# coding:utf-8

from collections import defaultdict

import numpy as np

from numpy import *

class knn:

def __init__(self):

pass

##给出训练数据以及对应的类别

def createDataSet(self):

group = array([[1.0, 2.0], [1.2, 0.1], [0.1, 1.4], [0.3, 3.5]])

labels = ['A', 'A', 'B', 'B']

return group, labels

###通过KNN进行分类

def classify(self, input, data_set, labels, k):

# 将input扩展成 n行的举证

in_matrix = tile(input, (len(data_set), 1))

# 输入举证和数据集做差 (x1-x2)

diff = in_matrix - data_set

# (x1-x2)**2

diff = diff ** 2

# (x1-x2)** 2 +(y1-y2)**2

sm = np.sum(diff, axis=1)

sm = np.sqrt(sm)

# 将距离排序

si = np.argsort(sm)

label_dict = defaultdict(int)

max_num = 0

target_lb = None

for i in range(k):

index = si[i]

lb = labels[index]

label_dict[lb] += 1

if label_dict[lb] > max_num:

max_num = label_dict[lb]

target_lb = lb

return target_lb

def norm_data_set(self, data_set):

'''

将数据集归一化

:param data_set:

:return:

'''

# 最大和最小的行向量

val_min = np.min(data_set, 0)

val_max = np.max(data_set, 0)

# 数据变动范围向量

val_range = val_max - val_min

row_num = data_set.shape[0]

matrix_range = tile(val_range, (row_num, 1))

matrix_sp = data_set - tile(val_min, (row_num, 1))

matrix_normal = matrix_sp / matrix_range

return matrix_normal

def norm_vec(self, vec, data_set):

'''

将被分类的向量归一化

:param vec:

:param data_set:

:return:

'''

data_set = np.vstack((data_set, vec))

# 最大和最小的行向量

val_min = np.min(data_set, 0)

val_max = np.max(data_set, 0)

# 数据变动范围向量

val_range = val_max - val_min

span = vec - val_min

return span / val_range

if __name__ == '__main__':

k = knn()

g, l = k.createDataSet()

ng = k.norm_data_set(g)

vec = [0.3, 3.2]

n_vec = k.norm_vec(vec, g)

b = k.classify(n_vec, ng, l, 4)