机器学习实战 pca 代码跑不出来

[lxtylovewd]

from numpy import *  
  
def loadDataSet(filename,delim = "\t"):  
    fr = open(filename)  
    stringArr = [line.strip().split(delim) for line in fr.readlines()]  
    datArr = [map(float, line) for line in stringArr]  
    return mat(datArr)  
  
#dataMat对应数据集，N个特征  
def pca(dataMat, topNfeat=9999999):  
    meanVals = mean(dataMat, axis = 0)   #求平均值  
    meanRemoved = dataMat - meanVals #去平均值  
    covMat = cov(meanRemoved,rowvar=0) #计算协防差矩阵  
    eigVals, eigVects = linalg.eig(mat(covMat))  
    eigValInd = argsort(eigVals)  
    #从小到大对N个值排序  
    eigValInd = eigValInd[: -(topNfeat + 1) : -1]  
    redEigVects = eigVects[:, eigValInd]  
    #将数据转换到新空间  
    lowDDataMat = meanRemoved * redEigVects  
    reconMat = (lowDDataMat * redEigVects.T) + meanVals  
    return lowDDataMat, reconMat  
  
#测试  
dataMat = loadDataSet("testSet.txt")  
lowDMat, reconMat = pca(dataMat,1)  
print shape(lowDMat)  
  
#show  
import matplotlib  
import matplotlib.pyplot as plt  
fig = plt.figure()  
ax = fig.add_subplot(111)  
ax.scatter(dataMat[:,0].flatten().A[0], dataMat[:,1].flatten().A[0], marker='^',  s = 90 )  
ax.scatter(reconMat[:,0].flatten().A[0], reconMat[:,1].flatten().A[0],marker='o', s = 50 , c ='red' )

运行之后报错：
Traceback (most recent call last):
File "D:/Documents/GitHub/untitled2/pca1.py", line 30, in <module>
lowDMat, reconMat = pca(dataMat, 1)
File "D:/Documents/GitHub/untitled2/pca1.py", line 13, in pca
meanVals = mean(dataMat, axis=0) # 求平均值
File "D:\Program Files\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py", line 2906, in mean
return mean(axis=axis, dtype=dtype, out=out, **kwargs)
File "D:\Program Files\Anaconda3\lib\site-packages\numpy\matrixlib\defmatrix.py", line 549, in mean
return N.ndarray.mean(self, axis, dtype, out, keepdims=True)._collapse(axis)
File "D:\Program Files\Anaconda3\lib\site-packages\numpy\core\_methods.py", line 73, in _mean
ret, rcount, out=ret, casting='unsafe', subok=False)
TypeError: unsupported operand type(s) for /: 'map' and 'int'
咋整

[jz745224058]

问题解决了吗？

[??165]

第25 行直接用numpy的loadtxt函数打开文件就行。

[SMEB_9]

老问题了，前面几篇也有几处类似的报错。
修改如下：
def loadDataSet函数 第三行 改为：datArr = [list(map(float, line)) for line in stringArr]
因为2.7和3.6map的返回值不同。