DT
# -*- coding: UTF-8 -*-
'''
Created on Oct 12, 2010
Decision Tree Source Code for Machine Learning in Action Ch. 3
@author: Peter Harrington
'''
from math import log
import operator
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
'''
information entropy, 將數學公式翻譯爲代碼
'''
def calcShannonEnt(dataSet):
numEntries = len(dataSet)
labelCounts = {}
for featVec in dataSet: #the the number of unique elements and their occurance
currentLabel = featVec[-1]
if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0
labelCounts[currentLabel] += 1
shannonEnt = 0.0
for key in labelCounts:
prob = float(labelCounts[key])/numEntries
shannonEnt -= prob * log(prob,2) #log base 2
return shannonEnt
'''
axis爲屬性的下標值
value爲屬性的取值(若該屬性表現爲兩種形式則取值爲0或1)
將dataSet按照指定屬性(axis)的指定表現形式(value)進行劃分,每劃分一次要消耗一個屬性。
'''
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
'''
利用information gain來確定那個屬性爲最佳劃分屬性
'''
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中存放的是同一種屬性
featList = [example[i] for example in dataSet]#create a list of all the examples of this feature
#將list中重複的值使用set去除,使值唯一
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
'''
當消耗完所有fecture後 存在的子集中有超過一種的屬性時,爲確定該子集屬於那個label,要
通過該函數進行vote確定,與KNN中的投票函數相似
'''
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]
'''
遞歸創建樹,以字典的形式存儲樹
'''
def createTree(dataSet,labels):
#get the class from the dataSet
classList = [example[-1] for example in dataSet]
#classList中第一個數據類型的數量等於classList的長度
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)
#dataset中的數值是將feature數值化(0或1),dataset最後一個值是class值。
#label中屬性的具體表現(如:有肺、有鰭)
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel:{}}
del(labels[bestFeat]) #產生一個節點消耗一個屬性
#獲得一個屬性上有幾種表現形式,即一個節點處能分幾個杈
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
#遞歸創建樹
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
return myTree
'''
test
'''
def classify(inputTree,featLabels,testVec):
#獲得根節點
firstStr = inputTree.keys()[0]
#獲得根節點key對應的value(即根節點下的所有內容),這個value也是一個字典的形式,其中的key的個數爲根節點屬性表現形式的個數
secondDict = inputTree[firstStr]
#得到根節點feature的在featLabels中的下標值
featIndex = featLabels.index(firstStr)
#測試數據在根節點屬性上的取值(即測試數據往屬性的哪個分叉走)
key = testVec[featIndex]
#測試數據在下一節點
valueOfFeat = secondDict[key]
#若下一節點是一個字典,說明下一節點爲非葉子節點,遞歸。若爲葉子節點則得到classLabel
if isinstance(valueOfFeat, dict):
classLabel = classify(valueOfFeat, featLabels, testVec)
else: classLabel = valueOfFeat
return classLabel
'''
存儲樹:因爲每次創建樹都會浪費大量的時間,所以存儲樹避免每次都進行創建
python的pickle模塊實現了基本的數據序列和反序列化。通過pickle模塊的序列化操作我們能夠將程
序中運行的對象信息保存到文件中去,永久存儲;
通過pickle模塊的反序列化操作,我們能夠從文件中創建上一次程序保存的對象。
'''
def storeTree(inputTree,filename):
import pickle
fw = open(filename,'w')
pickle.dump(inputTree,fw) #序列化
fw.close()
'''
從存儲的文件總提取樹
'''
def grabTree(filename):
import pickle
fr = open(filename)
return pickle.load(fr) #反序列化
treePlotter
# -*- coding: UTF-8 -*-
'''
Created on Oct 14, 2010
@author: Peter Harrington
'''
import matplotlib.pyplot as plt
decisionNode = dict(boxstyle="sawtooth", fc="0.8")
leafNode = dict(boxstyle="round4", fc="0.8")
arrow_args = dict(arrowstyle="<-")
def getNumLeafs(myTree):
numLeafs = 0
firstStr = myTree.keys()[0]
secondDict = myTree[firstStr]
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
numLeafs += getNumLeafs(secondDict[key])
else: numLeafs +=1
return numLeafs
def getTreeDepth(myTree):
maxDepth = 0
firstStr = myTree.keys()[0]
secondDict = myTree[firstStr]
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
thisDepth = 1 + getTreeDepth(secondDict[key])
else: thisDepth = 1
if thisDepth > maxDepth: maxDepth = thisDepth
return maxDepth
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 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 = 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()
#def createPlot():
# fig = plt.figure(1, facecolor='white')
# fig.clf()
# createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
# plotNode('a decision node', (0.5, 0.1), (0.1, 0.5), decisionNode)
# plotNode('a leaf node', (0.8, 0.1), (0.3, 0.8), leafNode)
# plt.show()
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]
#createPlot(thisTree)
main
from treePlotter import *
from DT import *
from ss.DT import storeTree
#dataSet, labels = createDataSet()
#print calcShannonEnt(dataSet)
#myTree = createTree(dataSet, labels)
#print myTree
#storeTree(myTree, 'ss')
myTree = grabTree('ss')
#print myTree
createPlot(myTree)
'''
fr = open('lenses.txt')
lens = [inst.strip().split('\t') for inst in fr.readlines()]
lensLabel = ['age','prescript','astigmatic','tearRate']
myTree = createTree(lens, lensLabel)
createPlot(myTree)
'''