def add_class_noise(data, noise_level, rnd_seed):
"""adds class Noise
:param data: Orange dataset
:param noise_level:
:param rnd_seed:
:return:
"""
meta_noisy = orange.EnumVariable("noise", values=["no", "yes"])
mid = orange.newmetaid()
while mid in data.domain.getmetas().keys():
mid = orange.newmetaid()
data.domain.addmeta(mid, meta_noisy)
data.addMetaAttribute("noise", "no")
# Generate random indices for noise insertion
percent = float(noise_level) / 100
try:
rnds = int(rnd_seed)
except:
rnds = 0
print "Random Seed:", rnds
orange.setrandseed(rnds)
noise_indices = random.sample(range(len(data)),
int(round(percent * len(data))))
#print "Amount of added noise:", percent*100, "percent (", len(noise_indices), "examples ):"
#print "Random indices for added noise:", noise_indices
className = data.domain.classVar.name
#print "Class name:", className
for index in noise_indices:
data[index]["noise"] = "yes"
temp = data[index][className]
## if len(data.domain.classVar.values) > 2:
# random value + check if it is diferent from the current one
new_label = data.domain.classVar.randomvalue()
while new_label == temp:
new_label = data.domain.classVar.randomvalue()
data[index][className] = new_label
## else:
## # switch the class value
## data[index][className] = data.domain.classVar.nextvalue(data[index][className])
#print "\t", temp, "changed to:", data[index].getclass(), "(", index, ")"
#print "\n"
noise_indices.sort()
return noise_indices, data
def add_class_noise(data, noise_level, rnd_seed):
"""adds class Noise
:param data: Orange dataset
:param noise_level:
:param rnd_seed:
:return:
"""
meta_noisy = orange.EnumVariable("noise", values=["no", "yes"])
mid = orange.newmetaid()
while mid in data.domain.getmetas().keys():
mid = orange.newmetaid()
data.domain.addmeta(mid, meta_noisy)
data.addMetaAttribute("noise", "no")
# Generate random indices for noise insertion
percent = float(noise_level)/100
try:
rnds = int(rnd_seed)
except:
rnds = 0
print "Random Seed:", rnds
orange.setrandseed(rnds)
noise_indices = random.sample(range(len(data)), int(round(percent*len(data))))
#print "Amount of added noise:", percent*100, "percent (", len(noise_indices), "examples ):"
#print "Random indices for added noise:", noise_indices
className = data.domain.classVar.name
#print "Class name:", className
for index in noise_indices:
data[index]["noise"] = "yes"
temp = data[index][className]
## if len(data.domain.classVar.values) > 2:
# random value + check if it is diferent from the current one
new_label = data.domain.classVar.randomvalue()
while new_label == temp:
new_label = data.domain.classVar.randomvalue()
data[index][className] = new_label
## else:
## # switch the class value
## data[index][className] = data.domain.classVar.nextvalue(data[index][className])
#print "\t", temp, "changed to:", data[index].getclass(), "(", index, ")"
#print "\n"
noise_indices.sort()
return noise_indices, data
def entropyDiscretization(data):
"""
Discretizes continuous attributes using the entropy based discretization.
It removes the attributes discretized to a single interval and prints their names.
Arguments: data
Returns: table of examples with discretized atributes. Attributes that are
categorized to a single value (constant) are removed.
"""
orange.setrandseed(0)
tablen = orange.Preprocessor_discretize(
data, method=orange.EntropyDiscretization())
attrlist = []
nrem = 0
for i in tablen.domain.attributes:
if (len(i.values) > 1):
attrlist.append(i)
else:
nrem = nrem + 1
attrlist.append(tablen.domain.classVar)
return tablen.select(attrlist)
selection = orange.MakeRandomIndices2(data, p)
train_data = data.select(selection, 0)
test_data = data.select(selection, 1)
classifiers = []
for l in learners:
classifiers.append(l(train_data))
acc1 = accuracy(test_data, classifiers)
print "%d: %s" % (i + 1, acc1)
for j in range(len(learners)):
acc[j] += acc1[j]
for j in range(len(learners)):
acc[j] = acc[j] / n
return acc
orange.setrandseed(0)
# set up the learners
bayes = orange.BayesLearner()
tree = orngTree.TreeLearner()
#tree = orngTree.TreeLearner(mForPruning=2)
bayes.name = "bayes"
tree.name = "tree"
learners = [bayes, tree]
# compute accuracies on data
data = orange.ExampleTable("voting")
acc = test_rnd_sampling(data, learners)
print "Classification accuracies:"
for i in range(len(learners)):
print learners[i].name, acc[i]
ar = [0.0]*len(learners)
selection = orange.MakeRandomIndicesCV(data, folds=k)
for test_fold in range(k):
train_data = data.select(selection, test_fold, negate=1)
test_data = data.select(selection, test_fold)
classifiers = []
for l in learners:
classifiers.append(l(train_data))
result = aroc(test_data, classifiers)
for j in range(len(learners)):
ar[j] += result[j]
for j in range(len(learners)):
ar[j] = ar[j]/k
return ar
orange.setrandseed(0)
# set up the learners
bayes = orange.BayesLearner()
tree = orngTree.TreeLearner(mForPruning=2)
maj = orange.MajorityLearner()
bayes.name = "bayes"
tree.name = "tree"
maj.name = "majority"
learners = [bayes, tree, maj]
# compute accuracies on data
data = orange.ExampleTable("voting")
acc = cross_validation(data, learners, k=10)
print "Area under ROC:"
for i in range(len(learners)):
print learners[i].name, "%.2f" % acc[i]
