机器学习实战决策树 python3实现 R语言实现（1）

本文链接：https://blog.csdn.net/weixin_41206770/article/details/79688131

本文介绍了如何用Python3和R语言实现决策树。首先展示Python3的实现，包括数据收集、预处理、分析、训练及测试算法的详细步骤。接着，文章将转向R语言的实现过程，帮助读者对比两种语言在实现决策树上的差异。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

二话不说，上代码：

1.python3实现

Python实现：ID3算法

1.决策树构造：trees.py

from math import log
import operator
#简单的鉴定函数
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
#计算给定的数据集的香农熵
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
#按照给定特征划分数据集
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
#选择最好的数据划分方式
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
#字典对象存储了classList中每个类标签出现的频率，最后利用operator操作键值排序，返回出现次数最多的分类名称。
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]
#创建树的函数代码
def createTree(dataSet,labels):
    classList =