def calcShannonEnt(dataSet):
 NumEntries = len(dataSet)
 labelsCount = {}
 for i in dataSet:
  currentlabel = i[-1]
  if currentlabel not in labelsCount.keys():
   labelsCount[currentlabel]=0
  labelsCount[currentlabel]+=1
 ShannonEnt = 0.0
 for key in labelsCount:
  prob = labelsCount[key]/NumEntries
  ShannonEnt -= prob*log(prob,2)
 return ShannonEnt

def createdataSet():
 #dataSet = [['1','1','yes'],['1','0','no'],['0','1','no'],['0','0','no']]
 dataSet = [[1,1,'yes'],[1,0,'no'],[0,1,'no'],[0,0,'no']]
 labels = ['no surfacing','flippers']
 return dataSet,labels

def splitDataSet(dataSet,axis,value):
 retDataSet = []
 for featVec in dataSet:
  if featVec[axis] == value:
   reducedfeatVec = featVec[:axis]
   reducedfeatVec.extend(featVec[axis+1:])
   retDataSet.append(reducedfeatVec)
 return retDataSet

def choosebestfeatureToSplit(dataSet):
 Numfeatures = len(dataSet)-1
 BaseShannonEnt = calcShannonEnt(dataSet)
 bestInfoGain=0.0
 bestfeature = -1
 for i in range(Numfeatures):
  featlist = [example[i] for example in dataSet]
  featSet = set(featlist)
  newEntropy = 0.0
  for value in featSet:
   subDataSet = splitDataSet(dataSet,i,value)
   prob = len(subDataSet)/len(dataSet)
   newEntropy += prob*calcShannonEnt(subDataSet) 
  infoGain = BaseShannonEnt-newEntropy
  if infoGain>bestInfoGain:
   bestInfoGain=infoGain
   bestfeature = i
 return bestfeature

def majorityCnt(classlist):
 ClassCount = {}
 for vote in classlist:
  if vote not in ClassCount.keys():
   ClassCount[vote]=0
  ClassCount[vote]+=1
 sortedClassCount = sorted(ClassCount.items(),key = operator.itemgetter(1),reverse = True)
 return sortedClassCount[0][0]

def createTrees(dataSet,labels):
 classList = [example[-1] for example in dataSet]
 if classList.count(classList[0]) == len(classList):
  return classList[0]
 if len(dataSet[0])==1:
  return majorityCnt(classList)
 bestfeature = choosebestfeatureToSplit(dataSet)
 bestfeatureLabel = labels[bestfeature]
 myTree = {bestfeatureLabel:{}}
 del(labels[bestfeature])
 featValue = [example[bestfeature] for example in dataSet]
 uniqueValue = set(featValue)
 for value in uniqueValue:
  subLabels = labels[:]
  myTree[bestfeatureLabel][value] = createTrees(splitDataSet(dataSet,bestfeature,value),subLabels)
 return myTree

import matplotlib.pyplot as plt
decisionNode = dict(boxstyle = 'sawtooth',fc = '0.8')
leafNode = dict(boxstyle = 'sawtooth',fc = '0.8')
arrow_args = dict(arrowstyle = '<-')

def plotNode(nodeTxt,centerPt,parentPt,nodeType):
 createPlot.ax1.annotate(nodeTxt,xy = parentPt,xycoords = 'axes fraction',\
       xytext = centerPt,textcoords = 'axes fraction',\
       va = 'center',ha = 'center',bbox = nodeType,\
       arrowprops = arrow_args)
 
def createPlot():
 fig = plt.figure(1,facecolor = 'white')
 fig.clf()
 createPlot.ax1 = plt.subplot(111,frameon = False)
 plotNode('test1',(0.5,0.1),(0.1,0.5),decisionNode)
 plotNode('test2',(0.8,0.1),(0.3,0.8),leafNode)
 plt.show()

def getNumleafs(myTree):
 numLeafs=0
 key_sorted= sorted(myTree.keys())
 firstStr = key_sorted[0]
 secondDict = myTree[firstStr]
 for key in secondDict.keys():
  if type(secondDict[key]).__name__=='dict':
   numLeafs+=getNumleafs(secondDict[key])
  else:
   numLeafs+=1
 return numLeafs

def getTreeDepth(myTree):
 maxdepth=0
 key_sorted= sorted(myTree.keys())
 firstStr = key_sorted[0]
 secondDict = myTree[firstStr]
 for key in secondDict.keys():
  if type(secondDict[key]).__name__ == 'dict':
   thedepth=1+getTreeDepth(secondDict[key])
  else:
   thedepth=1
  if thedepth>maxdepth:
   maxdepth=thedepth
 return maxdepth

def plotMidText(cntrPt,parentPt,txtString):
 xMid = (parentPt[0]-cntrPt[0])/2.0+cntrPt[0]
 yMid = (parentPt[1]-cntrPt[1])/2.0+cntrPt[1]
 createPlot.ax1.text(xMid,yMid,txtString)
 
def plotTree(myTree,parentPt,nodeTxt):
 numLeafs = getNumleafs(myTree)
 depth = getTreeDepth(myTree)
 key_sorted= sorted(myTree.keys())
 firstStr = key_sorted[0]
 cntrPt = (plotTree.xOff+(1.0+float(numLeafs))/2.0/plotTree.totalW,plotTree.yOff)
 plotMidText(cntrPt,parentPt,nodeTxt)
 plotNode(firstStr,cntrPt,parentPt,decisionNode)
 secondDict = myTree[firstStr]
 plotTree.yOff -= 1.0/plotTree.totalD
 for key in secondDict.keys():
  if type(secondDict[key]).__name__ == 'dict':
   plotTree(secondDict[key],cntrPt,str(key))
  else:
   plotTree.xOff+=1.0/plotTree.totalW
   plotNode(secondDict[key],(plotTree.xOff,plotTree.yOff),cntrPt,leafNode)
   plotMidText((plotTree.xOff,plotTree.yOff),cntrPt,str(key))
 plotTree.yOff+=1.0/plotTree.totalD
 
def createPlot(inTree):
 fig = plt.figure(1,facecolor = 'white')
 fig.clf()
 axprops = dict(xticks = [],yticks = [])
 createPlot.ax1 = plt.subplot(111,frameon = False,**axprops)
 plotTree.totalW = float(getNumleafs(inTree))
 plotTree.totalD = float(getTreeDepth(inTree))
 plotTree.xOff = -0.5/ plotTree.totalW; plotTree.yOff = 1.0
 plotTree(inTree,(0.5,1.0),'')
 plt.show()