1 # 1 匯入模組和包
 2 import matplotlib.pyplot as plt #匯入繪製資料圖的資料庫
 3 from sklearn.datasets import make_blobs
 4 from sklearn.cluster import KMeans
 5 from sklearn.metrics import calinski_harabasz_score, silhouette_score
 6 from matplotlib.font_manager import FontProperties
 7 
 8 font_set = FontProperties(fname=r"
 
c:\windows\fonts\simsun.ttc", size=15)    #匯入漢字模板
 9 with open('result.csv', 'r', encoding='GBK') as f:      #開啟result.csv檔案（檔案可自己指定）
10     results = f.readlines()[1:100]  #讀取表格資料的從第二行到101行（多少行自己指定）
11     # res = []
12     # for it in results:
13     #     tmp = it.split(',')[1:]
14     #     tmp = list(map(lambda x: float(x), tmp))
 

15     #     res.append(it)
16     X = [list(map(lambda x: float(x), it.split(',')[1:])) for it in results] 
17 
18 # # 1、模型訓練
19 # y_pre = KMeans(n_clusters=clu_num).fit_predict(X)
20 
21 
22 # 1、建立空列表
23 sc_list = []
24 
25 # 2、設定中心點個數，檢視SC的變化範圍
26 for clu_num in range(2, 10):
27     # 初始化迭代器一次的Kmeans
 

28     my_kmeans = KMeans(n_clusters=clu_num, max_iter=100, random_state=0)
29     # 模型訓練
30     my_kmeans.fit(X)
31     y_pre = my_kmeans.fit_predict(X)
32 
33     # 將SC的每一次迭代結果新增到空列表內
34     sc_list.append(silhouette_score(X, y_pre))
35 
36 # 3、影象視覺化
37 plt.figure(figsize=(20, 8), dpi=100)
38 plt.scatter(range(2, 10), sc_list)
39 plt.plot(range(2, 10), sc_list)
40 x_ticks = range(1, 10, 1)
41 plt.xticks(x_ticks)
42 plt.xlabel('中心點個數', fontproperties=font_set)
43 plt.ylabel('輪廓係數', fontproperties=font_set)
44 plt.grid()
45 plt.show()