决策树（chap3）Machine Learning In Action学习笔记

# -*- coding:utf-8 -*-
from math import log
from numpy import *
import operator
def createDataSet():
    dataSet = [[1, 1, ‘yes‘],
               [1, 1, ‘yes‘],
               [1, 0, ‘no‘],
               [0, 1, ‘no‘],
               [0, 1, ‘no‘]]
    labels = [‘no surfacing‘, ‘flippers‘]
    # change to discrete values
    return dataSet, labels
# 测量给定数据集的信息熵，度量数据的无序程度，熵越大则数据越无序。
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        labelCounts[currentLabel] = labelCounts.get(currentLabel, 0) + 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(当我们按照某个特征划分数据集时，就需要将所有符合要求的元素抽取出来)
# axis：用来划分数据集的特征(索引值), value：该特征选取的属性值(需要返回的值)
def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:]
            reducedFeatVec.remove(value)
            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):
        # 创建唯一的分类标签列表
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)
        newEntropy = 0.0
        # 计算每种划分方式的信息熵
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet) / float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntropy
        # 计算最好的信息增益
        if infoGain > bestInfoGain:
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature
def majorityCnt(classList):
    classCount = {}
    for vote in classList:
        classCount[vote] = classCount.get(vote, 0) + 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]
    # 两个结束条件：类别完全相同或者遍历完所有特征
    if len(set(classList)) == 1:
        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(splitDataSet(dataSet, bestFeat, value), subLabels)
    return myTree
def classify(inputTree, featLabels, testVec):
    firstStr = inputTree.keys()[0]
    secondDict = inputTree[firstStr]
    featIndex = featLabels.index(firstStr)
    for key in secondDict.keys():
        if testVec[featIndex] == key:
            if type(secondDict[key]).__name__ == ‘dict‘:
                classLabel = classify(secondDict[key], featLabels, testVec)
            else:
                classLabel = secondDict[key]
    return classLabel
# 使用pickle模块存储决策树
def storeTree(inputTree, filename):
    import pickle
    fw = open(filename, ‘w‘)
    pickle.dump(inputTree, fw)
    fw.close()
def grabTree(filename):
    import pickle
    fr = open(filename)
    return pickle.load(fr)