【风马一族_Python】 决策树

《机器学习实战》第三章 决策树

-------------------------------------

#1 trees.py　　计算给定数据集的香农熵

-------------------------------------

from math import log

# 计算给定数据集的香农熵
def calcShannonEnt(dataSet):
    numEnres = len(dataSet)
    labelCoounts = {}
    for featVec in dataSet:
        #为所有可能分类创建字典
        currentLabel = featVec[-1]
        if currentLabel not in labelCoounts.keys():
            labelCoounts[currentLabel] = 0
        labelCoounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCoounts:
        prob = float(labelCoounts[key]) / numEnres
        shannonEnt -= prob * log(prob, 2)               #以2为底求对数
    return shannonEnt

#用来 得到简单鱼类鉴定数据集
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

-------------------------------------

#2 trees.py　　划分数据集 待划分的数据集、划分数据集的待征、需要返回的特征的值

-------------------------------------

# 划分数据集   待划分的数据集、划分数据集的待征、需要返回的特征的值
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

-------------------------------------

#3 trees.py　　选择最好的数据集划分方式

-------------------------------------

# 划分数据集   待划分的数据集、划分数据集的待征、需要返回的特征的值
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


# 选择最好的数据集划分方式
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

-------------------------------------

#4 trees.py　　创建树的函数代码   两个参数：数据集、标签列表

-------------------------------------

import operator

# 创建树的函数代码 两个参数：数据集、标签列表
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]

    # 类别完全相同则停止继续划分
    if classList.count(classList[0]) == len(classList):
        return classList[0]

    # 遍历完所有特征时返回出现次数最多的
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)

    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel: {}}
    del (labels[bestFeat])

    # 得到列表包含的所有属性值
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)

    # 遍历当前选择特征包含的所有属性值，在每个数据集划分上递归调用函数createTree()
    for value in uniqueVals:
        subLabels = labels[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)

    return myTree