def distance(self, first: Instance, second: Instance, a0=None, a1=None):
if a0 is None or isinstance(a0, PerformanceStats):
return self.distance(first, second, float("inf"), a0)
elif isinstance(a0, float):
distance = 0
firstNumValues = first.numValues()
secondNumValues = second.numValues()
numAttributes = self.m_Data.numAttributes()
classIndex = self.m_Data.classIndex()
self.validate()
p1 = p2 = 0
while p1 < firstNumValues or p2 < secondNumValues:
if p1 >= firstNumValues:
firstI = numAttributes
else:
firstI = first.index(p1)
if p2 >= secondNumValues:
secondI = numAttributes
else:
secondI = second.index(p2)
if firstI == classIndex:
p1 += 1
continue
if firstI < numAttributes and not self.m_ActiveIndices[firstI]:
p1 += 1
continue
if secondI == classIndex:
p2 += 1
continue
if secondI < numAttributes and not self.m_ActiveIndices[
secondI]:
p2 += 1
continue
if firstI == secondI:
diff = self.difference(firstI, first.valueSparse(p1),
second.valueSparse(p2))
p1 += 1
p2 += 1
elif firstI > secondI:
diff = self.difference(secondI, 0, second.valueSparse(p2))
p2 += 1
else:
diff = self.difference(firstI, first.valueSparse(p1), 0)
p1 += 1
if isinstance(a1, PerformanceStats):
a1.incrCoordCount()
distance = self.updateDistance(distance, diff)
if distance > a0:
return float('inf')
return distance
def updateRanges(self, instance: Instance, ranges: List[List[float]]):
numVals = instance.numValues()
prevIndex = 0
for j in range(numVals):
currIndex = instance.index(j)
while prevIndex < currIndex:
if 0 < ranges[prevIndex][self.R_MIN]:
ranges[prevIndex][self.R_MIN] = 0
ranges[prevIndex][self.R_WIDTH] = ranges[prevIndex][
self.R_MAX] - ranges[prevIndex][self.R_MIN]
if 0 > ranges[prevIndex][self.R_MAX]:
ranges[prevIndex][self.R_MAX] = 0
ranges[prevIndex][self.R_WIDTH] = ranges[prevIndex][
self.R_MAX] - ranges[prevIndex][self.R_MIN]
prevIndex += 1
prevIndex += 1
if not instance.isMissingSparse(j):
val = instance.valueSparse(j)
if val < ranges[currIndex][self.R_MIN]:
ranges[currIndex][self.R_MIN] = val
ranges[currIndex][self.R_WIDTH] = ranges[currIndex][
self.R_MAX] - ranges[currIndex][self.R_MIN]
if val > ranges[currIndex][self.R_MAX]:
ranges[currIndex][self.R_MAX] = val
ranges[currIndex][self.R_WIDTH] = ranges[currIndex][
self.R_MAX] - ranges[currIndex][self.R_MIN]
return ranges
def updateRangesFirst(self, instance: Instance, numAtt: int,
ranges: List[List]):
for i in range(len(ranges)):
for j in range(len(ranges[i])):
ranges[i][j] = 0
numVals = instance.numValues()
for j in range(numVals):
currIndex = instance.index(j)
if not instance.isMissingSparse(j):
return True
return False
