《机器学习实战》K-近邻算法学习中碰到的问题与解决方案

《机器学习实战》pdf下载
http://vdisk.weibo.com/s/d8sdffMJBKv8o?category_id=0&parents_ref=d8sdffMJ22tud
机器学习实战源码和数据集下载
https://blog.csdn.net/sinat_29957455/article/details/79123394


1.import kNN 的时候报错
需要安装numpy，方法是cmd下运行下面这句：
python -m pip install numpy


可能报错
“No module named pip”


上网查询解决方案
windows平台
cmd中敲命令：python -m ensurepip


可能报错
“No module named ensurepip”

查到如果用python 2.X需要python版本大于等于2.7.9,而我装的是2.7.6

https://www.zhihu.com/question/54906859

卸载重装2.7.9
2.7.9下载：
https://blog.csdn.net/FUCAIHE/article/details/45353283


2.解决pip install 速度慢的问题
https://blog.csdn.net/sinat_29694963/article/details/79514930


3.classLabelVector.append(int(listFromLine[-1]))这句程序执行报错ValueError
https://blog.csdn.net/daniel_0720/article/details/50839783?locationNum=15


4.unindent does not match any outer indentation level
https://www.cnblogs.com/heimanba/p/3783022.html


5.python -m pip install matplotlib出错
https://www.cnblogs.com/-1307/p/6529269.html


6.运行下面这段出错。（NameError: name 'array' is not defined）
import kNN
datingDataMat,datingLabels = kNN.file2matrix('datingTestSet.txt')
import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1], datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
plt.show()
解决方案：加上from numpy import array，如下
import kNN
from numpy import array
datingDataMat,datingLabels = kNN.file2matrix('datingTestSet.txt')
import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1], datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
plt.show()

py文件中只实现了file2matrix，我认为应该还有一个file1matrix

废话少说，代码在此（建议使用pycharm运行，调试的话：F8单步运行，F7进入，F9运行到下一个断点）

# coding=UTF-8
from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt
from numpy import array

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.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


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 file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())  # get the number of lines in the file
    returnMat = zeros((numberOfLines, 3))  # prepare matrix to return
    classLabelVector = []  # prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

def file1matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())  # get the number of lines in the file
    returnMat = zeros((numberOfLines, 3))  # prepare matrix to return
    classLabelVector = []  # prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        if listFromLine[-1] == 'largeDoses':
            classLabelVector.append(3)
        elif listFromLine[-1] == 'smallDoses':
            classLabelVector.append(2)
        elif listFromLine[-1] == 'didntLike':
            classLabelVector.append(1)
        index += 1
    return returnMat, classLabelVector

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m, 1))
    normDataSet = normDataSet / tile(ranges, (m, 1))  # element wise divide
    return normDataSet, ranges, minVals


def datingClassTest():
    hoRatio = 0.50  # hold out 10%
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')  # load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m * hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3)
        print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print "the total error rate is: %f" % (errorCount / float(numTestVecs))
    print errorCount


def img2vector(filename):
    returnVect = zeros((1, 1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0, 32 * i + j] = int(lineStr[j])
    return returnVect


def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')  # load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]  # take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')  # iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]  # take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        if (classifierResult != classNumStr):
            print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)
            print "fileNameStr: %s" % fileNameStr
        if (classifierResult != classNumStr): errorCount += 1.0
    print "\nthe total number of errors is: %d" % errorCount
    print "\nthe total error rate is: %f" % (errorCount / float(mTest))


def classifyPerson():
    resultList = ["not at all", "in small doses", "in large doses"]
    percentTats = float(raw_input("percentage of time spent playing video games? "))
    ffMiles = float(raw_input("frequent flier miles earned per year? "))
    iceCream = float(raw_input("liters of ice cream consumed per year? "))
    inArr = array([ffMiles, percentTats, iceCream])

    datingDataMat, datingLabels = file2matrix('datingTestSet.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)  # 需要对新来的测试集也做归一化，故需要用到ranges和minVals两个变量
    classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
    print "You will probably like this person: ", resultList[classifierResult - 1]

datingDataMat1,datingLabels1 =file1matrix('datingTestSet.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
#ax.scatter(datingDataMat1[:,1], datingDataMat1[:,2])
ax.scatter(datingDataMat1[:,1], datingDataMat1[:,2],15.0*array(datingLabels1),15.0*array(datingLabels1))
plt.show()

normal ,ranges ,minVals = autoNorm(datingDataMat1)
#datingClassTest()
# classifyPerson()

handwritingClassTest()