from numpy import *		# 导入numpy模块import operator		# 导入operator模块def createDataSet():		# 创建数据集函数	# 构建一个数组存放特征值    group = array(        [[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]]    )    # 构建一个数组存放目标值    labels = ["A", "A", "B", "B"]    return group, labels

# 返回矩阵的行数dataSetSize = dataSet.shape[0]	# 列数不变，行数变成dataSetSize列diffMat = tile(inX, (dataSetSize, 1)) - dataSetsqDiffMat = diffMat ** 2sqDistances = sqDiffMat.sum(axis=1)distances = sqDistances**0.5

# 返回矩阵的行数dataSetSize = dataSet.shape[0]	# 以第一步的数据为例answer:4		# 4行

inX = [1. , 0.]# 列数不变，行数变成dataSetSize列diffMat = tile(inX, (dataSetSize, 1)) - dataSet# tile(inX, (dataSetSize, 1))inX = [	[1. , 0.],	[1. , 0.],	[1. , 0.],	[1. , 0.]]# inX - dataSet两个矩阵相减（行列相等相加相减才有意义）dataSet = [		[1. , 1.1],        [1. , 1. ],        [0. , 0. ],        [0. , 0.1]]diffMat = [	[0. , -1.1],	[0. , -1.],	[1. , 0.],	[1. , -0.1]]

# 求平方差sqDiffMat = diffMat * 2

# 计算矩阵中每一行元素之和# 此时会形成一个多行1列的矩阵sqDistances = sqDiffMat.sum(axis=1)

# 开根号distances = sqDistances**0.5

# 对数组进行排序sortedDistIndicies = distances.argsort()

classCount = {}		# 新建一个字典# 确定前k个距离最小元素所在的主要分类for i in range(k):	# voteIlabel的取值是labels中sortedDistIndicies[i]的位置	voteIlabel = labels[sortedDistIndicies[i]]	classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1

# 排序sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)

return sortedClassCount[0][0]

#include <iostream>#include <vector>#include <algorithm>#include <cmath>#include <map>int sum_vector(std::vector<int>& v) {	int sum = 0;	for (int i = 0; i < v.size(); ++i) {		sum = v[i] + sum;	}	return sum;}int knn(int k) {	using std::cout;	using std::endl;	using std::vector;	vector<vector<int>> x;		vector<int> x_sample = {2, 3, 4};		for (int i = 0; i < 4; ++i) {		x.push_back(x_sample);	}	vector<int> y = {1, 1, 1, 1};	int dataSetSize = x.size();			vector<int> x_test = {4, 3, 4};	vector<vector<int>> x_test_matrix;	for (int i = 0; i < dataSetSize; ++i) {		x_test_matrix.push_back(x_test);	}	vector<int> v_total;	for (int i = 0; i < dataSetSize; ++i) {		for (int j = 0; j < x_test_matrix[i].size(); ++j) {			x_test_matrix[i][j] = x_test_matrix[i][j] - x[i][j];			x_test_matrix[i][j] = x_test_matrix[i][j] * 2;		}		int sum_vec = sum_vector(x_test_matrix[i]);		v_total.push_back(sqrt(sum_vec));	}	sort(v_total.begin(), v_total.end());	std::map<int, int> mp;	for (int i = 0; i < k; ++i) {		int label = y[v_total[i]];		mp[label] += 1;	}	int max_end_result = 0;	for (std::map<int, int>::iterator it = mp.begin(); it != mp.end(); it++) {		if (it->first > max_end_result) {			max_end_result = it->first;		}	}	return max_end_result;}int main() {	int k = 12;	int value = knn(k);	std::cout << "result:" << std::endl;	return 0;}

def file2matrix(filename):	fr = open(filename)	# 读取行数据直到尾部	arrayOLines = fr.readlines()	# 获取行数	numberOfLines = len(arrayOLines)	# 创建返回shape为（numberOfLines, 3）numpy矩阵	returnMat = zeros((numberOfLines, 3))	classLabelVector = []	index = 0	for line in arrayOLines:		# 去除首尾的回车符		line = line.strip()		# 以tab字符"	"为符号进行分割字符串		listFromLine = line.split("	")		# 选取前3个元素，把他们存储到特征矩阵中		returnMat[index, :] = listFromLine[0: 3]		# 把目标变量放到目标数组中		classLabelVector.append(int(listFromLine[-1]))		index += 1	return returnMat, classLabelVector

# max：最大特征值# min：最小特征值newValue = (oldValue - min)/(max-min)

def autoNorm(dataSet):	# min(0)返回该矩阵中每一列的最小值	minVals = dataSet.min(0)	# max(0)返回该矩阵中每一列的最大值	maxVals = dataSet.max(0)	# 求出极值	ranges = maxVals - minVals	# 创建一个相同行列的0矩阵	normDataSet = zeros(shape(dataSet))	# 得到行数	m = dataSet.shape[0]	# 得到一个原矩阵减去m倍行1倍列的minVals	normDataSet = dataSet - tile(minVlas, (m,1))	# 特征值相除	normDataSet = normDataSet/tile(ranges, (m, 1))	return normDataSet, ranges, minVals

from sklearn.datasets import load_iris      # 导入内置数据集from sklearn.model_selection import train_test_split        # 提供数据集分类方法from sklearn.preprocessing import StandardScaler        # 标准化from sklearn.neighbors import KNeighborsClassifier      # KNNdef knn_iris():    # 获得鸢尾花数据集    iris = load_iris()    # 获取数据集    # random_state为随机数种子，一个数据集中相等的行不能大于6    x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6)    # 特征工程：标准化    transfer = StandardScaler()    # 训练集标准化    x_train = transfer.fit_transform(x_train)    # 测试集标准化    x_test = transfer.transform(x_test)    # 设置近邻个数    estimator = KNeighborsClassifier(n_neighbors=3)    # 训练集测试形成模型    estimator.fit(x_train, y_train)    # 模型预估    # 根据预测特征值得出预测目标值    y_predict = estimator.predict(x_test)    print("y_predict: ", y_predict)    # 得出预测目标值和真实目标值之间是否相等    print("直接比对真实值和预测值：", y_test == y_predict)    # 计算准确率    score = estimator.score(x_test, y_test)    print("准确率为：", score)def main():    knn_iris()if __name__ == "__main__":    main()