正文
k-近邻算法（kNN）准备数据：归一化数值
提示：扫一扫查出行【扫一扫了解最新限行尾号】
复制提示
#准备数据：归一化数值
def autoNorm(dataSet): #autoNorm()函数可以自动将数字特征值转换为0到1的区间
minVals = dataSet.min(0)
maxVals = dataSet.max(0) #ddataSet.max(0)中的参数0使得函数可以从列中选取最小值
ranges = maxVals - minVals
normDataSet = zeros(shape(dataSet))
m = dataSet.shape[0]
#newValue = (oldValue-min)/(max-min)，该公式可以将任意取值范围的特征值转换为0到1区间内的值
#tile()函数将变量内容复制成输入矩阵同样大小的矩阵（具体特征值相除）
#在numpy库中，矩阵除法需要使用函数linalg.solve(matA,matB)
normDataSet = dataSet - tile(minVals, (m,1))
normDataSet = normDataSet/tile(ranges, (m,1))
return normDataSet, ranges, minVals
运行结果：
>>>normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
>>>normMat
array([[1., 1., 1.],
[0., 0., 0.],
[0., 0., 0.],
...,
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]])
>>>ranges
array([4.092000e+04, 8.326976e+00, 9.539520e-01])
>>>minVals
array([0., 0., 0.])
出现的错误：
>>>normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
Traceback (most recent call last):
File "<input>", line 1, in <module>
NameError: name 'kNN' is not defined >>>normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
Traceback (most recent call last):
File "<input>", line 1, in <module>
AttributeError: module 'kNN' has no attribute 'autoNorm'
解决办法：
个人解决办法：重启PyCharm，运行kNN.py，重新完整的输入运行命令，问题就解决了
>>>from numpy import *
>>>random.rand(4,4)
>>>randMat = mat(random.rand(4,4))
>>>randMat.I
>>>invRandMat = randMat.I
>>>myEye = randMat*invRandMat
>>>myEye - eye(4)
>>>group,labels = kNN.createDataSet()
>>>group
>>>labels
>>>kNN.classify0([0,0], group, labels, 3)
>>>datingDataMat,datingLabels = kNN.file2matrix('datingTestSet.txt')
>>>datingDataMat
>>>datingLabels[0:16]
>>>import matplotlib
>>>import matplotlib.pyplot as plt
>>>fig = plt.figure()
>>>ax = fig.add_subplot(111)
>>>ax.scatter(datingDataMat[:,1], datingDataMat[:,2])
>>>plt.show()
>>>normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
>>>normMat
array([[1., 1., 1.],
[0., 0., 0.],
[0., 0., 0.],
...,
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]])
>>>ranges
array([4.092000e+04, 8.326976e+00, 9.539520e-01])
>>>minVals
array([0., 0., 0.])
