trees.py文件代码：
from math import log
import operator
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
def calcShannonEnt(dataSet):
numEntries = len(dataSet)
labelCounts = {}
for featVec in dataSet: #the the number of unique elements and their occurance
currentLabel = featVec[-1]#取出这一行的最后一个值，即类别yes or no
if currentLabel not in labelCounts.keys():
labelCounts[currentLabel] = 0#如果没有这个键，就增加一个键值为零
labelCounts[currentLabel] += 1
shannonEnt = 0.0
for key in labelCounts:
prob = float(labelCounts[key])/numEntries#p(xi)
shannonEnt -= prob * log(prob,2) #log base 2 -p(xi)*log(p(xi))
return shannonEnt
#创建测试数据
def createDataSet():
dataSet = [[1, 1, 'yes'],
[1, 1, 'yes'],
[1, 0, 'no'],
[0, 1, 'no'],
[0, 1, 'no']]
labels = ['no surfacing','flippers']
#change to discrete values
return dataSet, labels
myDat,labels = createDataSet()
##print(calcShannonEnt(myDat))
##def createDataSet():
## dataSet = [[1, 1, 'maybe'],
## [1, 1, 'yes'],
## [1, 0, 'no'],
## [0, 1, 'no'],
## [0, 1, 'no']]
## labels = ['no surfacing','flippers']
## #change to discrete values
## return dataSet, labels
##
##myDat,labels = createDataSet()
##print(calcShannonEnt(myDat))
def splitDataSet(dataSet, axis, value):
retDataSet = []
for featVec in dataSet:
if featVec[axis] == value:
reducedFeatVec = featVec[:axis] #chop out axis used for splitting
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
return retDataSet
##print(splitDataSet(myDat,0,1))
##print(splitDataSet(myDat,0,0))
def chooseBestFeatureToSplit(dataSet):
numFeatures = len(dataSet[0]) - 1 #the last column is used for the labels
baseEntropy = calcShannonEnt(dataSet)
bestInfoGain = 0.0; bestFeature = -1
for i in range(numFeatures): #iterate over all the features
featList = [example[i] for example in dataSet]#create a list of all the examples of this feature
uniqueVals = set(featList) #get a set of unique values
newEntropy = 0.0
for value in uniqueVals:
subDataSet = splitDataSet(dataSet, i, value)
prob = len(subDataSet)/float(len(dataSet))
newEntropy += prob * calcShannonEnt(subDataSet)
infoGain = baseEntropy - newEntropy #calculate the info gain; ie reduction in entropy
if (infoGain > bestInfoGain): #compare this to the best gain so far
bestInfoGain = infoGain #if better than current best, set to best
bestFeature = i
return bestFeature #returns an integer
##print(chooseBestFeatureToSplit(myDat))
def majorityCnt(classList):
classCount={}
for vote in classList:
if vote not in classCount.keys():
classCount[vote] = 0
classCount[vote] += 1
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
def createTree(dataSet,labels):
classList = [example[-1] for example in dataSet]
if classList.count(classList[0]) == len(classList):
return classList[0]#stop splitting when all of the classes are equal
if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet
return majorityCnt(classList)
bestFeat = chooseBestFeatureToSplit(dataSet)
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel:{}}
del(labels[bestFeat])
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals:
subLabels = labels[:] #copy all of labels, so trees don't mess up existing labels
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
return myTree
myTree = createTree(myDat,labels)
labels.insert(0,'no surfacing')#在myTree产生的过程中删除了'no surfacing',这里要插入进来
##print(labels)
##print(myTree)
def classify(inputTree, featLabels, testVec):
firstStr = next(iter(inputTree)) #获取决策树结点
secondDict = inputTree[firstStr] #下一个字典
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
decisionNode = dict(boxstyle = 'sawtooth',fc = '0.8')
leafNode = dict(boxstyle = 'round4',fc = '0.8')
arrow_args = dict(arrowstyle = '<-')
def plotNode(nodeTxt,centerPt,parentPt,nodeType):
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)
createPlot.ax1.annotate(nodeTxt,xy = parentPt,xycoords = 'axes fraction',
xytext = centerPt,textcoords = 'axes fraction',
va = 'center',ha = 'center',bbox = nodeType,
arrowprops = arrow_args,FontProperties=font)
##print(classify(myTree,labels,[1,0]))
##print(classify(myTree,labels,[1,1]))
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)
##storeTree(myTree,'classifierStorage.pk')
##print(grabTree('classifierStorage.pk'))
def getNumLeafs(myTree):
numLeafs = 0
firstStr = list(myTree.keys())[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
firstStr = list(myTree.keys())[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
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, va="center", ha="center", rotation=30)
def plotTree(myTree, parentPt, nodeTxt):#if the first key tells you what feat was split on
numLeafs = getNumLeafs(myTree) #this determines the x width of this tree
depth = getTreeDepth(myTree)
firstStr = list(myTree.keys())[0] #the text label for this node should be this
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':#test to see if the nodes are dictonaires, if not they are leaf nodes
plotTree(secondDict[key],cntrPt,str(key)) #recursion
else: #it's a leaf node print the leaf node
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
#if you do get a dictonary you know it's a tree, and the first element will be another dict
def createPlot(inTree):
fig = plt.figure(1, facecolor='white')
fig.clf()
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops) #no ticks
#createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
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()
fr = open('lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ['age','prescript','astigmatic','tearRate']
lensesTree = createTree(lenses,lensesLabels)
print(lensesTree)
createPlot(lensesTree)
treePlotter.py文件代码：
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
decisionNode = dict(boxstyle = 'sawtooth',fc = '0.8')
leafNode = dict(boxstyle = 'round4',fc = '0.8')
arrow_args = dict(arrowstyle = '<-')
def plotNode(nodeTxt,centerPt,parentPt,nodeType):
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)
createPlot.ax1.annotate(nodeTxt,xy = parentPt,xycoords = 'axes fraction',
xytext = centerPt,textcoords = 'axes fraction',
va = 'center',ha = 'center',bbox = nodeType,
arrowprops = arrow_args,FontProperties=font)
##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()
##createPlot()
##import matplotlib.pyplot as plt
##from matplotlib.font_manager import FontProperties
##
##decisionNode=dict(boxstyle="sawtooth",fc="0.8")
##leafNode=dict(boxstyle="round4",fc="0.8")
##
##def plotNode(nodeTxt,centerPt,parentPt,nodeType):
## arrow_args=dict(arrowstyle="<-")#定义箭头格式
## font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)#设置中文字体
## #绘制结点
## createPlot.ax1.annotate(nodeTxt,xy=parentPt,xycoords='axes fraction',
## xytext=centerPt,textcoords='axes fraction',
## va="center",ha="center",bbox=nodeType,
## arrowprops=arrow_args, FontProperties=font)
##
##def createPlot():
## fig=plt.figure(1,facecolor='white')#创建fig
## fig.clf()#清空fig
## createPlot.ax1=plt.subplot(111, frameon=False)#去掉x、y轴
## plotNode('决策节点',(0.5,0.1),(0.1,0.5),decisionNode)
## plotNode('叶子节点',(0.8,0.1),(0.3,0.8),leafNode)
## plt.show()
##
##
##createPlot()
def getNumLeafs(myTree):
numLeafs = 0
firstStr = list(myTree.keys())[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
firstStr = list(myTree.keys())[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
def retrieveTree(i):
listOfTrees =[{'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 listOfTrees[i]
##print(retrieveTree(0))
##print(getNumLeafs(retrieveTree(0)))
##print(getTreeDepth(retrieveTree(0)))
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, va="center", ha="center", rotation=30)
def plotTree(myTree, parentPt, nodeTxt):#if the first key tells you what feat was split on
numLeafs = getNumLeafs(myTree) #this determines the x width of this tree
depth = getTreeDepth(myTree)
firstStr = list(myTree.keys())[0] #the text label for this node should be this
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':#test to see if the nodes are dictonaires, if not they are leaf nodes
plotTree(secondDict[key],cntrPt,str(key)) #recursion
else: #it's a leaf node print the leaf node
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
#if you do get a dictonary you know it's a tree, and the first element will be another dict
def createPlot(inTree):
fig = plt.figure(1, facecolor='white')
fig.clf()
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops) #no ticks
#createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
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()
myTree = retrieveTree(0)
##createPlot(myTree)
##myTree['no surfacing'][3] = 'maybe'
##createPlot(myTree)
版权声明：本文为weixin_43955530原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接和本声明。