def evaluate(self, Classifier, *args):
proportion = 0
average = 0.0
accuracies = []
performance = Performance()
trainingSet = DataSet()
for num in range(0, len(args[0])):
if args[0][num] == "-t":
trainingSet.load(args[0][num + 1])
if args[0][num] == "-T":
testSet = DataSet()
testSet.load(args[0][num + 1])
if args[0][num] == "-p":
proportion = float(args[0][num + 1])
for items in range(
0,
int(proportion *
len(trainingSet.getExamples().getExamplesList()))):
trainingSet.getExamples().add(
trainingSet.getExamples().getExamplesList()[items])
trainingSet.setAttributes(trainingSet.getAttributes())
if type(Classifier) == ID3:
Classifier.train(trainingSet)
performance = Classifier.classify(testSet)
return str(performance)
else:
print "Error in Evaluator:evaluate"
performance = Classifier.classify(testSet)
return str(performance)
for num in range(0, self.folds):
testSet = DataSet()
trainSet = DataSet()
for items in trainingSet.getExamples().getExamplesList():
randomNum = random.randint(0, self.folds - 1)
if randomNum != num:
testSet.getExamples().add(items)
else:
trainingSet.getExamples().add(items)
testSet.setAttributes(trainingSet.getAttributes())
trainSet.setAttributes(trainingSet.getAttributes())
if (len(trainingSet.attributes.attributes) > 0):
trainSet = trainingSet
Classifier.train(trainSet)
tempPerformance = Classifier.classify(testSet)
accuracies.append(tempPerformance.accuracy)
average += tempPerformance.accuracy
performance += tempPerformance
return str(performance) + " +- " + str(self.stdDev(
accuracies, average))
def evaluate(self, Classifier, *args):
proportion = 0
average = 0.0
accuracies = []
performance = Performance()
trainingSet = DataSet()
for num in range(0, len(args[0])):
if args[0][num] == "-t":
trainingSet.load(args[0][num+1])
if args[0][num] == "-T":
testSet = DataSet()
testSet.load(args[0][num+1])
if args[0][num] == "-p":
proportion = float(args[0][num+1])
for items in range(0, int(proportion * len(trainingSet.getExamples().getExamplesList()))):
trainingSet.getExamples().add(trainingSet.getExamples().getExamplesList()[items])
trainingSet.setAttributes(trainingSet.getAttributes())
if type(Classifier) == ID3:
Classifier.train(trainingSet)
performance = Classifier.classify(testSet)
return str(performance)
else:
print "Error in Evaluator:evaluate"
performance = Classifier.classify(testSet)
return str(performance)
for num in range(0, self.folds):
testSet = DataSet()
trainSet = DataSet()
for items in trainingSet.getExamples().getExamplesList():
randomNum = random.randint(0,self.folds-1)
if randomNum != num:
testSet.getExamples().add(items)
else:
trainingSet.getExamples().add(items)
testSet.setAttributes(trainingSet.getAttributes())
trainSet.setAttributes(trainingSet.getAttributes())
if (len(trainingSet.attributes.attributes) > 0):
trainSet = trainingSet
Classifier.train(trainSet)
tempPerformance = Classifier.classify(testSet)
accuracies.append(tempPerformance.accuracy)
average += tempPerformance.accuracy
performance += tempPerformance
return str(performance) + " +- " + str(self.stdDev(accuracies, average))
print results
return results
if __name__=="__main__":
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import random
import os
print os.getcwd()
ds = DataSet("..//..//data//ml//test_weather.gla")
p = Perceptron(dataset=ds, epochs=10)
print "Perceptron test:", p.classify([0,0,1,1])
p.test(ds.getExamples())
attribute1 = [n for n in xrange(10)]
attribute2a = [random.sample(range(50)[:35],1)[0] for n in xrange(5)]
attribute2b = [random.sample(range(50)[20:],1)[0] for n in xrange(5)]
class0examples = [[attribute1[n], attribute2a[n], 0] for n in xrange(5)]
class1examples = [[attribute1[n], attribute2b[n], 1] for n in xrange(5)]
for exs in class1examples+class0examples:
#print exs
ds.addExample(Factory().example(exs))
class0 = [x.getValues() for x in ds.getExamplesByClass(0)]
class0x = [x[0] for x in class0]
class0y = [x[1] for x in class0]
return results
if __name__ == "__main__":
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import random
import os
print os.getcwd()
ds = DataSet("..//..//data//ml//test_weather.gla")
p = Perceptron(dataset=ds, epochs=10)
print "Perceptron test:", p.classify([0, 0, 1, 1])
p.test(ds.getExamples())
attribute1 = [n for n in xrange(10)]
attribute2a = [random.sample(range(50)[:35], 1)[0] for n in xrange(5)]
attribute2b = [random.sample(range(50)[20:], 1)[0] for n in xrange(5)]
class0examples = [[attribute1[n], attribute2a[n], 0] for n in xrange(5)]
class1examples = [[attribute1[n], attribute2b[n], 1] for n in xrange(5)]
for exs in class1examples + class0examples:
#print exs
ds.addExample(Factory().example(exs))
class0 = [x.getValues() for x in ds.getExamplesByClass(0)]
class0x = [x[0] for x in class0]
class0y = [x[1] for x in class0]
@return integer indicating the class of the unknown data.
"""
types = {
"levenshtein": Distance().levenshtein, "l": Distance().levenshtein, 0: Distance().levenshtein ,
"hamming": Distance().hamming, "h": Distance().hamming, 1: Distance().hamming ,
"euclidean": Distance().euclidean, "e": Distance().euclidean, 2: Distance().euclidean ,
"manhattan": Distance().manhattan, "m": Distance().manhattan, 3: Distance().manhattan ,
"chebyshev": Distance().chebyshev, "c": Distance().chebyshev, 4: Distance().chebyshev
}
results = [types[distanceType](x.getValue(), data) for x in self.trainset]
results = [(i,x) for i,x in enumerate(results)]
kernels = sorted(results, key = lambda x:x[1])[:3]
kernels = [self.trainset[i].getLabel() for i,x in kernels]
kernels = [(n, kernels.count(n)) for n in set(kernels)]
return sorted(kernels, key = lambda x:x[1], reverse = True)[0][0]
if __name__ == "__main__":
from DataSet import DataSet
ds = DataSet("C:\\Users\\a5rjqzz\\Desktop\\Python\\pyClassifiers\\data\\IBk\\sample_set_lang.gla")
bk = IBk()
bk.train(ds.getExamples())
kn = ds.convert("y n n")
cl = bk.classify(kn, 3)
print cl
print ds.getAttributes(1)[-1].getLabel(cl)
class knn(Classifier):
def __init__(self, *args):
super(knn, self).__init__(*args)
self.k = 3
self.instances = DataSet()
self.setOptions(args)
def train(self, inDataSet):
self.instances = inDataSet
def classify(self, input):
neighbors = []
if type(input) == Example:
for index, item in enumerate(self.instances.getExamples().getExamplesList()):
if len(neighbors) < self.k:
tempNeighbor = neighbor()
tempNeighbor.setNeighbor(self.instances.getAttributes().getAttributesList()[self.instances.getAttributes().getClassIndex()].domain[item.values[self.instances.getAttributes().getClassIndex()]], self.distance(input, item))
neighbors.append(tempNeighbor)
else:
highestDist = -1
highestIndex = -1
for num in range(0, len(neighbors)):
if num < len(neighbors)-1:
if neighbors[num].distance >= neighbors[num + 1].distance:
highestDist = neighbors[num].distance
highestIndex = num
else:
highestDist = neighbors[num + 1].distance
highestIndex = num + 1
elif neighbors[num] < highestDist:
highestDist = neighbors[num]
highestIndex = num
if self.distance(input, self.instances.getExamples().getExamplesList()[index]) < highestDist:
newNeighbor = neighbor()
newNeighbor.setNeighbor(self.instances.getAttributes().getAttributesList()[self.instances.getAttributes().getClassIndex()].domain[item.values[self.instances.getAttributes().getClassIndex()]], self.distance(input,item))
neighbors[highestIndex] = newNeighbor
return self.vote(neighbors)
elif type(input) == DataSet:
rightCount = 0
for index, item in enumerate(self.instances.getExamples().getExamplesList()):
if self.classify(self.instances.getExamples().getExamplesList()[index]) == self.instances.getAttributes().getClassAttribute().domain[self.instances.getExamples().getExamplesList()[index].values[self.instances.getExamples().attributes.getClassIndex()]]:
rightCount += 1
performance = Performance()
performance.setPerf(rightCount, len(self.instances.getExamples().getExamplesList()))
return performance
def setOptions(self, arguments):
for num in range(0, len(arguments[0])):
if arguments[0][num] == "-k":
self.k = int(arguments[0][num+1])
elif arguments[0][num] == "-t":
newDataSet = DataSet()
newDataSet.load(arguments[0][num+1])
self.instances = newDataSet
def distance(self, observation, example):
total = 0
for num in range(0, len(observation.attributes.getAttributesList())-1):
if observation.values[num] != example.values[num]:
total += 1
return total
def vote(self, neighbors):
voteDict = {}
for index, items in enumerate(neighbors):
if items.classifier in voteDict.keys():
voteDict[items.classifier] += 1
else:
voteDict[items.classifier] = 1
return max(voteDict, key = voteDict.get)
