python2.7.5下KNN file2matrix错误解决

使用python2.7.5版本错误解决

依照机器学习实战KNN的代码报错如下：

runloader@runloader-dell:~/ml/Ch02$ python

Python 2.7.5+ (default, Feb 27 2014, 19:37:08)

[GCC 4.8.1] on linux2

Type "help", "copyright", "credits" or "license" for more information.

>>> import kNN

>>> datingDataMat,datingLabels = kNN.file2matrix('datingTestSet.txt')

Traceback (most recent call last):

  File "<stdin>", line 1, in <module>

  File "kNN.py", line 48, in file2matrix

    classLabelVector.append(int(listFromLine[-1]))
ValueError: invalid literal for int() with base 10: 'largeDoses'

KNN源码如下：

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]))  ###是因为此处的int导致

        index += 1

    return returnMat,classLabelVector

修改后代码如下：

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(listFromLine[-1])  

        index += 1  

    return returnMat,classLabelVector

>>> import kNN

>>> datingDataMat,datingLabels = mykNN.file2matrix('datingTestSet.txt')

>>> import matplotlib

>>> import matplotlib.pyplot as plt

>>> fig = plt.figure()

>>> ax = fig.add_subplot(111)

>>> ax.scatter(mat[:,1], mat[:,2], 15.0*array(map(int,lab)),15.0*array(map(int,lab))) ##替换原文中的ax.scatter(datingDataMat[:,1], datingDataMat[:, 2]

<matplotlib.collections.PathCollection object at 0x3c04310>

>>> plt.show()

结果能正常执行了

请查看了harrington本人的回复，Manning  出版社此书的论坛