#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
@title:决策树
"""
import operator
#计算给定数据集的香农熵
from math import log
def calcShannonEnt(dataSet):
numEntries = len(dataSet)
labelCounts = {}
for featVec in dataSet:
currentLabel = featVec[-1]
if currentLabel not in labelCounts.keys():
labelCounts[currentLabel] = 0
labelCounts[currentLabel] += 1
shannonEnt = 0.0
for keys in labelCounts:
prob = float(labelCounts[keys])/numEntries
shannonEnt -= prob*log(prob,2)
return shannonEnt
#创建数据集
def createDataSet():
dataSet = [[1, 1, 'yes'],
[1, 1, 'yes'],
[1, 0, 'no'],
[0, 1, 'no'],
[0, 1, 'no']]
labels = ['no surfacing', 'flippers']
return dataSet, labels
#按照给定特征划分数据集
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
#选择最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet):
numFeatures = len(dataSet[0]) - 1
baseEntropy = calcShannonEnt(dataSet) #计算原始香农熵
bestInfoGain = 0.0
bestFeature = -1
for i in range(numFeatures):
featList = [example[i] for example in dataSet] #将第i个特征的值都取出
uniqueVals = set(featList) #将特征的所有可能取值列出来
newEntropy = 0.0
for value in uniqueVals: #遍历特征的每个取值,调用函数splitDataSet划分数据集计算信息熵
subDataSet = splitDataSet(dataSet, i, value)
prob = len(subDataSet)/float(len(dataSet))
newEntropy += prob*calcShannonEnt(subDataSet)
infoGain = baseEntropy - newEntropy
if(infoGain > bestInfoGain):
bestInfoGain = infoGain
bestFeature = i
return bestFeature
#多数表决的方法定义叶子节点的分类
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]
#创建树的函数代码
def createTree(dataSet, labels):
classList = [example[-1] for example in dataSet] #类别列表
if classList.count(classList[0]) == len(classList): #类别列表中第一个类别的个数是否等于整个类别列表中的长度
return classList[0]
if len(dataSet[0]) == 1: #遍历完所有的特征(仍不能将数据集划分成仅包含唯一类别的分组)时返回出现次数最多的类别
return majorityCnt(classList)
bestFeat = chooseBestFeatureToSplit(dataSet)
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel:{}} #字典存储树的信息
del(labels[bestFeat])
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals: #遍历选择特征的所有属性值
subLabels = labels[:] #复制类标签(每次调用createTree()时不改变原始列表的内容)
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,bestFeat,value),subLabels)
return myTree
'''matplotlib注解绘制树形图'''
#使用文本注解绘制树节点
import matplotlib.pyplot as plt
decisionNode = dict(boxstyle="sawtooth", fc="0.8")
leafNode = dict(boxstyle="round4",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('决策节点', (0.5, 0.1), (0.1, 0.5), decisionNode)
plotNode('叶节点', (0.8, 0.1), (0.3, 0.8), leafNode)
plt.show()
'''
'''构造注解树'''
#获取叶节点的数目和树的层数
def getNumLeafs(myTree):
numLeafs = 0
firstStr = list(myTree.keys())[0]
secondDict = myTree[firstStr]
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict': #判断子节点是否为字典类型,若是则为判断节点
numLeafs += getNumLeafs(secondDict[key]) #判断节点往下分,总会找到叶子节点
else:
numLeafs += 1
return numLeafs
#myTree -- {'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
def getTreeDepth(myTree):
maxDepth = 0
firstStr = list(myTree.keys())[0] #'no surfacing'
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
#定义函数retrieveTree输出预先存储的树信息,避免每次测试代码时都要从数据中创建树的麻烦
def retrieveTree(i):
listOfTree = [{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}} ,\
{'no surfacing': {0: 'no', 1: {'flippers': {0: {'head':{0:'no', 1: 'yes'}},1:'no'}}}} ]
return listOfTree[i]
#plotTree函数
def plotMidText(cntrPt,parentPt,txtString): #在父子节点间填充文本信息
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)
firstStr = list(myTree.keys())[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 = 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 = 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 = 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()
'''使用决策树执行分类'''
#使用决策树的分类函数
def classify(inputTree, featLabels, testVec):
firstStr = list(inputTree.keys())[0]
secondDict = inputTree[firstStr]
featIndex = featLabels.index(firstStr)
for key in secondDict.keys():
if testVec[featIndex] == key:
if type(secondDict[key]).__name__=='dict':
classLabel = classify(secondDict[key], featLabels, testVec)
else:
classLabel = secondDict[key]
return classLabel
#使用算法:决策树的存储pivkle模块
def storeTree(inputTree, filename):
import pickle
fw = open(filename, 'wb')
pickle.dump(inputTree, fw)
fw.close()
def grabTree(filename):
import pickle
fr = open(filename, 'rb')
return pickle.load(fr)