Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 100ec91

Browse files
提交第 120 天文章《机器学习算法之 K均值聚类》对应示例代码
1 parent 023673c commit 100ec91

File tree

3 files changed

+282
-0
lines changed

3 files changed

+282
-0
lines changed

‎day-120/Iris.csv‎

Lines changed: 151 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,151 @@
1+
Id,SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Species
2+
1,5.1,3.5,1.4,0.2,Iris-setosa
3+
2,4.9,3.0,1.4,0.2,Iris-setosa
4+
3,4.7,3.2,1.3,0.2,Iris-setosa
5+
4,4.6,3.1,1.5,0.2,Iris-setosa
6+
5,5.0,3.6,1.4,0.2,Iris-setosa
7+
6,5.4,3.9,1.7,0.4,Iris-setosa
8+
7,4.6,3.4,1.4,0.3,Iris-setosa
9+
8,5.0,3.4,1.5,0.2,Iris-setosa
10+
9,4.4,2.9,1.4,0.2,Iris-setosa
11+
10,4.9,3.1,1.5,0.1,Iris-setosa
12+
11,5.4,3.7,1.5,0.2,Iris-setosa
13+
12,4.8,3.4,1.6,0.2,Iris-setosa
14+
13,4.8,3.0,1.4,0.1,Iris-setosa
15+
14,4.3,3.0,1.1,0.1,Iris-setosa
16+
15,5.8,4.0,1.2,0.2,Iris-setosa
17+
16,5.7,4.4,1.5,0.4,Iris-setosa
18+
17,5.4,3.9,1.3,0.4,Iris-setosa
19+
18,5.1,3.5,1.4,0.3,Iris-setosa
20+
19,5.7,3.8,1.7,0.3,Iris-setosa
21+
20,5.1,3.8,1.5,0.3,Iris-setosa
22+
21,5.4,3.4,1.7,0.2,Iris-setosa
23+
22,5.1,3.7,1.5,0.4,Iris-setosa
24+
23,4.6,3.6,1.0,0.2,Iris-setosa
25+
24,5.1,3.3,1.7,0.5,Iris-setosa
26+
25,4.8,3.4,1.9,0.2,Iris-setosa
27+
26,5.0,3.0,1.6,0.2,Iris-setosa
28+
27,5.0,3.4,1.6,0.4,Iris-setosa
29+
28,5.2,3.5,1.5,0.2,Iris-setosa
30+
29,5.2,3.4,1.4,0.2,Iris-setosa
31+
30,4.7,3.2,1.6,0.2,Iris-setosa
32+
31,4.8,3.1,1.6,0.2,Iris-setosa
33+
32,5.4,3.4,1.5,0.4,Iris-setosa
34+
33,5.2,4.1,1.5,0.1,Iris-setosa
35+
34,5.5,4.2,1.4,0.2,Iris-setosa
36+
35,4.9,3.1,1.5,0.1,Iris-setosa
37+
36,5.0,3.2,1.2,0.2,Iris-setosa
38+
37,5.5,3.5,1.3,0.2,Iris-setosa
39+
38,4.9,3.1,1.5,0.1,Iris-setosa
40+
39,4.4,3.0,1.3,0.2,Iris-setosa
41+
40,5.1,3.4,1.5,0.2,Iris-setosa
42+
41,5.0,3.5,1.3,0.3,Iris-setosa
43+
42,4.5,2.3,1.3,0.3,Iris-setosa
44+
43,4.4,3.2,1.3,0.2,Iris-setosa
45+
44,5.0,3.5,1.6,0.6,Iris-setosa
46+
45,5.1,3.8,1.9,0.4,Iris-setosa
47+
46,4.8,3.0,1.4,0.3,Iris-setosa
48+
47,5.1,3.8,1.6,0.2,Iris-setosa
49+
48,4.6,3.2,1.4,0.2,Iris-setosa
50+
49,5.3,3.7,1.5,0.2,Iris-setosa
51+
50,5.0,3.3,1.4,0.2,Iris-setosa
52+
51,7.0,3.2,4.7,1.4,Iris-versicolor
53+
52,6.4,3.2,4.5,1.5,Iris-versicolor
54+
53,6.9,3.1,4.9,1.5,Iris-versicolor
55+
54,5.5,2.3,4.0,1.3,Iris-versicolor
56+
55,6.5,2.8,4.6,1.5,Iris-versicolor
57+
56,5.7,2.8,4.5,1.3,Iris-versicolor
58+
57,6.3,3.3,4.7,1.6,Iris-versicolor
59+
58,4.9,2.4,3.3,1.0,Iris-versicolor
60+
59,6.6,2.9,4.6,1.3,Iris-versicolor
61+
60,5.2,2.7,3.9,1.4,Iris-versicolor
62+
61,5.0,2.0,3.5,1.0,Iris-versicolor
63+
62,5.9,3.0,4.2,1.5,Iris-versicolor
64+
63,6.0,2.2,4.0,1.0,Iris-versicolor
65+
64,6.1,2.9,4.7,1.4,Iris-versicolor
66+
65,5.6,2.9,3.6,1.3,Iris-versicolor
67+
66,6.7,3.1,4.4,1.4,Iris-versicolor
68+
67,5.6,3.0,4.5,1.5,Iris-versicolor
69+
68,5.8,2.7,4.1,1.0,Iris-versicolor
70+
69,6.2,2.2,4.5,1.5,Iris-versicolor
71+
70,5.6,2.5,3.9,1.1,Iris-versicolor
72+
71,5.9,3.2,4.8,1.8,Iris-versicolor
73+
72,6.1,2.8,4.0,1.3,Iris-versicolor
74+
73,6.3,2.5,4.9,1.5,Iris-versicolor
75+
74,6.1,2.8,4.7,1.2,Iris-versicolor
76+
75,6.4,2.9,4.3,1.3,Iris-versicolor
77+
76,6.6,3.0,4.4,1.4,Iris-versicolor
78+
77,6.8,2.8,4.8,1.4,Iris-versicolor
79+
78,6.7,3.0,5.0,1.7,Iris-versicolor
80+
79,6.0,2.9,4.5,1.5,Iris-versicolor
81+
80,5.7,2.6,3.5,1.0,Iris-versicolor
82+
81,5.5,2.4,3.8,1.1,Iris-versicolor
83+
82,5.5,2.4,3.7,1.0,Iris-versicolor
84+
83,5.8,2.7,3.9,1.2,Iris-versicolor
85+
84,6.0,2.7,5.1,1.6,Iris-versicolor
86+
85,5.4,3.0,4.5,1.5,Iris-versicolor
87+
86,6.0,3.4,4.5,1.6,Iris-versicolor
88+
87,6.7,3.1,4.7,1.5,Iris-versicolor
89+
88,6.3,2.3,4.4,1.3,Iris-versicolor
90+
89,5.6,3.0,4.1,1.3,Iris-versicolor
91+
90,5.5,2.5,4.0,1.3,Iris-versicolor
92+
91,5.5,2.6,4.4,1.2,Iris-versicolor
93+
92,6.1,3.0,4.6,1.4,Iris-versicolor
94+
93,5.8,2.6,4.0,1.2,Iris-versicolor
95+
94,5.0,2.3,3.3,1.0,Iris-versicolor
96+
95,5.6,2.7,4.2,1.3,Iris-versicolor
97+
96,5.7,3.0,4.2,1.2,Iris-versicolor
98+
97,5.7,2.9,4.2,1.3,Iris-versicolor
99+
98,6.2,2.9,4.3,1.3,Iris-versicolor
100+
99,5.1,2.5,3.0,1.1,Iris-versicolor
101+
100,5.7,2.8,4.1,1.3,Iris-versicolor
102+
101,6.3,3.3,6.0,2.5,Iris-virginica
103+
102,5.8,2.7,5.1,1.9,Iris-virginica
104+
103,7.1,3.0,5.9,2.1,Iris-virginica
105+
104,6.3,2.9,5.6,1.8,Iris-virginica
106+
105,6.5,3.0,5.8,2.2,Iris-virginica
107+
106,7.6,3.0,6.6,2.1,Iris-virginica
108+
107,4.9,2.5,4.5,1.7,Iris-virginica
109+
108,7.3,2.9,6.3,1.8,Iris-virginica
110+
109,6.7,2.5,5.8,1.8,Iris-virginica
111+
110,7.2,3.6,6.1,2.5,Iris-virginica
112+
111,6.5,3.2,5.1,2.0,Iris-virginica
113+
112,6.4,2.7,5.3,1.9,Iris-virginica
114+
113,6.8,3.0,5.5,2.1,Iris-virginica
115+
114,5.7,2.5,5.0,2.0,Iris-virginica
116+
115,5.8,2.8,5.1,2.4,Iris-virginica
117+
116,6.4,3.2,5.3,2.3,Iris-virginica
118+
117,6.5,3.0,5.5,1.8,Iris-virginica
119+
118,7.7,3.8,6.7,2.2,Iris-virginica
120+
119,7.7,2.6,6.9,2.3,Iris-virginica
121+
120,6.0,2.2,5.0,1.5,Iris-virginica
122+
121,6.9,3.2,5.7,2.3,Iris-virginica
123+
122,5.6,2.8,4.9,2.0,Iris-virginica
124+
123,7.7,2.8,6.7,2.0,Iris-virginica
125+
124,6.3,2.7,4.9,1.8,Iris-virginica
126+
125,6.7,3.3,5.7,2.1,Iris-virginica
127+
126,7.2,3.2,6.0,1.8,Iris-virginica
128+
127,6.2,2.8,4.8,1.8,Iris-virginica
129+
128,6.1,3.0,4.9,1.8,Iris-virginica
130+
129,6.4,2.8,5.6,2.1,Iris-virginica
131+
130,7.2,3.0,5.8,1.6,Iris-virginica
132+
131,7.4,2.8,6.1,1.9,Iris-virginica
133+
132,7.9,3.8,6.4,2.0,Iris-virginica
134+
133,6.4,2.8,5.6,2.2,Iris-virginica
135+
134,6.3,2.8,5.1,1.5,Iris-virginica
136+
135,6.1,2.6,5.6,1.4,Iris-virginica
137+
136,7.7,3.0,6.1,2.3,Iris-virginica
138+
137,6.3,3.4,5.6,2.4,Iris-virginica
139+
138,6.4,3.1,5.5,1.8,Iris-virginica
140+
139,6.0,3.0,4.8,1.8,Iris-virginica
141+
140,6.9,3.1,5.4,2.1,Iris-virginica
142+
141,6.7,3.1,5.6,2.4,Iris-virginica
143+
142,6.9,3.1,5.1,2.3,Iris-virginica
144+
143,5.8,2.7,5.1,1.9,Iris-virginica
145+
144,6.8,3.2,5.9,2.3,Iris-virginica
146+
145,6.7,3.3,5.7,2.5,Iris-virginica
147+
146,6.7,3.0,5.2,2.3,Iris-virginica
148+
147,6.3,2.5,5.0,1.9,Iris-virginica
149+
148,6.5,3.0,5.2,2.0,Iris-virginica
150+
149,6.2,3.4,5.4,2.3,Iris-virginica
151+
150,5.9,3.0,5.1,1.8,Iris-virginica

‎day-120/__init__.py‎

Whitespace-only changes.

‎day-120/clusters.py‎

Lines changed: 131 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,131 @@
1+
'''
2+
__author__ = justdopython.com
3+
'''
4+
import numpy as np
5+
import pandas as pd
6+
import random
7+
8+
9+
class Clusters():
10+
def __init__(self, train_data, K):
11+
'''
12+
:params train_data: ndarray. 训练数据.
13+
:params K: int. 要划分的簇的数量.
14+
15+
:attr train_data:
16+
'''
17+
super().__init__()
18+
19+
self.train_data = train_data
20+
self.K = K
21+
# 标记聚类是否完成。具体的真假,取决于是否还存在需要从一个簇移动到另一个簇的数据
22+
self.finished = False
23+
24+
# 随机选取 K 个数据作为各个簇的中心点
25+
index = random.sample(range(len(self.train_data)), self.K)
26+
self.centroid = train_data[index, 1:5]
27+
28+
# 将训练数据均匀分配到各个簇,以便以同一的形式适用于数据的分配
29+
self.clusters = []
30+
offset = len(train_data) // self.K
31+
for i in range(self.K):
32+
start = offset * i
33+
if i < self.K-1:
34+
self.clusters.append(train_data[start:start+offset,:])
35+
else:
36+
# 最后一个簇包含剩下的所有数据
37+
self.clusters.append(train_data[start:,:])
38+
39+
40+
# 加载所要用到的数据集
41+
@staticmethod
42+
def getData():
43+
'''
44+
获取数据,返回值类型为 ndarray
45+
'''
46+
train_data = pd.read_csv('iris.csv').to_numpy()
47+
48+
return train_data
49+
50+
# 将各数据分配到每个簇中去
51+
def assign(self):
52+
self.finished = True
53+
# data_index_list 和 target_index_list 分别记录"需要移动的数据在当前簇中的索引"以及"要移动到的目标簇索引"
54+
target_index_list = []
55+
data_index_list = []
56+
for i in range(self.K):
57+
target_index_list.append([])
58+
data_index_list.append([])
59+
60+
for cluster_index in range(len(self.clusters)):
61+
for data_index in range(len(self.clusters[cluster_index])):
62+
diff = self.clusters[cluster_index][data_index, 1:5] - self.centroid
63+
distance_square = np.sum(diff * diff, axis=1)
64+
target_index = np.argmin(distance_square)
65+
66+
if cluster_index != target_index:
67+
self.finished = False
68+
target_index_list[cluster_index].append(target_index)
69+
data_index_list[cluster_index].append(data_index)
70+
71+
for cluster_index in range(self.K):
72+
for index in range(len(target_index_list[cluster_index])):
73+
target_index = target_index_list[cluster_index][index]
74+
data_index = data_index_list[cluster_index][index]
75+
76+
self.clusters[target_index] = np.append(self.clusters[target_index],
77+
self.clusters[cluster_index][data_index, :]).reshape(-1, 6)
78+
79+
for cluster_index in range(self.K):
80+
data_index = data_index_list[cluster_index]
81+
self.clusters[cluster_index] = np.delete(self.clusters[cluster_index], data_index, axis=0)
82+
83+
84+
# 更新各个簇的质心
85+
def update(self):
86+
for cluster_index in range(len(self.clusters)):
87+
self.centroid[cluster_index] = np.mean(self.clusters[cluster_index][:,1:5], axis=0)
88+
89+
def train(self):
90+
'''
91+
进行聚类训练
92+
'''
93+
while not self.finished:
94+
self.assign()
95+
self.update()
96+
print('训练完成!!!')
97+
98+
def printResult(self):
99+
'''
100+
打印聚类结果
101+
'''
102+
print('-'*80)
103+
print('*'*80)
104+
print('-'*80)
105+
print('*'*30, '聚类结果', '*'*30)
106+
print('-'*30,'各簇中心','-'*30)
107+
for i in range(self.K):
108+
print('第', str(i), '簇中心:', self.centroid[i])
109+
print('-'*80)
110+
print('-'*30,'各簇结果','-'*30)
111+
for i in range(self.K):
112+
print('-'*20, '第', str(i), '簇结果', '-'*20,)
113+
for d in self.clusters[i]:
114+
print(d[5])
115+
116+
print('-'*80)
117+
print('*'*80)
118+
print('-'*80)
119+
120+
121+
122+
123+
if __name__ == '__main__':
124+
print('-'*80)
125+
K = int(input('请输入要划分的簇数(应为正整数):'))
126+
data = Clusters.getData()
127+
clusters = Clusters(data, K)
128+
129+
clusters.train()
130+
131+
clusters.printResult()

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /