决策树完结篇 (二)
et]
uniqueva ls = set(featValues)
for value in uniqueva ls:
subLabels = labels[:]
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)
return myTree
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
myDat,labels = CreateDataSet()
print(calcShannonEnt(myDat))
print(splitDataSet(myDat, 1, 1))
print(chooseBestFeatureToSplit(myDat))
myTree = createTree(myDat, labels)
print(classify(myTree, labels, [1, 0]))
print(classify(myTree, labels, [1, 1]))
import math
import operator
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 key in labelCounts:
prob = float(labelCounts[key])/numEntries
shannonEnt -= prob*math.log(prob, 2)
return shannonEnt
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
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):
numberFeatures = len(dataSet[0])-1
baseEntropy = calcShannonEnt(dataSet)
bestInfoGain = 0.0;
bestFeature = -1;
for i in range(numberFeatures):
featList = [example[i] for example in dataSet]
print(featList)
uniqueva ls = set(featList)
print(uniqueva ls)
newEntropy =0.0
for value in uniqueva ls:
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
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, inputlabels):
labels=inputlabels[:]
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)
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel:{}}
del(labels[bestFeat])
featValues = [example[bestFeat] for example in dataSet]
uniqueva ls = set(featValues)
for value in uniqueva ls:
subLabels = labels[:]
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)
return myTree
def classify(inputTr