How do I calculate tree edit distance? [closed]

Answer 1

I made a simple python wrapper (apted.py) for the APTED algorithm using jpype if anyone is interested:

# To use, create a folder named lib next to apted.py, then put APTED.jar into it

import os, os.path, jpype 

global distancePackage
distancePackage = None

global utilPackage
utilPackage = None

def StartJVM():
  # from http://www.gossamer-threads.com/lists/python/python/379020
  root = os.path.abspath(os.path.dirname(__file__)) 
  jpype.startJVM(jpype.getDefaultJVMPath(), 
  "-Djava.ext.dirs=%s%slib" % (root, os.sep))
  global distancePackage
  distancePackage = jpype.JPackage("distance")
  global utilPackage
  utilPackage = jpype.JPackage("util")


def StopJVM():
  jpype.shutdownJVM()


class APTED:
  def __init__(self, delCost, insCost, matchCost):
    global distancePackage
    if distancePackage is None:
      raise Exception("Need to call apted.StartJVM() first")
    self.myApted = distancePackage.APTED(float(delCost), float(insCost), float(matchCost))

  def nonNormalizedTreeDist(self, lblTreeA, lblTreeB):
    return self.myApted.nonNormalizedTreeDist(lblTreeA.myLblTree, lblTreeB.myLblTree)


class LblTree:
  def __init__(self, treeString):
    global utilPackage
    if utilPackage is None:
      raise Exception("Need to call apted.StartJVM() first")

    self.myLblTree = utilPackage.LblTree.fromString(treeString)

'''
# Example usage:

import apted
apted.StartJVM()
aptedDist = apted.APTED(delCost=1, insCost=1, matchCost=1)
treeA = apted.LblTree('{a}')
treeB = apted.LblTree('{b{c}}')
dist = aptedDist.nonNormalizedTreeDist(treeA, treeB)
print dist


# When you are done using apted
apted.StopJVM()
# For some reason it doesn't usually let me start it again and crashes python upon exit when I do this so call only as needed
'''