knn和决策树算法

本篇为学习过程，为机器学习实战书重操后的knn和决策树算法的代码。

knn算法

首先创建knn.py的模块 创建两个函数 分别为构造数据集和分类函数。

from numpy import *
import operator

def createDataSet():
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    return group, labels


def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = \
        classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items()\
     key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

在编辑程序模块执行的操作为(knn文件在MLcode文件夹中)：

from MLcode import kNN

group,labels=kNN.createDataSet()
kNN.classify0([0,0],group,labels,3)

输出B，完成算法。

决策树算法

import operator
from math import log

def createDataSet():
    dataSet = [ ['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', 0.697, 0.460, '好瓜'],
                ['乌黑', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', 0.774, 0.376, '好瓜'],
                ['乌黑', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', 0.634, 0.264, '好瓜'],
                ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', 0.608, 0.318, '好瓜'],
                ['浅白', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', 0.556, 0.215, '好瓜'],
                ['青绿', '稍蜷', '浊响', '清晰', '稍凹', '软粘', 0.403, 0.237, '好瓜'],
                ['乌黑', '稍蜷', '浊响', '稍糊', '稍凹', '软粘', 0.481, 0.149, '好瓜'],
                ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '硬滑', 0.437, 0.211, '好瓜'],
                ['乌黑', '稍蜷', '沉闷', '稍糊', '稍凹', '硬滑', 0.666, 0.091, '坏瓜'],
                ['青绿', '硬挺', '清脆', '清晰', '平坦', '软粘', 0.243, 0.267, '坏瓜'],
                ['浅白', '硬挺', '清脆', '模糊', '平坦', '硬滑', 0.245, 0.057, '坏瓜'],
                ['浅白', '蜷缩', '浊响', '模糊', '平坦', '软粘', 0.343, 0.099, '坏瓜'],
                ['青绿', '稍蜷', '浊响', '稍糊', '凹陷', '硬滑', 0.639, 0.161, '坏瓜'],
                ['浅白', '稍蜷', '沉闷', '稍糊', '凹陷', '硬滑', 0.657, 0.198, '坏瓜'],
                ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '软粘', 0.360, 0.370, '坏瓜'],
                ['浅白', '蜷缩', '浊响', '模糊', '平坦', '硬滑', 0.593, 0.042, '坏瓜'],
                ['青绿', '蜷缩', '沉闷', '稍糊', '稍凹', '硬滑', 0.719, 0.103, '坏瓜']    ]
    labels = ['色泽', '根蒂', '敲击', '纹理', '脐部', '触感', '密度', '含糖率']
    return dataSet, labels

def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet: #the the number of unique elements and their occurance
        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) #log base 2
    return shannonEnt

def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]     #chop out axis used for splitting
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet

def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 1      #the last column is used for the labels
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):        #iterate over all the features
        featList = [example[i] for example in dataSet]#create a list of all the examples of this feature
        uniqueVals = set(featList)       #get a set of unique values
        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     #calculate the info gain; ie reduction in entropy
        if (infoGain > bestInfoGain):       #compare this to the best gain so far
            bestInfoGain = infoGain         #if better than current best, set to best
            bestFeature = i
    return bestFeature                      #returns an integer

def majorityCnt(classList):
    classCount={}
    for vote in classList:
        classCount[classList]=classCount.get(classList,0)+1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createTree(dataSet,labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList):
        return classList[0]#stop splitting when all of the classes are equal
    if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet
        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[:]       #copy all of labels, so trees don't mess up existing 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)
    key = testVec[featIndex]
    valueOfFeat = secondDict[key]
    if isinstance(valueOfFeat, dict):
        classLabel = classify(valueOfFeat, featLabels, testVec)
    else: classLabel = valueOfFeat
    return classLabel

操作文件

from MLcode import tree

myDat,labels=tree.createDataSet()
myDat
yTree = tree.createTree(myDat,labels)
myTree

完成算法。