ID3决策树（Python实现）

最新推荐文章于 2023-07-17 16:41:01 发布

原创

最新推荐文章于 2023-07-17 16:41:01 发布 · 327 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#python #ID3

from math import log

#计算香农熵(信息熵)
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

# 创造数据集
def creatDataSet():
    dataSet = [[1, 1, 'yes'],
               [1, 1, 'yes'],
               [1, 0, 'no'],
               [0, 1, 'no'],
               [0, 1, 'no']]
    labels = ['no surfacing', 'flippers']
    return dataSet, labels


#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[axi