机器学习实战

KNN算法代码：

from numpy import *  #NumPy是用Python进行科学计算的基础软件包
import operator  #operator模块输出一系列对应Python内部操作符的函数

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):
	# dataSet.shape[1] 为第一维的长度，dataSet.shape[0] 为第二维的长度，也就是有多少行
	dataSetSize = dataSet.shape[0]   #显然这里有4行，dataSetSize=4
	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]

key1: shape函数是numpy.core.fromnumeric中的函数，它的功能是查看矩阵或者数组的维数。

>>> c = array([[1,1],[1,2],[1,3],[1,4]])
>>> c.shape
(4, 2)
>>> c.shape[0]
4
>>> c.shape[1]
2

key2: tile(A,reps)

Examples
    --------
    >>> a = np.array([0, 1, 2])
    >>> np.tile(a, 2)
    array([0, 1, 2, 0, 1, 2])
    >>> np.tile(a, (2, 2))
    array([[0, 1, 2, 0, 1, 2],
           [0, 1, 2, 0, 1, 2]])
    >>> np.tile(a, (2, 1, 2))
    array([[[0, 1, 2, 0, 1, 2]],
           [[0, 1, 2, 0, 1, 2]]])
    
    >>> b = np.array([[1, 2], [3, 4]])
    >>> np.tile(b, 2)
    array([[1, 2, 1, 2],
           [3, 4, 3, 4]])
    >>> np.tile(b, (2, 1))
    array([[1, 2],
           [3, 4],
           [1, 2],
           [3, 4]])
    
    >>> c = np.array([1,2,3,4])
    >>> np.tile(c,(4,1))
    array([[1, 2, 3, 4],
           [1, 2, 3, 4],
           [1, 2, 3, 4],
           [1, 2, 3, 4]])

key3: diffMat ** 2
数组的平方，就是数字里的每个数单独平方，位置不变。

key4: sqDiffMat.sum(axis = 1)
axis = 0时跨行，所有行相加；axis = 1时跨列，所有列相加。

def file2matrix(filename):
	fr = open(filename)
	arrayOLines = fr.readlines()
	numberOfLines = len(arrayOLines)
	returnMat = zeros((numberOfLines, 3))
	classLabelVector = []
	index = 0
	for line in arrayOLines:
		line = line.strip()
		listFromLine = line.split('\t')
		returnMat[index,:] = listFromLine[0:3]   #https://blog.csdn.net/csj664103736/article/details/72828584/
		classLabelVector.append(int(listFromLine[-1]))
		index += 1
	return returnMat,classLabelVector