├── FCM.py
├── K_means.py
├── README.md
└── data
    ├── hh.png
    └── iris.data


/FCM.py:
--------------------------------------------------------------------------------
 1 | # -*- coding = utf-8 -*-
 2 | # @Time : 2021/11/21 13:33
 3 | # @Author : Luxlios
 4 | # @File : FCM.py
 5 | # @Software : PyCharm
 6 | 
 7 | import pandas as pd
 8 | import numpy as np
 9 | import matplotlib.pyplot as plt
10 | 
11 | # 数据标准化函数
12 | def generalization(data):
13 |     num = data.shape[1]   # 读取列数，对每一列标准化
14 |     _data = np.zeros([num,1], np.float)
15 |     for i in range(num):
16 |         _data = data[:,i]
17 |         _range = np.max(_data)-np.min(_data)
18 |         data[:,i] = (_data-np.min(_data))/_range
19 |     return data
20 | 
21 | 
22 | # FCM聚类算法（软聚类）
23 | # 采用初始化隶属度矩阵，计算聚类中心，计算代价行数后再更新隶属度矩阵的策略
24 | def FCM(data, K, alpha):
25 |     # 输入数据data和簇数K和柔性参数alpha
26 |     num = data.shape[0]
27 | 
28 |     # 每一行均匀分布并且和为1，对隶属度矩阵u初始化
29 |     u = np.random.random([num, K])
30 |     # np.sum后化作行array向量，因此需要添加一个低位轴转化为列array
31 |     u = np.divide(u, np.sum(u, axis=1)[:, np.newaxis])
32 | 
33 |     change = True  # 隶属度矩阵与阈值大小关系的flag
34 |     while change:
35 |         # 目标函数（总的欧式距离点乘隶属矩阵，所有元素之和）最小，
36 |         # 用lagrange乘数法得到隶属矩阵和聚类中心的更新公式
37 |         center = np.divide(np.dot((u ** alpha).T, data), np.sum(u ** alpha, axis=0)[:, np.newaxis])  # dot为矩阵乘法
38 | 
39 |         change = False
40 |         # 计算样本与聚类中心的距离
41 |         distance = np.zeros([num, K])
42 |         for i in range(num):
43 |             for j in range(K):
44 |                 distance[i, j] = np.linalg.norm(data[i, :] - center[j, :], ord=2)  # L2距离
45 | 
46 |         # 更新隶属度矩阵
47 |         u_new = np.zeros([num, K])
48 |         for i in range(num):
49 |             for j in range(K):
50 |                 u_new[i, j] = 1. / np.sum((distance[i, j] / distance[i, :]) ** (2 / (alpha - 1)))
51 | 
52 |         # 判断隶属度矩阵变化与阈值的比较
53 |         if np.sum(abs(u_new - u)) > 10:
54 |             change = True
55 |             u = u_new
56 |     # 返回聚类中心和样本隶属度矩阵
57 |     return center, u_new
58 | 
59 | # 展示聚类结果的函数
60 | # iris数据集有四维，只选用前三维数据进行展示
61 | def show(data, center, _class, k, name):
62 |     # 输入数据，聚类中心，分类结果，簇数
63 |     color = ['r', 'g', 'b', 'c', 'y', 'm']
64 |     num = data.shape[0]
65 |     picture = plt.subplot(111, projection='3d')
66 |     for i in range(k):
67 |         picture.scatter(center[i][0], center[i][1], center[i][2], c=color[i], marker='x')
68 |     for i in range(num):
69 |         picture.scatter(data[i][0], data[i][1], data[i][2], c=color[_class[i]], marker='.')
70 |     plt.title(name)
71 |     plt.show()
72 | 
73 | if __name__ == '__main__':
74 |     # IRIS数据集读取
75 |     data = pd.read_csv('.\data\iris.data', header=None)  # 有header会把第一行数据当列名
76 |     data = np.array(data)
77 |     x = data[:, [0, 1, 2, 3]]  # 数据
78 |     y = data[:, 4]  # 标签
79 |     x = generalization(x)  # 标准化
80 |     center2, u = FCM(x, 3, 2)
81 |     # 选取隶属度最大的作为种类，方便后续评价效果
82 |     class2 = np.argmax(u, axis=1)
83 |     show(x, center2, class2, 3, 'FCM')
84 | 


--------------------------------------------------------------------------------
/K_means.py:
--------------------------------------------------------------------------------
  1 | # -*- coding = utf-8 -*-
  2 | # @Time : 2021/11/21 13:26
  3 | # @Author : Luxlios
  4 | # @File : K_means.py
  5 | # @Software : PyCharm
  6 | 
  7 | import pandas as pd
  8 | import numpy as np
  9 | import cv2
 10 | import matplotlib.pyplot as plt
 11 | 
 12 | # 数据标准化函数
 13 | def generalization(data):
 14 |     num = data.shape[1]   # 读取列数，对每一列标准化
 15 |     _data = np.zeros([num,1], np.float)
 16 |     for i in range(num):
 17 |         _data = data[:,i]
 18 |         _range = np.max(_data)-np.min(_data)
 19 |         data[:,i] = (_data-np.min(_data))/_range
 20 |     return data
 21 | 
 22 | # Kmeans聚类算法(硬聚类)
 23 | def K_means(data, K):
 24 |     # 输入数据data和簇数K
 25 |     num = data.shape[0]
 26 |     _class = np.zeros([num], np.int)  # 保存每一个元素的分类
 27 | 
 28 |     # 初始化中心点，随机选取k个索引，得到k个初始中心点
 29 |     rand = np.random.random(size=K)  # np.random.randint(size)
 30 |     rand = rand * num
 31 |     rand = np.floor(rand).astype(int)
 32 |     center = data[rand]
 33 |     # print(rand)
 34 | 
 35 |     # 主体循环，通过初始中心对于所有数据点分类
 36 |     # 对于这些分类，每一类计算每一个维度的均值，得到新的中心点
 37 |     # 循环下去直到中心点不发生变化
 38 |     change = True  # 中心点是否变化的flag
 39 |     while change:
 40 |         distance = np.zeros([num, K])
 41 |         for i in range(num):
 42 |             for j in range(K):
 43 |                 # L2距离,得到样本与所有中心的距离
 44 |                 distance[i, j] = np.sqrt(np.sum((data[i, :] - center[j, :]) ** 2))
 45 | 
 46 |         for i in range(num):
 47 |             _class[i] = np.argmin(distance[i, :])  # 得到最近距离的索引
 48 | 
 49 |         change = False
 50 |         for i in range(K):
 51 |             cluster = data[_class == i]  # 得到分类索引为i的所有数据
 52 |             center_new = np.mean(cluster, axis=0)
 53 |             if np.sum(np.abs(center[i] - center_new), axis=0) > 10:
 54 |                 center[i] = center_new
 55 |                 change = True
 56 |     # 返回聚类中心和样本类别
 57 |     return center, _class
 58 | 
 59 | 
 60 | # 展示聚类结果的函数
 61 | # iris数据集有四维，只选用前三维数据进行展示
 62 | def show(data, center, _class, k, name):
 63 |     # 输入数据，聚类中心，分类结果，簇数
 64 |     plt.figure()
 65 |     color = ['r', 'g', 'b', 'c', 'y', 'm']
 66 |     num = data.shape[0]
 67 |     picture = plt.subplot(111, projection='3d')
 68 |     for i in range(k):
 69 |         picture.scatter(center[i][0], center[i][1], center[i][2], c=color[i], marker='x')
 70 |     for i in range(num):
 71 |         picture.scatter(data[i][0], data[i][1], data[i][2], c=color[_class[i]], marker='.')
 72 |     plt.title(name)
 73 | 
 74 | if __name__ == '__main__':
 75 |     # Iris数据集聚类
 76 |     data = pd.read_csv('.\data\iris.data', header=None)  # 有header会把第一行数据当列名
 77 |     data = np.array(data)
 78 |     x = data[:, [0, 1, 2, 3]]  # 数据
 79 |     y = data[:, 4]  # 标签
 80 |     x = generalization(x)  # 标准化
 81 |     center1, class1 = K_means(x, 3)
 82 |     show(x, center1, class1, 3, 'K_means')
 83 | 
 84 |     # 图像聚类分割
 85 |     img = cv2.imread('.\data\hh.png')
 86 |     _img = img.copy()
 87 |     _img = _img[:, :, ::-1]
 88 |     plt.figure()
 89 |     plt.subplot(111), plt.imshow(_img), plt.title('hh'), plt.axis('off')
 90 | 
 91 |     # 将图像像素矩阵读成一列
 92 |     pixel = img.reshape(-1, 3)
 93 |     pixel = np.float32(pixel)
 94 |     # K_means聚类
 95 |     center3, class3 = K_means(pixel, 4)
 96 |     center4, class4 = K_means(pixel, 6)
 97 |     center5, class5 = K_means(pixel, 8)
 98 | 
 99 |     # 聚类结果展示
100 |     k_picture3 = class3.reshape(img.shape[0], img.shape[1])
101 |     k_picture4 = class4.reshape(img.shape[0], img.shape[1])
102 |     k_picture5 = class5.reshape(img.shape[0], img.shape[1])
103 |     plt.figure()
104 |     plt.subplot(131), plt.imshow(k_picture3), plt.title('k=4'), plt.axis('off')
105 |     plt.subplot(132), plt.imshow(k_picture4), plt.title('k=6'), plt.axis('off')
106 |     plt.subplot(133), plt.imshow(k_picture5), plt.title('k=8'), plt.axis('off')
107 |     plt.show()
108 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | ### Clustering
 2 | 手写K均值K_means和模糊C均值FCM算法对Iris鸢尾花数据集聚类以及图像聚类分割
 3 | 
 4 | 数据集：[Iris](http://archive.ics.uci.edu/ml/datasets/Iris) 
 5 | 
 6 | ### Requirement
 7 | `pandas`  
 8 | `numpy`  
 9 | `cv2`  
10 | `matplotlib`
11 | 
12 | ### Content
13 | - [算法流程图](#算法流程图)
14 | - [结果展示](#结果展示)
15 |   - [K_means](#K_mean算法在Iris数据集聚类和图片聚类分割结果)
16 |   - [FCM](#FCM算法在Iris数据集聚类结果)
17 | 
18 | ### 算法流程图
19 | <div align=center>
20 | <img src="https://github.com/Luxlios/Figure/blob/main/Clustering/flow_chart.png" height="700">
21 | </div>
22 | 左边为K均值K_means算法流程图，右边为模糊C均值FCM算法流程图
23 | 
24 | ### 结果展示
25 | #### K_mean算法在Iris数据集聚类和图片聚类分割结果
26 | 鸢尾花数据集有四维特征，这里只展示前三维。
27 | <div align=center>
28 | <img src="https://github.com/Luxlios/Figure/blob/main/Clustering/K_means.png" height="300">
29 | </div>
30 | 原图片如下。
31 | <div align=center>
32 | <img src="https://github.com/Luxlios/Figure/blob/main/Clustering/hh.png" height="300">
33 | </div>
34 | 聚类分割结果如下，簇数分别为4、6、8。
35 | <div align=center>
36 | <img src="https://github.com/Luxlios/Figure/blob/main/Clustering/K_means_img_segment.png" height="300">
37 | </div>
38 | 
39 | #### FCM算法在Iris数据集聚类结果
40 | 鸢尾花数据集有四维特征，这里只展示前三维。同时，由于FCM算法得到的是隶属度矩阵，为了展示，取每个样本隶属度最大的作为其聚类结果。
41 | <div align=center>
42 | <img src="https://github.com/Luxlios/Figure/blob/main/Clustering/FCM.png" height="300">
43 | </div> 
44 | 


--------------------------------------------------------------------------------
/data/hh.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Luxlios/Clustering/60925f742d22af0d172ba31d8a1ccb1128b1f93a/data/hh.png


--------------------------------------------------------------------------------
/data/iris.data:
--------------------------------------------------------------------------------
  1 | 5.1,3.5,1.4,0.2,Iris-setosa
  2 | 4.9,3.0,1.4,0.2,Iris-setosa
  3 | 4.7,3.2,1.3,0.2,Iris-setosa
  4 | 4.6,3.1,1.5,0.2,Iris-setosa
  5 | 5.0,3.6,1.4,0.2,Iris-setosa
  6 | 5.4,3.9,1.7,0.4,Iris-setosa
  7 | 4.6,3.4,1.4,0.3,Iris-setosa
  8 | 5.0,3.4,1.5,0.2,Iris-setosa
  9 | 4.4,2.9,1.4,0.2,Iris-setosa
 10 | 4.9,3.1,1.5,0.1,Iris-setosa
 11 | 5.4,3.7,1.5,0.2,Iris-setosa
 12 | 4.8,3.4,1.6,0.2,Iris-setosa
 13 | 4.8,3.0,1.4,0.1,Iris-setosa
 14 | 4.3,3.0,1.1,0.1,Iris-setosa
 15 | 5.8,4.0,1.2,0.2,Iris-setosa
 16 | 5.7,4.4,1.5,0.4,Iris-setosa
 17 | 5.4,3.9,1.3,0.4,Iris-setosa
 18 | 5.1,3.5,1.4,0.3,Iris-setosa
 19 | 5.7,3.8,1.7,0.3,Iris-setosa
 20 | 5.1,3.8,1.5,0.3,Iris-setosa
 21 | 5.4,3.4,1.7,0.2,Iris-setosa
 22 | 5.1,3.7,1.5,0.4,Iris-setosa
 23 | 4.6,3.6,1.0,0.2,Iris-setosa
 24 | 5.1,3.3,1.7,0.5,Iris-setosa
 25 | 4.8,3.4,1.9,0.2,Iris-setosa
 26 | 5.0,3.0,1.6,0.2,Iris-setosa
 27 | 5.0,3.4,1.6,0.4,Iris-setosa
 28 | 5.2,3.5,1.5,0.2,Iris-setosa
 29 | 5.2,3.4,1.4,0.2,Iris-setosa
 30 | 4.7,3.2,1.6,0.2,Iris-setosa
 31 | 4.8,3.1,1.6,0.2,Iris-setosa
 32 | 5.4,3.4,1.5,0.4,Iris-setosa
 33 | 5.2,4.1,1.5,0.1,Iris-setosa
 34 | 5.5,4.2,1.4,0.2,Iris-setosa
 35 | 4.9,3.1,1.5,0.1,Iris-setosa
 36 | 5.0,3.2,1.2,0.2,Iris-setosa
 37 | 5.5,3.5,1.3,0.2,Iris-setosa
 38 | 4.9,3.1,1.5,0.1,Iris-setosa
 39 | 4.4,3.0,1.3,0.2,Iris-setosa
 40 | 5.1,3.4,1.5,0.2,Iris-setosa
 41 | 5.0,3.5,1.3,0.3,Iris-setosa
 42 | 4.5,2.3,1.3,0.3,Iris-setosa
 43 | 4.4,3.2,1.3,0.2,Iris-setosa
 44 | 5.0,3.5,1.6,0.6,Iris-setosa
 45 | 5.1,3.8,1.9,0.4,Iris-setosa
 46 | 4.8,3.0,1.4,0.3,Iris-setosa
 47 | 5.1,3.8,1.6,0.2,Iris-setosa
 48 | 4.6,3.2,1.4,0.2,Iris-setosa
 49 | 5.3,3.7,1.5,0.2,Iris-setosa
 50 | 5.0,3.3,1.4,0.2,Iris-setosa
 51 | 7.0,3.2,4.7,1.4,Iris-versicolor
 52 | 6.4,3.2,4.5,1.5,Iris-versicolor
 53 | 6.9,3.1,4.9,1.5,Iris-versicolor
 54 | 5.5,2.3,4.0,1.3,Iris-versicolor
 55 | 6.5,2.8,4.6,1.5,Iris-versicolor
 56 | 5.7,2.8,4.5,1.3,Iris-versicolor
 57 | 6.3,3.3,4.7,1.6,Iris-versicolor
 58 | 4.9,2.4,3.3,1.0,Iris-versicolor
 59 | 6.6,2.9,4.6,1.3,Iris-versicolor
 60 | 5.2,2.7,3.9,1.4,Iris-versicolor
 61 | 5.0,2.0,3.5,1.0,Iris-versicolor
 62 | 5.9,3.0,4.2,1.5,Iris-versicolor
 63 | 6.0,2.2,4.0,1.0,Iris-versicolor
 64 | 6.1,2.9,4.7,1.4,Iris-versicolor
 65 | 5.6,2.9,3.6,1.3,Iris-versicolor
 66 | 6.7,3.1,4.4,1.4,Iris-versicolor
 67 | 5.6,3.0,4.5,1.5,Iris-versicolor
 68 | 5.8,2.7,4.1,1.0,Iris-versicolor
 69 | 6.2,2.2,4.5,1.5,Iris-versicolor
 70 | 5.6,2.5,3.9,1.1,Iris-versicolor
 71 | 5.9,3.2,4.8,1.8,Iris-versicolor
 72 | 6.1,2.8,4.0,1.3,Iris-versicolor
 73 | 6.3,2.5,4.9,1.5,Iris-versicolor
 74 | 6.1,2.8,4.7,1.2,Iris-versicolor
 75 | 6.4,2.9,4.3,1.3,Iris-versicolor
 76 | 6.6,3.0,4.4,1.4,Iris-versicolor
 77 | 6.8,2.8,4.8,1.4,Iris-versicolor
 78 | 6.7,3.0,5.0,1.7,Iris-versicolor
 79 | 6.0,2.9,4.5,1.5,Iris-versicolor
 80 | 5.7,2.6,3.5,1.0,Iris-versicolor
 81 | 5.5,2.4,3.8,1.1,Iris-versicolor
 82 | 5.5,2.4,3.7,1.0,Iris-versicolor
 83 | 5.8,2.7,3.9,1.2,Iris-versicolor
 84 | 6.0,2.7,5.1,1.6,Iris-versicolor
 85 | 5.4,3.0,4.5,1.5,Iris-versicolor
 86 | 6.0,3.4,4.5,1.6,Iris-versicolor
 87 | 6.7,3.1,4.7,1.5,Iris-versicolor
 88 | 6.3,2.3,4.4,1.3,Iris-versicolor
 89 | 5.6,3.0,4.1,1.3,Iris-versicolor
 90 | 5.5,2.5,4.0,1.3,Iris-versicolor
 91 | 5.5,2.6,4.4,1.2,Iris-versicolor
 92 | 6.1,3.0,4.6,1.4,Iris-versicolor
 93 | 5.8,2.6,4.0,1.2,Iris-versicolor
 94 | 5.0,2.3,3.3,1.0,Iris-versicolor
 95 | 5.6,2.7,4.2,1.3,Iris-versicolor
 96 | 5.7,3.0,4.2,1.2,Iris-versicolor
 97 | 5.7,2.9,4.2,1.3,Iris-versicolor
 98 | 6.2,2.9,4.3,1.3,Iris-versicolor
 99 | 5.1,2.5,3.0,1.1,Iris-versicolor
100 | 5.7,2.8,4.1,1.3,Iris-versicolor
101 | 6.3,3.3,6.0,2.5,Iris-virginica
102 | 5.8,2.7,5.1,1.9,Iris-virginica
103 | 7.1,3.0,5.9,2.1,Iris-virginica
104 | 6.3,2.9,5.6,1.8,Iris-virginica
105 | 6.5,3.0,5.8,2.2,Iris-virginica
106 | 7.6,3.0,6.6,2.1,Iris-virginica
107 | 4.9,2.5,4.5,1.7,Iris-virginica
108 | 7.3,2.9,6.3,1.8,Iris-virginica
109 | 6.7,2.5,5.8,1.8,Iris-virginica
110 | 7.2,3.6,6.1,2.5,Iris-virginica
111 | 6.5,3.2,5.1,2.0,Iris-virginica
112 | 6.4,2.7,5.3,1.9,Iris-virginica
113 | 6.8,3.0,5.5,2.1,Iris-virginica
114 | 5.7,2.5,5.0,2.0,Iris-virginica
115 | 5.8,2.8,5.1,2.4,Iris-virginica
116 | 6.4,3.2,5.3,2.3,Iris-virginica
117 | 6.5,3.0,5.5,1.8,Iris-virginica
118 | 7.7,3.8,6.7,2.2,Iris-virginica
119 | 7.7,2.6,6.9,2.3,Iris-virginica
120 | 6.0,2.2,5.0,1.5,Iris-virginica
121 | 6.9,3.2,5.7,2.3,Iris-virginica
122 | 5.6,2.8,4.9,2.0,Iris-virginica
123 | 7.7,2.8,6.7,2.0,Iris-virginica
124 | 6.3,2.7,4.9,1.8,Iris-virginica
125 | 6.7,3.3,5.7,2.1,Iris-virginica
126 | 7.2,3.2,6.0,1.8,Iris-virginica
127 | 6.2,2.8,4.8,1.8,Iris-virginica
128 | 6.1,3.0,4.9,1.8,Iris-virginica
129 | 6.4,2.8,5.6,2.1,Iris-virginica
130 | 7.2,3.0,5.8,1.6,Iris-virginica
131 | 7.4,2.8,6.1,1.9,Iris-virginica
132 | 7.9,3.8,6.4,2.0,Iris-virginica
133 | 6.4,2.8,5.6,2.2,Iris-virginica
134 | 6.3,2.8,5.1,1.5,Iris-virginica
135 | 6.1,2.6,5.6,1.4,Iris-virginica
136 | 7.7,3.0,6.1,2.3,Iris-virginica
137 | 6.3,3.4,5.6,2.4,Iris-virginica
138 | 6.4,3.1,5.5,1.8,Iris-virginica
139 | 6.0,3.0,4.8,1.8,Iris-virginica
140 | 6.9,3.1,5.4,2.1,Iris-virginica
141 | 6.7,3.1,5.6,2.4,Iris-virginica
142 | 6.9,3.1,5.1,2.3,Iris-virginica
143 | 5.8,2.7,5.1,1.9,Iris-virginica
144 | 6.8,3.2,5.9,2.3,Iris-virginica
145 | 6.7,3.3,5.7,2.5,Iris-virginica
146 | 6.7,3.0,5.2,2.3,Iris-virginica
147 | 6.3,2.5,5.0,1.9,Iris-virginica
148 | 6.5,3.0,5.2,2.0,Iris-virginica
149 | 6.2,3.4,5.4,2.3,Iris-virginica
150 | 5.9,3.0,5.1,1.8,Iris-virginica
151 | 
152 | 


--------------------------------------------------------------------------------