def splitCritValue(self,
bags: Distribution,
totalNoInst: float = None,
numerator: float = None):
if totalNoInst is None and numerator is None:
numerator = self.oldEnt(bags) - self.newEnt(bags)
if Utils.equal(numerator, 0):
return float('inf')
denumerator = self.splitEnt(bags)
if Utils.equal(denumerator, 0):
return float('inf')
return denumerator / numerator
elif numerator is None:
res = 0
noUnkown = totalNoInst - bags.total()
if Utils.gr(bags.total(), 0):
for i in range(bags.numBags()):
res = res - self.lnFunc(bags.perBag(i))
res = res - self.lnFunc(noUnkown)
res = res + self.lnFunc(totalNoInst)
return res / math.log(2)
else:
denumerator = self.splitEnt(bags, totalNoInst)
if Utils.equal(denumerator, 0):
return 0
denumerator /= totalNoInst
return numerator / denumerator
def newEnt(self,bags:Distribution):
res=0
for i in range(bags.numBags()):
for j in range(bags.numClasses()):
res=res+self.lnFunc(bags.perClassPerBag(i,j))
res=res-self.lnFunc(bags.perBag(i))
return -(res/math.log(2))
def splitEnt(self, bags: Distribution, totalnoInst: float = None):
if totalnoInst is None:
return super().splitEnt(bags)
res = 0
noUnknown = totalnoInst - bags.total()
if Utils.gr(bags.total(), 0):
for i in range(bags.numBags()):
res = res - self.lnFunc(bags.perBag(i))
res = res - self.lnFunc(noUnknown)
res = res + self.lnFunc(totalnoInst)
return res / math.log(2)
def splitEnt(self,bags:Distribution):
res=0
for i in range(bags.numBags()):
res=res+self.lnFunc(bags.perBag(i))
return (self.lnFunc(bags.total())-res)/math.log(2)