最近在学树模型,所以今天花了点时间把机器学习实战上的ID3算法敲了一遍。这个算法比较简单,不过我也是看着书敲的,因为python还不够熟悉,所以一边学点python的函数什么的。代码这边留个档,以后好回头看看。
# -*- coding: utf-8 -*-
"""
@author: 沈同学
"""
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 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 splitDateSet(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=splitDateSet(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
#--------------------------------------------------------------------------------
import operator
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]
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]
uniqueVals=set(featValues)
for value in uniqueVals:
subLabels=labels[:]
myTree[bestFeatLabel][value]=createTree(splitDateSet(dataSet,bestFeat,value),subLabels)
return myTree
#----------------------------------------------------------------------------------