K近邻分类--python实现KNN分类，包含各种距离度量和预处理方法

import csv
from random import shuffle
from math import sqrt

#读取train.csv、test.csv
train = []
with open('D:\\train.csv', 'rt') as f:
    csvread = csv.reader(f)
    for i in csvread:
        i[0] = float(i[0])
        i[1] = float(i[1])
        i[2] = int(i[2])
        train.append(i)

test = []
with open('D:\\test.csv', 'rt') as f:
    csvread = csv.reader(f)
    for i in csvread:
        i[0] = float(i[0])
        i[1] = float(i[1])
        test.append(i)

#将训练集按4：1划分成估计集和验证集
train0 = []
train1 = []
gj = []
yz = []
for sample in train:
    if sample[-1] == 0:
        train0.append(sample)
    else:
        train1.append(sample)
l0 = int(len(train0) / 5)
l1 = int(len(train1) / 5)
shuffle(train0)
shuffle(train1)
yz = yz+train0[:l0]+train1[:l1]
gj = gj+train0[l0:]+train1[l1:]

#预处理
#0均值，1方差预处理方式
def a_v(train):
    average = []
    variance = []
    for i in range(len(train[0])-1):
        sum = 0
        for sample in train:
            sum += sample[i]
        average.append(sum/len(train))
    for i in range(len(train[0])-1):
        sum = 0
        for sample in train:
            sum += (sample[i]-average[i])**2
        variance.append(sqrt(sum/len(train)))

    for i in range(len(train)):
        for j in range(len(train[0])-1):
            train[i][j] = (train[i][j]-average[j])/variance[j]
    return average, variance

def a_v_t(test, average, variance):
    for i in range(len(test)):
        test[i][0] = (test[i][0]-average[0])/variance[0]
        test[i][1] = (test[i][1]-average[1])/variance[1]

#线性映射至[0,1]
def min_max(train):
    min = [10000,10000]
    max = [-10000,-10000]
    for sample in train:
        if sample[0] < min[0]:
            min[0] = sample[0]
        if sample[0] > max[0]:
            max[0] = sample[0]
        if sample[1] < min[1]:
            min[1] = sample[1]
        if sample[1] > max[1]:
            max[1] = sample[1]
    for i in range(len(train)):
        train[i][0] = (train[i][0]-min[0])/max[0]
        train[i][1] = (train[i][0]-min[1])/max[1]
    return min, max

def min_max_t(test,min,max):
    for i in range(len(test)):
        test[i][0] = (test[i][0]-min[0])/max[0]
        test[i][1] = (test[i][1]-min[1])/max[1]

#距离度量
#绝对值距离
def l1_dis(sample1,sample2):
    return abs(sample1[0]-sample2[0])+abs(sample1[1]-sample[1])
#欧式距离
def l2_dis(sample1,sample2):
    return sqrt((sample1[0]-sample2[0])**2 + (sample1[1]-sample2[1])**2)
#切氏距离
def l00_dis(sample1,sample2):
    return abs(sample1[0]-sample2[0]) if abs(sample1[0]-sample2[0]) > abs(sample1[1]-sample2[1]) else abs(sample1[1]-sample2[1])


#预处理
a, v = a_v(gj)
a_v_t(yz,a,v)

# min, max = min_max(gj)
# min_max_t(yz, min, max)

#用KNN模型进行预测
def KNN(train, test, k, dis_function):
    rig = 0
    for test_sample in test:
        temp_d = []
        temp_s = []
        for train_sample in train:
            d = dis_function(test_sample,train_sample)
            if len(temp_s) <= k:
                temp_d.append(d)
                temp_s.append(train_sample)
            else:
                for z in range(len(temp_d)):
                    if d < temp_d[z]:
                        temp_d[z], d = d, temp_d[z]
                        temp_s[z], train_sample = train_sample, temp_s[z]
        sum_0 = 0
        sum_1 = 0
        for m in temp_s:
            if m[-1] == 0:
                sum_0 += 1
            else:
                sum_1 +=1
        if sum_0 >= sum_1:
            p = 0
        else:
            p = 1
        if test_sample[-1] == p:
            rig+=1
    return rig/len(test)

 for k in range(1,11):
     print('k= ', k,':')
     print(round(KNN(gj, yz, k, l1_dis), 4))