Merge pull request #30 from Harold-Ran/patch-2

Update K-means_Clustering.py

Author: Dod-o

Clustering/K-means_Clustering/K-means_Clustering.py

@@ -79,6 +79,7 @@ def cal_distance(xi, xj):
     dist = 0
     for col in range(len(xi)):
         dist += (xi[col]-xj[col]) ** 2
+    dist = math.sqrt(dist)
     return dist
 
 
@@ -125,8 +126,8 @@ def Adjusted_Rand_Index(group_dict, Ylist, k):
                 if n in group_dict[i] and n in y_dict[j]:
                     group_array[i][j] += 1  #如果数据n同时在group_dict的类别i和y_dict的类别j中，group_array[i][j]的数值加一
     RI = 0  #定义兰德系数(RI)
-    sum_i = np.zeros(3)  #定义一个数组，用于保存聚类结果group_dict中每一类的个数
-    sum_j = np.zeros(3)  #定义一个数组，用于保存外部标签y_dict中每一类的个数
+    sum_i = np.zeros(k)  #定义一个数组，用于保存聚类结果group_dict中每一类的个数
+    sum_j = np.zeros(k)  #定义一个数组，用于保存外部标签y_dict中每一类的个数
     for i in range(k):
         for j in range(k):
             sum_i[i] += group_array[i][j]
@@ -189,4 +190,4 @@ def Kmeans(Xarray, k, iters):
     group_dict, scores = Kmeans(Xarray, k, iters)  #进行k均值聚类
     end = time.time()  #保存结束时间
     print('Time:', end-start)
-    plt.plot(range(iters), scores)  #绘制ARI得分折线图
+    plt.plot(range(iters), scores)  #绘制ARI得分折线图