求大神解答！！！机器学习实践Python决策树算法错误，求大神指点~~~错误类型：list index out of range。。。。。。。。。。。。。。。。

[小白_noob]

from math import log
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 * 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):
numFeatures = len(dataSet[0]) - 1
baseEntropy = calcShannonEnt(dataSet)
bestInfoGain = 0.0; bestFeature = -1
for i in range(numFeatures):
featList = [example[i] for example in dataSet]
uniqueVals = set(featList)
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
if (infoGain > bestInfoGain):
bestInfoGain = infoGain
bestFeature = i
return bestFeature

def createTree(dataSet,labels):
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:{}}
subLabels=labels[:]
del(labels[bestFeat])
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals:
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

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)

def predictLensesType():
fr=open('lenses.txt','rb')
lenses=[inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels=['age','prescript','astigmatic','tearRate']
lensesTree=createTree(lenses,lensesLabels)
return lensesTree


这是我照书上写的代码，可是在进行最后一步预测隐形眼镜时出错，错误类型是说我程序中第56行（标红的那一行）：list index out of range，可是我找不到哪里的对应列表的编号不存在，求大神帮忙解决一下，谢谢

[陈年椰子]

从代码上来看，如果 lenses 是空的， 应该会出错。这个时候 classList[0] 不存在。

在 lensesTree=createTree(lenses,lensesLabels)
前 print(len(lenses)) 看看

[小白_noob]

恩恩，是空的，因为lenses里面没有数据，里面加上数据后就可以运行了，已经解决了，谢谢~~~

[祺云]

你好，我里面有数据还是不可以