover)
data.setClassIndex(data.numAttributes() - 1)
for num in range(1, 30, 2):
file.write(str(num))
for algoknn in tree_algorithms:
log.write("---------------------------------\nK: " + str(num) +
", Search Algorithm: " + algoknn.__class__.__name__ + "\n")
algo = IBk()
algo.setNearestNeighbourSearchAlgorithm(algoknn)
algo.setKNN(num)
x = time.time()
algo.buildClassifier(data)
log.write("Time to build classifier: " + str(time.time() - x) + "\n")
evaluation = Evaluation(data)
output = PlainText() # plain text output for predictions
output.setHeader(data)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
x = time.time()
#evaluation.evaluateModel(algo, data, [output, attRange, outputDistribution])
evaluation.crossValidateModel(algo, data, 10, rand,
ball = BallTree()
ball.setDistanceFunction(EuclideanDistance()) # only Euclidean Distance function
tree_algorithms_instance.append(ball)
cover = CoverTree()
cover.setDistanceFunction(EuclideanDistance()) # only Euclidean Distance function
tree_algorithms_instance.append(cover)
for num in range(int(p['knn.initial']),fulltrainset.numInstances(),(fulltrainset.numInstances() / int(p['knn.numdatapoints']))):
filelimit.write(str(num))
trainset = Instances(fulltrainset,0,num) # create training set
trainset.setClassIndex(trainset.numAttributes() - 1)
for algoknn in tree_algorithms_instance :
log.write("---------------------------------\nTraining Set Size: " + str(trainset.numInstances()) + ", Test Set Size: " + str(testset.numInstances()) + ", Full training set size: " + str(fulltrainset.numInstances()) + "\n")
for dataset in [testset, fulltrainset]:
algo = IBk()
algo.setNearestNeighbourSearchAlgorithm(algoknn)
algo.setKNN(int(p['knn.K']))
algo.buildClassifier(trainset)
evaluation = Evaluation(trainset)
output = PlainText() # plain text output for predictions
output.setHeader(trainset)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
x = time.time()
if (int(crossvalidate)):
evaluation.crossValidateModel(algo, dataset, 10, rand, [output, attRange, outputDistribution])
else:
evaluation.evaluateModel(algo, dataset, [output, attRange, outputDistribution])
EuclideanDistance()) # only Euclidean Distance function
tree_algorithms_instance.append(cover)
for num in range(int(p['knn.initial']), fulltrainset.numInstances(),
(fulltrainset.numInstances() / int(p['knn.numdatapoints']))):
filelimit.write(str(num))
trainset = Instances(fulltrainset, 0, num) # create training set
trainset.setClassIndex(trainset.numAttributes() - 1)
for algoknn in tree_algorithms_instance:
log.write("---------------------------------\nTraining Set Size: " +
str(trainset.numInstances()) + ", Test Set Size: " +
str(testset.numInstances()) + ", Full training set size: " +
str(fulltrainset.numInstances()) + "\n")
for dataset in [testset, fulltrainset]:
algo = IBk()
algo.setNearestNeighbourSearchAlgorithm(algoknn)
algo.setKNN(int(p['knn.K']))
algo.buildClassifier(trainset)
evaluation = Evaluation(trainset)
output = PlainText() # plain text output for predictions
output.setHeader(trainset)
buffer = StringBuffer() # buffer to use
output.setBuffer(buffer)
attRange = Range() # no additional attributes output
outputDistribution = Boolean(False) # we don't want distribution
x = time.time()
if (int(crossvalidate)):
evaluation.crossValidateModel(
algo, dataset, 10, rand,
[output, attRange, outputDistribution])
