def __call__(self, examples, weight=0):
if not self.learner:
self.learner = self.instance()
if not hasattr(self, "split") and not hasattr(self, "measure"):
if examples.domain.classVar.varType == orange.VarTypes.Discrete:
measure = orange.MeasureAttribute_gainRatio()
else:
measure = orange.MeasureAttribute_MSE()
self.learner.split.continuousSplitConstructor.measure = measure
self.learner.split.discreteSplitConstructor.measure = measure
tree = self.learner(examples, weight)
if getattr(self, "sameMajorityPruning", 0):
tree = orange.TreePruner_SameMajority(tree)
if getattr(self, "mForPruning", 0):
tree = orange.TreePruner_m(tree, m=self.mForPruning)
return tree
import orange, orngTree, orngStat, orngWrap
learner = orngTree.TreeLearner()
data = orange.ExampleTable("voting")
tuner = orngWrap.TuneMParameters(object=learner,
parameters=[
("minSubset", [2, 5, 10, 20]),
("measure", [
orange.MeasureAttribute_gainRatio(),
orange.MeasureAttribute_gini()
])
],
evaluate=orngStat.AUC)
classifier = tuner(data)
meas.unknownsTreatment = meas.UnknownsToCommon
print fstr % (("- unknowns to common:", ) +
tuple([meas(i, data2) for i in range(attrs)]))
meas.unknownsTreatment = meas.UnknownsAsValue
print fstr % (("- unknowns as value:", ) +
tuple([meas(i, data2) for i in range(attrs)]))
print
print "Information gain"
printVariants(orange.MeasureAttribute_info())
print "Gain ratio"
printVariants(orange.MeasureAttribute_gainRatio())
print "Gini index"
printVariants(orange.MeasureAttribute_gini())
print "Relief"
meas = orange.MeasureAttribute_relief()
print fstr % (
("- no unknowns:", ) + tuple([meas(i, data) for i in range(attrs)]))
print fstr % (
("- with unknowns:", ) + tuple([meas(i, data2) for i in range(attrs)]))
print
print "Cost matrix ((0, 5), (1, 0))"
meas = orange.MeasureAttribute_cost()
meas.cost = ((0, 5), (1, 0))
import orange, orngMisc
data = orange.ExampleTable("lymphography")
findBest = orngMisc.BestOnTheFly(orngMisc.compare2_firstBigger)
for attr in data.domain.attributes:
findBest.candidate((orange.MeasureAttribute_gainRatio(attr, data), attr))
print "%5.3f: %s" % findBest.winner()
findBest = orngMisc.BestOnTheFly(callCompareOn1st = True)
for attr in data.domain.attributes:
findBest.candidate((orange.MeasureAttribute_gainRatio(attr, data), attr))
print "%5.3f: %s" % findBest.winner()
findBest = orngMisc.BestOnTheFly()
for attr in data.domain.attributes:
findBest.candidate(orange.MeasureAttribute_gainRatio(attr, data))
bestIndex = findBest.winnerIndex()
print "%5.3f: %s" % (findBest.winner(), data.domain[bestIndex])
def instance(self):
learner = orange.TreeLearner()
hasSplit = hasattr(self, "split")
if hasSplit:
learner.split = self.split
else:
learner.split = orange.TreeSplitConstructor_Combined()
learner.split.continuousSplitConstructor = orange.TreeSplitConstructor_Threshold(
)
binarization = getattr(self, "binarization", 0)
if binarization == 1:
learner.split.discreteSplitConstructor = orange.TreeSplitConstructor_ExhaustiveBinary(
)
elif binarization == 2:
learner.split.discreteSplitConstructor = orange.TreeSplitConstructor_OneAgainstOthers(
)
else:
learner.split.discreteSplitConstructor = orange.TreeSplitConstructor_Attribute(
)
measures = {
"infoGain": orange.MeasureAttribute_info,
"gainRatio": orange.MeasureAttribute_gainRatio,
"gini": orange.MeasureAttribute_gini,
"relief": orange.MeasureAttribute_relief,
"retis": orange.MeasureAttribute_MSE
}
measure = getattr(self, "measure", None)
if type(measure) == str:
measure = measures[measure]()
if not hasSplit and not measure:
measure = orange.MeasureAttribute_gainRatio()
measureIsRelief = type(measure) == orange.MeasureAttribute_relief
relM = getattr(self, "reliefM", None)
if relM and measureIsRelief:
measure.m = relM
relK = getattr(self, "reliefK", None)
if relK and measureIsRelief:
measure.k = relK
learner.split.continuousSplitConstructor.measure = measure
learner.split.discreteSplitConstructor.measure = measure
wa = getattr(self, "worstAcceptable", 0)
if wa:
learner.split.continuousSplitConstructor.worstAcceptable = wa
learner.split.discreteSplitConstructor.worstAcceptable = wa
ms = getattr(self, "minSubset", 0)
if ms:
learner.split.continuousSplitConstructor.minSubset = ms
learner.split.discreteSplitConstructor.minSubset = ms
if hasattr(self, "stop"):
learner.stop = self.stop
else:
learner.stop = orange.TreeStopCriteria_common()
mm = getattr(self, "maxMajority", 1.0)
if mm < 1.0:
learner.stop.maxMajority = self.maxMajority
me = getattr(self, "minExamples", 0)
if me:
learner.stop.minExamples = self.minExamples
for a in [
"storeDistributions", "storeContingencies", "storeExamples",
"storeNodeClassifier", "nodeLearner", "maxDepth"
]:
if hasattr(self, a):
setattr(learner, a, getattr(self, a))
return learner
def selectAttributes(data, attrContOrder, attrDiscOrder, projections=None):
if data.domain.classVar == None or data.domain.classVar.varType != orange.VarTypes.Discrete:
return ([attr.name for attr in data.domain.attributes], [], 0)
shown = [data.domain.classVar.name]
hidden = []
maxIndex = 0 # initialize outputs
# # both are RELIEF
if attrContOrder == "ReliefF" and attrDiscOrder == "ReliefF":
attrVals = orngFSS.attMeasure(data, orange.MeasureAttribute_relief())
s, h = getTopAttrs(attrVals, 0.95)
return (shown + s, hidden + h, 0)
# # both are NONE
elif attrContOrder == "None" and attrDiscOrder == "None":
for item in data.domain.attributes:
shown.append(item.name)
return (shown, hidden, 0)
# disc and cont attribute list
discAttrs = []
contAttrs = []
for attr in data.domain.attributes:
if attr.varType == orange.VarTypes.Continuous:
contAttrs.append(attr.name)
elif attr.varType == orange.VarTypes.Discrete:
discAttrs.append(attr.name)
###############################
# sort continuous attributes
if attrContOrder == "None":
shown += contAttrs
elif attrContOrder in [
"ReliefF", "Fisher discriminant", "Signal to Noise",
"Signal to Noise For Each Class"
]:
if attrContOrder == "ReliefF":
measure = orange.MeasureAttribute_relief(k=10, m=50)
elif attrContOrder == "Fisher discriminant":
measure = MeasureFisherDiscriminant()
elif attrContOrder == "Signal to Noise":
measure = S2NMeasure()
else:
measure = S2NMeasureMix()
dataNew = data.select(contAttrs + [data.domain.classVar])
attrVals = orngFSS.attMeasure(dataNew, measure)
s, h = getTopAttrs(attrVals, 0.95)
shown += s
hidden += h
else:
print "Unknown value for attribute order: ", attrContOrder
# ###############################
# sort discrete attributes
if attrDiscOrder == "None":
shown += discAttrs
elif attrDiscOrder == "GainRatio" or attrDiscOrder == "Gini" or attrDiscOrder == "ReliefF":
if attrDiscOrder == "GainRatio":
measure = orange.MeasureAttribute_gainRatio()
elif attrDiscOrder == "Gini":
measure = orange.MeasureAttribute_gini()
else:
measure = orange.MeasureAttribute_relief()
dataNew = data.select(discAttrs + [data.domain.classVar])
attrVals = orngFSS.attMeasure(dataNew, measure)
s, h = getTopAttrs(attrVals, 0.95)
shown += s
hidden += h
elif attrDiscOrder == "Oblivious decision graphs":
#shown.append(data.domain.classVar.name)
attrs = getFunctionalList(data)
for item in attrs:
shown.append(item)
for attr in data.domain.attributes:
if attr.name not in shown and attr.varType == orange.VarTypes.Discrete:
hidden.append(attr.name)
else:
print "Unknown value for attribute order: ", attrDiscOrder
return (shown, hidden, maxIndex)
def __call__(self, gen, weightID=0):
selectBest = orngMisc.BestOnTheFly()
for attr in gen.domain.attributes:
selectBest.candidate(self.measure(attr, gen, None, weightID))
bestAttr = gen.domain.attributes[selectBest.winnerIndex()]
classifier = orange.ClassifierByLookupTable(gen.domain.classVar,
bestAttr)
contingency = orange.ContingencyAttrClass(bestAttr, gen, weightID)
for i in range(len(contingency)):
classifier.lookupTable[i] = contingency[i].modus()
classifier.distributions[i] = contingency[i]
classifier.lookupTable[-1] = contingency.innerDistribution.modus()
classifier.distributions[-1] = contingency.innerDistribution
for d in classifier.distributions:
d.normalize()
return classifier
oal = OneAttributeLearner(orange.MeasureAttribute_gainRatio())
c = oal(tab)
print c.variable
print c.variable.values
print c.lookupTable
print c.distributions
for ex in tab:
print "%s ---> %s" % (ex, c(ex))