# -*- coding:utf-8 -*-

from numpy import *
import numpy as np
import pandas as pd
from math import log
import operator

#計算數據集的香農熵
def calcShannonEnt(dataSet):
  numEntries=len(dataSet)
  labelCounts={}
  #給所有可能分類創建字典
  for featVec in dataSet:
    currentLabel=featVec[-1]
    if currentLabel not in labelCounts.keys():
      labelCounts[currentLabel]=0
    labelCounts[currentLabel]+=1
  shannonEnt=0.0
  #以2為底數計算香農熵
  for key in labelCounts:
    prob = float(labelCounts[key])/numEntries
    shannonEnt-=prob*log(prob,2)
  return shannonEnt


#對離散變量劃分數據集，取出該特征取值為value的所有樣本
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

#對連續變量劃分數據集，direction規定劃分的方向，
#決定是劃分出小于value的數據樣本還是大于value的數據樣本集
def splitContinuousDataSet(dataSet,axis,value,direction):
  retDataSet=[]
  for featVec in dataSet:
    if direction==0:
      if featVec[axis]>value:
        reducedFeatVec=featVec[:axis]
        reducedFeatVec.extend(featVec[axis+1:])
        retDataSet.append(reducedFeatVec)
    else:
      if featVec[axis]<=value:
        reducedFeatVec=featVec[:axis]
        reducedFeatVec.extend(featVec[axis+1:])
        retDataSet.append(reducedFeatVec)
  return retDataSet

#選擇最好的數據集劃分方式
def chooseBestFeatureToSplit(dataSet,labels):
  numFeatures=len(dataSet[0])-1
  baseEntropy=calcShannonEnt(dataSet)
  bestInfoGain=0.0
  bestFeature=-1
  bestSplitDict={}
  for i in range(numFeatures):
    featList=[example[i] for example in dataSet]
    #對連續型特征進行處理
    if type(featList[0]).__name__=='float' or type(featList[0]).__name__=='int':
      #產生n-1個候選劃分點
      sortfeatList=sorted(featList)
      splitList=[]
      for j in range(len(sortfeatList)-1):
        splitList.append((sortfeatList[j]+sortfeatList[j+1])/2.0)

      bestSplitEntropy=10000
      slen=len(splitList)
      #求用第j個候選劃分點劃分時，得到的信息熵，并記錄最佳劃分點
      for j in range(slen):
        value=splitList[j]
        newEntropy=0.0
        subDataSet0=splitContinuousDataSet(dataSet,i,value,0)
        subDataSet1=splitContinuousDataSet(dataSet,i,value,1)
        prob0=len(subDataSet0)/float(len(dataSet))
        newEntropy+=prob0*calcShannonEnt(subDataSet0)
        prob1=len(subDataSet1)/float(len(dataSet))
        newEntropy+=prob1*calcShannonEnt(subDataSet1)
        if newEntropy
            
              bestInfoGain:
      bestInfoGain=infoGain
      bestFeature=i
  #若當前節點的最佳劃分特征為連續特征，則將其以之前記錄的劃分點為界進行二值化處理
  #即是否小于等于bestSplitValue
  if type(dataSet[0][bestFeature]).__name__=='float' or type(dataSet[0][bestFeature]).__name__=='int':
    bestSplitValue=bestSplitDict[labels[bestFeature]]
    labels[bestFeature]=labels[bestFeature]+'<='+str(bestSplitValue)
    for i in range(shape(dataSet)[0]):
      if dataSet[i][bestFeature]<=bestSplitValue:
        dataSet[i][bestFeature]=1
      else:
        dataSet[i][bestFeature]=0
  return bestFeature

#特征若已經劃分完，節點下的樣本還沒有統一取值，則需要進行投票
def majorityCnt(classList):
  classCount={}
  for vote in classList:
    if vote not in classCount.keys():
      classCount[vote]=0
    classCount[vote]+=1
  return max(classCount)

#主程序，遞歸產生決策樹
def createTree(dataSet,labels,data_full,labels_full):
  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)
  bestFeat=chooseBestFeatureToSplit(dataSet,labels)
  bestFeatLabel=labels[bestFeat]
  myTree={bestFeatLabel:{}}
  featValues=[example[bestFeat] for example in dataSet]
  uniqueVals=set(featValues)
  if type(dataSet[0][bestFeat]).__name__=='str':
    currentlabel=labels_full.index(labels[bestFeat])
    featValuesFull=[example[currentlabel] for example in data_full]
    uniqueValsFull=set(featValuesFull)
  del(labels[bestFeat])
  #針對bestFeat的每個取值，劃分出一個子樹。
  for value in uniqueVals:
    subLabels=labels[:]
    if type(dataSet[0][bestFeat]).__name__=='str':
      uniqueValsFull.remove(value)
    myTree[bestFeatLabel][value]=createTree(splitDataSet\
     (dataSet,bestFeat,value),subLabels,data_full,labels_full)
  if type(dataSet[0][bestFeat]).__name__=='str':
    for value in uniqueValsFull:
      myTree[bestFeatLabel][value]=majorityCnt(classList)
  return myTree

import matplotlib.pyplot as plt
decisionNode=dict(boxstyle="sawtooth",fc="0.8")
leafNode=dict(boxstyle="round4",fc="0.8")
arrow_args=dict(arrowstyle="<-")


#計算樹的葉子節點數量
def getNumLeafs(myTree):
  numLeafs=0
  firstSides = list(myTree.keys())
  firstStr=firstSides[0]
  secondDict=myTree[firstStr]
  for key in secondDict.keys():
    if type(secondDict[key]).__name__=='dict':
      numLeafs+=getNumLeafs(secondDict[key])
    else: numLeafs+=1
  return numLeafs

#計算樹的最大深度
def getTreeDepth(myTree):
  maxDepth=0
  firstSides = list(myTree.keys())
  firstStr=firstSides[0]
  secondDict=myTree[firstStr]
  for key in secondDict.keys():
    if type(secondDict[key]).__name__=='dict':
      thisDepth=1+getTreeDepth(secondDict[key])
    else: thisDepth=1
    if thisDepth>maxDepth:
      maxDepth=thisDepth
  return maxDepth

#畫節點
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)

#畫箭頭上的文字
def plotMidText(cntrPt,parentPt,txtString):
  lens=len(txtString)
  xMid=(parentPt[0]+cntrPt[0])/2.0-lens*0.002
  yMid=(parentPt[1]+cntrPt[1])/2.0
  createPlot.ax1.text(xMid,yMid,txtString)

def plotTree(myTree,parentPt,nodeTxt):
  numLeafs=getNumLeafs(myTree)
  depth=getTreeDepth(myTree)
  firstSides = list(myTree.keys())
  firstStr=firstSides[0]
  cntrPt=(plotTree.x0ff+(1.0+float(numLeafs))/2.0/plotTree.totalW,plotTree.y0ff)
  plotMidText(cntrPt,parentPt,nodeTxt)
  plotNode(firstStr,cntrPt,parentPt,decisionNode)
  secondDict=myTree[firstStr]
  plotTree.y0ff=plotTree.y0ff-1.0/plotTree.totalD
  for key in secondDict.keys():
    if type(secondDict[key]).__name__=='dict':
      plotTree(secondDict[key],cntrPt,str(key))
    else:
      plotTree.x0ff=plotTree.x0ff+1.0/plotTree.totalW
      plotNode(secondDict[key],(plotTree.x0ff,plotTree.y0ff),cntrPt,leafNode)
      plotMidText((plotTree.x0ff,plotTree.y0ff),cntrPt,str(key))
  plotTree.y0ff=plotTree.y0ff+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.x0ff=-0.5/plotTree.totalW
  plotTree.y0ff=1.0
  plotTree(inTree,(0.5,1.0),'')
  plt.show()

df=pd.read_csv('watermelon_4_3.csv')
data=df.values[:,1:].tolist()
data_full=data[:]
labels=df.columns.values[1:-1].tolist()
labels_full=labels[:]
myTree=createTree(data,labels,data_full,labels_full)
print(myTree)
createPlot(myTree)