基于基于ID3决策树算法的实现决策树算法的实现(Python版版)
下面小编就为大家带来一篇基于ID3决策树算法的实现(Python版)。小编觉得挺不错的，现在就分享给大家，也
给大家做个参考。一起跟随小编过来看看吧
实例如下：实例如下：
# -*- coding:utf-8 -*-
from numpy import *
import numpy as np
import pandas as pd
from math import log
import operator
#计算数据集的香农熵
def calcShannonEnt(dataSet):
numEntries=len(dataSet)
labelCounts={}
#给所有可能分类创建字典
for featVec in dataSet:
currentLabel=featVec[-1]
if currentLabel not in labelCounts.keys():
labelCounts[currentLabel]=0
labelCounts[currentLabel]+=1
shannonEnt=0.0
#以2为底数计算香农熵
for key in labelCounts:
prob = float(labelCounts[key])/numEntries
shannonEnt-=prob*log(prob,2)
return shannonEnt
#对离散变量划分数据集，取出该特征取值为value的所有样本
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
#对连续变量划分数据集，direction规定划分的方向，
#决定是划分出小于value的数据样本还是大于value的数据样本集
def splitContinuousDataSet(dataSet,axis,value,direction):
retDataSet=[]
for featVec in dataSet:
if direction==0:
if featVec[axis]>value:
reducedFeatVec=featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
else:
if featVec[axis]<=value:
reducedFeatVec=featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
return retDataSet
#选择最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet,labels):
numFeatures=len(dataSet[0])-1
baseEntropy=calcShannonEnt(dataSet)
bestInfoGain=0.0
bestFeature=-1
bestSplitDict={}
for i in range(numFeatures):
featList=[example[i] for example in dataSet]
#对连续型特征进行处理
if type(featList[0]).__name__=='float' or type(featList[0]).__name__=='int':
#产生n-1个候选划分点
sortfeatList=sorted(featList)
splitList=[]
for j in range(len(sortfeatList)-1):
splitList.append((sortfeatList[j]+sortfeatList[j+1])/2.0)
bestSplitEntropy=10000
slen=len(splitList)
评论0