def test_normalize(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution(0, d)
dist2 = orange.Distribution(dist)
dist.normalize()
self.assertTrue(
all(x == y / 150 for x, y in zip(dist.values(), dist2.values())))
def test_discrete(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution(d.domain.class_var, d)
cc = orange.RandomClassifier(d.domain.class_var)
self.assertEqual(cc.probabilities.variable, cc.class_var)
cc2 = orange.RandomClassifier(None, dist)
self.assertEqual(cc2.class_var, d.domain.class_var)
self.assertEqual(cc2.probabilities.variable, cc2.class_var)
self.assertEqual(id(cc2.probabilities), id(dist))
self.assertTrue(all(x==50 for x in cc2.probabilities))
for cl in [cc, cc2]:
for e in d[0:150:20]:
anss = set()
for i in range(5):
anss.add(cl(e))
self.assertEqual(len(anss), 1)
anss = set()
for e in d:
anss.add(cl(e))
self.assertEqual(len(anss), 3)
for e in d[0:150:20]:
self.assertTrue(all(x==50 for x in cc2(e, orange.Classifier.GetProbabilities)))
self.assertRaises(TypeError, orange.RandomClassifier, dist)
self.assertRaises(ValueError, orange.RandomClassifier, None, orange.DiscDistribution())
self.assertRaises(ValueError, orange.RandomClassifier, d.domain[1], orange.Distribution(d.domain[0]))
def test_pickle(self):
import pickle
d = orange.ExampleTable("iris")
dist = orange.Distribution(d.domain[0], d)
cc = orange.ConstantClassifier(dist)
s = pickle.dumps(cc)
cc2 = pickle.loads(s)
self.assertEqual(cc.class_var, cc2.class_var)
self.assertEqual(cc.default_val, cc2.default_val)
self.assertEqual(cc.default_distribution, cc2.default_distribution)
cc.default_val = 42
s = pickle.dumps(cc)
cc2 = pickle.loads(s)
self.assertEqual(cc.default_val, cc2.default_val)
dist = orange.Distribution(d.domain.class_var, d)
cc = orange.ConstantClassifier(dist)
s = pickle.dumps(cc)
cc2 = pickle.loads(s)
self.assertEqual(cc.class_var, cc2.class_var)
self.assertEqual(cc.default_val, cc2.default_val)
self.assertEqual(cc.default_distribution, cc2.default_distribution)
cc.default_val = 1
s = pickle.dumps(cc)
cc2 = pickle.loads(s)
self.assertEqual(cc.default_val, cc2.default_val)
def test_hash(self):
d = orange.ExampleTable("zoo")
disc = orange.Distribution("type", d)
disc2 = orange.Distribution(d.domain.classVar, d)
self.assertEqual(hash(disc), hash(disc2))
disc2[0] += 1
self.assertNotEqual(hash(disc), hash(disc2))
def t2est_discrete(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution(d.domain.class_var, d)
cc = orange.ConstantClassifier(d.domain.class_var)
self.assertEqual(cc.class_var, d.domain.class_var)
self.assertEqual(cc.default_distribution.variable, cc.class_var)
cc2 = orange.ConstantClassifier(dist)
self.assertEqual(cc2.class_var, d.domain.class_var)
self.assertEqual(cc2.default_distribution.variable, cc2.class_var)
self.assertEqual(id(cc2.default_distribution), id(dist))
self.assertTrue(all(x==50 for x in cc2.default_distribution))
cc3 = orange.ConstantClassifier(d.domain.class_var, None, dist)
self.assertEqual(cc3.class_var, d.domain.class_var)
self.assertEqual(cc3.default_distribution.variable, cc3.class_var)
self.assertEqual(id(cc3.default_distribution), id(dist))
self.assertTrue(all(x==50 for x in cc3.default_distribution))
cc4 = orange.ConstantClassifier(d.domain.class_var, "Iris-setosa", dist)
self.assertEqual(cc4.class_var, d.domain.class_var)
self.assertEqual(cc4.default_distribution.variable, cc3.class_var)
self.assertEqual(id(cc4.default_distribution), id(dist))
self.assertTrue(all(x==50 for x in cc4.default_distribution))
for cl in [cc, cc2, cc3]:
for e in d[0:150:20]:
anss = set()
for i in range(5):
anss.add(cl(e))
self.assertEqual(len(anss), 1)
anss = set()
for e in d:
anss.add(cl(e))
self.assertEqual(len(anss), 3)
for e in d[0:150:20]:
anss = set()
for i in range(5):
self.assertEqual(cc4(e), "Iris-setosa")
for cl in [cc2, cc3, cc4]:
for e in d[0:150:20]:
self.assertTrue(all(x==50 for x in cl(e, orange.Classifier.GetProbabilities)))
self.assertRaises(TypeError, orange.ConstantClassifier, d.domain.class_var, dist)
self.assertRaises(ValueError, orange.ConstantClassifier, None, "?", orange.DiscDistribution())
self.assertRaises(ValueError, orange.ConstantClassifier, d.domain[1], "?", orange.Distribution(d.domain[0]))
cc4.default_distribution = [50, 50, 50]
self.assertEqual(list(cc4.default_distribution), [50, 50, 50])
cc5 = orange.ConstantClassifier(d.domain.class_var, "Iris-setosa", [50, 50, 50])
self.assertEqual(list(cc5.default_distribution), [50, 50, 50])
def test():
x = data.domain.attributes[1]
y = data.domain.attributes[2]
c = data.domain.classVar
print "H(%s) = %5.5f" % (x.name, _entropy(p2f(orange.Distribution(x, data))))
print "H(%s) = %5.5f" % (y.name, _entropy(p2f(orange.Distribution(y, data))))
print "H(%s,%s)= %5.5f" % (x.name, y.name, joint_entropy(x, y, data))
print "I(%s;%s)= %5.5f" % (x.name, y.name, mutual_information(x, y, data))
print "H(%s|%s)= %5.5f" % (x.name, c.name, mutual_information(x, c, data))
print "InfoGain = %5.5f" % orange.MeasureAttribute_info(x, data)
def test_construction(self):
d = orange.ExampleTable("zoo")
self.assertRaises(TypeError, orange.DiscDistribution, zip(d.domain["type"].values, self.freqs))
disc = orange.Distribution("type", d)
disc7 = orange.DiscDistribution(self.freqs)
self.assertEqual(disc, disc7)
disc1 = orange.Distribution(d.domain.classVar)
self.assertTrue(isinstance(disc1, orange.DiscDistribution))
def test_hash(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution("sepal length", d)
dist2 = orange.Distribution(dist)
self.assertEqual(hash(dist), hash(dist2))
dist2[4.4] += 1
self.assertNotEqual(hash(dist), hash(dist2))
dist2[4.4] -= 1
self.assertEqual(hash(dist), hash(dist2))
dist2[42] = 2011
self.assertNotEqual(hash(dist), hash(dist2))
def test_fromExamples(self):
d = orange.ExampleTable("zoo")
disc = orange.Distribution("type", d)
disc2 = orange.Distribution(d.domain.classVar, d)
self.assertEqual(disc, disc2)
disc3 = orange.Distribution(len(d.domain.attributes), d)
self.assertEqual(disc, disc3)
disc4 = orange.Distribution(-1, d)
self.assertEqual(disc, disc4)
disc5 = orange.get_class_distribution(d)
self.assertEqual(disc, disc5)
def test_classAttr_cont(self):
d = orange.ExampleTable("iris")
cd = orange.get_class_distribution(d)
ad = orange.Distribution(0, d)
cont = orange.ContingencyClassAttr(0, d)
fv = cont[0].keys()[0]
self.assertEqual(cont.inner_distribution, ad)
self.assertEqual(cont.outer_distribution, cd)
self.assertEqual(len(cont), len(cd))
s = pickle.dumps(cont)
cont2 = pickle.loads(s)
self.assertEqual(cont.innerDistribution, cont2.innerDistribution)
self.assertEqual(cont.innerVariable, cont2.innerVariable)
self.assertEqual(cont.outerDistribution, cont2.outerDistribution)
self.assertEqual(cont.outerVariable, cont2.outerVariable)
self.assertEqual(cont[0], cont2[0])
cont.normalize()
self.assertAlmostEqual(sum(cont.p_attr(0).values()), 1.0)
self.assertEqual(cont.p_attr(0)[fv], cont.p_attr(fv, 0))
self.assertEqual(cont.p_attr(0)[fv], cont2.p_attr(fv, 0)/cont2.p_attr(0).abs)
x = cont[0][0]
cont.add_var_class(0, 0, 0.5)
self.assertEqual(x+0.5, cont[0][0])
self.assertEqual(cont[fv][0], cont[fv,0])
with self.assertRaises(IndexError):
cont["?"]
def test_random(self):
d = orange.ExampleTable("zoo")
disc = orange.Distribution("type", d)
ans = set()
for i in range(1000):
ans.add(int(disc.random()))
self.assertEqual(ans, set(range(len(d.domain.classVar.values))))
def test_continuous(self):
d = orange.ExampleTable("iris")
dom2 = orange.Domain(d.domain.attributes)
d = orange.ExampleTable(dom2, d)
self.assertEqual(d.domain.class_var.var_type, orange.Variable.Type.Continuous)
dist = orange.Distribution(d.domain.class_var, d)
cc = orange.RandomClassifier(d.domain.class_var)
self.assertEqual(cc.class_var, d.domain.class_var)
self.assertEqual(cc.probabilities.variable, cc.class_var)
self.assertRaises(ValueError, cc, d[0])
cc2 = orange.RandomClassifier(None, dist)
self.assertEqual(cc2.class_var, d.domain.class_var)
self.assertEqual(cc2.probabilities.variable, cc2.class_var)
self.assertEqual(id(cc2.probabilities), id(dist))
for e in d[0:150:20]:
anss = set()
for i in range(5):
anss.add(cc2(e))
self.assertEqual(len(anss), 1)
anss = set()
for e in d:
anss.add(cc2(e))
self.assertGreater(len(anss), 10)
def filterAndStore(self):
self.examples = self.filter(self.data) # set examples
self.classifier = self.learner(self.examples) # set classifier
distribution = [0.0] * len(self.data.domain.classVar.values)
self.complexity = len(self.filter.conditions) # set rule complexity
if len(self.examples) > 0:
for d in self.examples:
distribution[int(d.getclass())] += 1
distribution = map(lambda d: d / len(self.examples), distribution)
self.classDistribution = orange.Distribution(
distribution) # set distribution
self.TP = self.examples.filter(
{self.examples.domain.classVar: self.targetClass})
self.FP = self.examples.filter(
{self.examples.domain.classVar: self.targetClass}, negate=1)
# self.TP = filter(lambda e: e.getclass()==self.targetClass, self.examples) # True positives
# self.FP = filter(lambda e: e.getclass()!=self.targetClass, self.examples) # flase positives
TPlen = len(self.TP) * 1.0
self.quality = TPlen / (len(
self.FP) + self.g) # set rule quality: generalization quocient
self.support = 1.0 * len(self.examples) / len(
self.data) # set rule support
self.confidence = TPlen / len(self.examples)
else:
self.classDistribution = distribution
self.TP = []
self.FP = []
self.quality = 0 # set rule quality: generalization kvocient
self.support = 0 # set rule support
def err(condDist, att, value, targetClass, priorError, data):
sumE = sum(condDist)
valueE = condDist[targetClass]
distAtt = orange.Distribution(att, data)
inf = distAtt[value] * (valueE / sumE) * (1 - valueE / sumE)
inf = max(inf, aproxZero)
var = max(1 / inf - priorError * priorError, 0)
return (math.sqrt(var))
def test_random(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution(0, d)
self.assertTrue(dist.random() in dist.keys())
rands = set()
for i in range(100):
rands.add(float(dist.random()))
self.assertTrue(len(rands) > 1)
def __call__(self, data, weight=0):
(X, y) = self.createArrayData(data)
exTable = orange.ExampleTable(data.domain)
for id, ex in self.anch_examples:
exTable.extend(orange.ExampleTable(ex, data.domain))
(X_anch, y_anch) = self.createArrayData(exTable)
betas = array([0.0] * (len(data.domain.attributes) + 1))
likelihood, betas = self.estimateBeta(X, y, betas, [0] * (len(betas)),
X_anch, y_anch)
# get attribute groups atGroup = [(startIndex, number of values), ...)
ats = data.domain.attributes
atVec = reduce(
lambda x, y: x + [(y, not y == x[-1][0])],
[a.getValueFrom and a.getValueFrom.whichVar or a for a in ats],
[(ats[0].getValueFrom and ats[0].getValueFrom.whichVar
or ats[0], 0)])[1:]
atGroup = [[0, 0]]
for v_i, v in enumerate(atVec):
if v[1] == 0: atGroup[-1][1] += 1
else: atGroup.append([v_i, 1])
# compute zero values for attributes
sumB = 0.
for ag in atGroup:
X_temp = concatenate((X[:, :ag[0] + 1], X[:, ag[0] + 1 + ag[1]:]),
1)
if X_anch:
X_anch_temp = concatenate(
(X_anch[:, :ag[0] + 1], X_anch[:, ag[0] + 1 + ag[1]:]), 1)
else:
X_anch_temp = X_anch
## print "1", concatenate((betas[:i+1],betas[i+2:]))
## print "2", betas
likelihood_temp, betas_temp = self.estimateBeta(
X_temp, y,
concatenate((betas[:ag[0] + 1], betas[ag[0] + ag[1] + 1:])),
[0] + [1] * (len(betas) - 1 - ag[1]), X_anch_temp, y_anch)
print "finBetas", betas, betas_temp
print "betas", betas[0], betas_temp[0]
sumB += betas[0] - betas_temp[0]
apriori = orange.Distribution(data.domain.classVar, data)
aprioriProb = apriori[0] / apriori.abs
print "koncni rezultat", sumB, math.log(
(1 - aprioriProb) / aprioriProb), betas[0]
beta = []
beta_se = []
print "likelihood2", likelihood
for i in range(len(betas)):
beta.append(betas[i])
beta_se.append(0.0)
return (self.OK, beta, beta_se, 0)
def __init__(self, rules=None, examples=None, weightID=0, **argkw):
self.rules = rules
self.examples = examples
self.weightID = weightID
self.classVar = examples.domain.classVar if examples is not None else None
self.__dict__.update(argkw)
if examples is not None:
self.prior = orange.Distribution(examples.domain.classVar,
examples)
def entropy(x, data):
"""entropy of an attribute x from dataset data"""
if type(x)==orange.EnumVariable:
return _entropy(p2f(orange.Distribution(x, data)))
if type(x)==list:
if len(x)==2: # joint entropy of a pair of attributes
c = orange.ContingencyAttrAttr(x, y, data)
return _entropy(p2f(flatten(c)))
else: # joint entropy of for a set of attributes
pass
def add_sub_rules(rules, examples, weight, learner, dists):
apriori = orange.Distribution(examples.domain.classVar, examples, weight)
newRules = orange.RuleList()
for r in rules:
newRules.append(r)
# loop through rules
for r in rules:
tmpList = orange.RuleList()
tmpRle = r.clone()
tmpRle.filter.conditions = []
tmpRle.parentRule = None
tmpRle.filterAndStore(examples, weight, r.classifier.defaultVal)
tmpList.append(tmpRle)
while tmpList and len(tmpList[0].filter.conditions) <= len(
r.filter.conditions):
tmpList2 = orange.RuleList()
for tmpRule in tmpList:
# evaluate tmpRule
oldREP = learner.ruleFinder.evaluator.returnExpectedProb
learner.ruleFinder.evaluator.returnExpectedProb = False
learner.ruleFinder.evaluator.evDistGetter.dists = createEVDistList(
dists[int(r.classifier.defaultVal)])
tmpRule.quality = learner.ruleFinder.evaluator(
tmpRule, examples, weight, r.classifier.defaultVal,
apriori)
learner.ruleFinder.evaluator.returnExpectedProb = oldREP
# if rule not in rules already, add it to the list
if not True in [rules_equal(ri, tmpRule)
for ri in newRules] and len(
tmpRule.filter.conditions
) > 0 and tmpRule.quality > apriori[
r.classifier.defaultVal] / apriori.abs:
newRules.append(tmpRule)
# create new tmpRules, set parent Rule, append them to tmpList2
if not True in [rules_equal(ri, tmpRule) for ri in newRules]:
for c in r.filter.conditions:
tmpRule2 = tmpRule.clone()
tmpRule2.parentRule = tmpRule
tmpRule2.filter.conditions.append(c)
tmpRule2.filterAndStore(examples, weight,
r.classifier.defaultVal)
if tmpRule2.classDistribution.abs < tmpRule.classDistribution.abs:
tmpList2.append(tmpRule2)
tmpList = tmpList2
for cl in examples.domain.classVar:
tmpRle = orange.Rule()
tmpRle.filter = orange.Filter_values(domain=examples.domain)
tmpRle.parentRule = None
tmpRle.filterAndStore(examples, weight, int(cl))
tmpRle.quality = tmpRle.classDistribution[int(
cl)] / tmpRle.classDistribution.abs
newRules.append(tmpRle)
return newRules
def data_center(data):
"""Return the central - average - point in the data set"""
atts = data.domain.attributes
astats = orange.DomainBasicAttrStat(data)
center = [astats[a].avg if a.varType == orange.VarTypes.Continuous \
else max(enumerate(orange.Distribution(a, data)), key=lambda x:x[1])[0] if a.varType == orange.VarTypes.Discrete
else None
for a in atts]
if data.domain.classVar:
center.append(0)
return orange.Example(data.domain, center)
def test_construction(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution("sepal length", d)
g = orange.GaussianDistribution(dist)
self.assertAlmostEqual(g.average(), dist.average())
self.assertAlmostEqual(g.modus(), dist.average())
self.assertAlmostEqual(g.var(), dist.var())
self.assertAlmostEqual(g.dev(), dist.dev())
g2 = orange.GaussianDistribution(dist.average(), dist.dev())
self.assertEqual(g, g2)
def test_add(self):
d = orange.ExampleTable("zoo")
disc = orange.Distribution("type", d)
disc2 = orange.Distribution(d.domain.classVar)
for ex in d:
disc2.add(ex[-1])
self.assertEqual(disc, disc2)
disc3 = orange.Distribution(d.domain.classVar)
for ex in d:
disc3.add(int(ex[-1]), 1.0)
self.assertEqual(disc, disc3)
disc4 = orange.Distribution(d.domain.classVar)
for ex in d:
disc4.add(float(ex[-1]), 1.0)
self.assertEqual(disc, disc4)
disc4.add(0, 1e-8)
self.assertNotEqual(disc4[0], disc[0])
def test_stat(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution(0, d)
self.assertAlmostEqual(dist.average(), 5.843333333)
self.assertAlmostEqual(dist.dev(), 0.8253012, 4)
self.assertEqual(dist.percentile(50), 5.8)
self.assertRaises(ValueError, dist.percentile, -5)
self.assertRaises(ValueError, dist.percentile, 105)
self.assertEqual(dist.density(5.0), 10)
self.assertEqual(dist.density(4.95), 8)
def test_add(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution(0, d)
dist2 = orange.Distribution(d.domain[0])
for ex in d:
dist2.add(ex[0])
self.assertEqual(dist, dist2)
dist3 = orange.ContDistribution()
for ex in d:
dist3.add(ex[0])
self.assertEqual(dist, dist3)
dist4 = orange.ContDistribution()
for ex in d:
dist4.add(ex[0], 1.0)
self.assertEqual(dist, dist4)
dist4.add(0, 1e-8)
self.assertNotEqual(dist4[0], dist[0])
def t2est_continuous(self):
d = orange.ExampleTable("iris")
dom2 = orange.Domain(d.domain.attributes)
d = orange.ExampleTable(dom2, d)
self.assertEqual(d.domain.class_var.var_type, orange.Variable.Continuous)
dist = orange.Distribution(d.domain.class_var, d)
cc = orange.ConstantClassifier(d.domain.class_var)
self.assertEqual(cc.class_var, d.domain.class_var)
self.assertEqual(cc.default_distribution.variable, cc.class_var)
cc2 = orange.ConstantClassifier(dist)
self.assertEqual(cc2.class_var, d.domain.class_var)
self.assertEqual(cc2.default_distribution.variable, cc2.class_var)
self.assertEqual(id(cc2.default_distribution), id(dist))
cc3 = orange.ConstantClassifier(d.domain.class_var, None, dist)
self.assertEqual(cc3.class_var, d.domain.class_var)
self.assertEqual(cc3.default_distribution.variable, cc3.class_var)
self.assertEqual(id(cc3.default_distribution), id(dist))
cc4 = orange.ConstantClassifier(d.domain.class_var, 5, dist)
self.assertEqual(cc4.class_var, d.domain.class_var)
self.assertEqual(cc4.default_distribution.variable, cc3.class_var)
self.assertEqual(id(cc4.default_distribution), id(dist))
for cl in [cc2, cc3]:
for e in d:
self.assertEqual(cl(e), dist.average())
for e in d:
self.assertEqual(cc4(e), 5)
self.assertRaises(TypeError, orange.ConstantClassifier, d.domain.class_var, dist)
self.assertRaises(ValueError, orange.ConstantClassifier, None, "?", orange.DiscDistribution())
self.assertRaises(ValueError, orange.ConstantClassifier, d.domain[1], "?", orange.Distribution(d.domain[0]))
cc4.default_distribution = [50, 50, 50]
self.assertEqual(list(cc4.default_distribution), [50, 50, 50])
def test_construction(self):
d = orange.ExampleTable("iris")
dist = orange.Distribution("sepal length", d)
import collections
dictdist = collections.defaultdict(float)
for e in d:
dictdist[float(e["sepal length"])] += 1
self.assertEqual(dist, dictdist)
dist2 = orange.ContDistribution(dictdist)
self.assertEqual(dist, dist2)
def __call__(self, examples, weight=0, fulldata=0):
if examples.domain.classVar.varType != 1:
raise "Logistic learner only works with discrete class."
translate = orng2Array.DomainTranslation(self.translation_mode_d,
self.translation_mode_c)
if fulldata != 0:
translate.analyse(fulldata, weight, warning=0)
else:
translate.analyse(examples, weight, warning=0)
translate.prepareLR()
mdata = translate.transform(examples)
# get the attribute importances
t = examples
importance = []
for i in xrange(len(t.domain.attributes)):
qi = orange.MeasureAttribute_relief(t.domain.attributes[i], t)
importance.append((qi, i))
importance.sort()
freqs = list(orange.Distribution(examples.domain.classVar, examples))
s = 1.0 / sum(freqs)
freqs = [x * s for x in freqs] # normalize
rl = RobustBLogisticLearner(regularization=self.regularization)
if len(examples.domain.classVar.values) > 2:
## form several experiments:
# identify the most frequent class value
tfreqs = [(freqs[i], i) for i in xrange(len(freqs))]
tfreqs.sort()
base = tfreqs[-1][1] # the most frequent class
classifiers = []
for i in xrange(len(tfreqs) - 1):
# edit the translation
alter = tfreqs[i][1]
cfreqs = [tfreqs[-1][0], tfreqs[i][0]] # 0=base,1=alternative
# edit all the examples
for j in xrange(len(mdata)):
c = int(examples[j].getclass())
if c == alter:
mdata[j][-1] = 1
else:
mdata[j][-1] = 0
r = rl(mdata, translate, importance, cfreqs)
classifiers.append(r)
return ArrayLogisticClassifier(classifiers, translate,
tfreqs, examples.domain.classVar,
len(mdata))
else:
r = rl(mdata, translate, importance, freqs)
return BasicLogisticClassifier(r, translate)
def maxNu(examples):
""" Given example table compute the maximum nu parameter for Nu_SVC
"""
nu = 1.0
dist = list(orange.Distribution(examples.domain.classVar, examples))
def pairs(seq):
for i, n1 in enumerate(seq):
for n2 in seq[i + 1:]:
yield n1, n2
return min([
2.0 * min(n1, n2) / (n1 + n2)
for n1, n2 in pairs(dist) if n1 != 0 and n2 != 0
] + [nu])
def __call__(self, examples, weight=0):
supervisedClassCheck(examples)
rules = orange.RuleList()
self.ruleStopping.apriori = orange.Distribution(
examples.domain.classVar, examples)
progress = getattr(self, "progressCallback", None)
if progress:
progress.start = 0.0
progress.end = 0.0
distrib = orange.Distribution(examples.domain.classVar, examples,
weight)
distrib.normalize()
for targetClass in examples.domain.classVar:
if progress:
progress.start = progress.end
progress.end += distrib[targetClass]
self.targetClass = targetClass
cl = orange.RuleLearner.__call__(self, examples, weight)
for r in cl.rules:
rules.append(r)
if progress:
progress(1.0, None)
return CN2UnorderedClassifier(rules, examples, weight)
def data_center(data):
"""
Returns a center of the instances in the data set (average across data instances for continuous attributes, most frequent value for discrete attributes).
"""
atts = data.domain.attributes
astats = orange.DomainBasicAttrStat(data)
center = [astats[a].avg if a.varType == orange.VarTypes.Continuous \
# else max(enumerate(orange.Distribution(a, data)), key=lambda x:x[1])[0] if a.varType == orange.VarTypes.Discrete
else _modus(orange.Distribution(a, data)) if a.varType == orange.VarTypes.Discrete
else None
for a in atts]
if data.domain.classVar:
center.append(0)
return orange.Example(data.domain, center)
