1. K-Means算法缺点
1)对k个初始质心的选择比较敏感,容易陷入局部最小值。如下面这两种情况。K-Means也是收敛了,只是收敛到了局部最小值。
2)k值得选择是用户指定的,不同的k得到的结果会有挺大的不同,如下图所示,左边是k=3的结果,蓝色的簇太稀疏了,蓝色的簇应该可以再划分成两个簇。右边的是k=5的结果,红色和蓝色的簇应该合并为一个簇
3)存在局限性,如下面这种非球状的数据分布就搞不定了。
4)数据量比较大的时候,收敛会比较慢。
2. K-Means算法优化
1)使用多次的随机初始化,计算每一次建模得到的代价函数的值,选取代价函数最小结果作为聚类结果。
2)使用肘部法则来选择k的值。如下图所示:
3. 肘部法则代码实现
注:数据集在文章末尾
import numpy as np
import matplotlib.pyplot as plt
# 载入数据
data = np.genfromtxt("kmeans.txt", delimiter=" ")
##### 模型训练
# 计算距离
def euclDistance(vector1, vector2):
return np.sqrt(sum((vector2 - vector1)**2))
# 初始化质心
def initCentroids(data, k):
numSamples, dim = data.shape
# k个质心,列数跟样本的列数一样
centroids = np.zeros((k, dim))
# 随机选出k个质心
for i in range(k):
# 随机选取一个样本的索引
index = int(np.random.uniform(0, numSamples))
# 作为初始化的质心
centroids[i, :] = data[index, :]
return centroids
# 传入数据集和k的值
def kmeans(data, k):
# 计算样本个数
numSamples = data.shape[0]
# 样本的属性,第一列保存该样本属于哪个簇,第二列保存该样本跟它所属簇的误差
clusterData = np.array(np.zeros((numSamples, 2)))
# 决定质心是否要改变的变量
clusterChanged = True
# 初始化质心
centroids = initCentroids(data, k)
while clusterChanged:
clusterChanged = False
# 循环每一个样本
for i in range(numSamples):
# 最小距离
minDist = 100000.0
# 定义样本所属的簇
minIndex = 0
# 循环计算每一个质心与该样本的距离
for j in range(k):
# 循环每一个质心和样本,计算距离
distance = euclDistance(centroids[j, :], data[i, :])
# 如果计算的距离小于最小距离,则更新最小距离
if distance < minDist:
minDist = distance
# 更新样本所属的簇
minIndex = j
# 更新最小距离
clusterData[i, 1] = distance
# 如果样本的所属的簇发生了变化
if clusterData[i, 0] != minIndex:
# 质心要重新计算
clusterChanged = True
# 更新样本的簇
clusterData[i, 0] = minIndex
# 更新质心
for j in range(k):
# 获取第j个簇所有的样本所在的索引
cluster_index = np.nonzero(clusterData[:, 0] == j)
# 第j个簇所有的样本点
pointsInCluster = data[cluster_index]
# 计算质心
centroids[j, :] = np.mean(pointsInCluster, axis = 0)
# showCluster(data, k, centroids, clusterData)
return centroids, clusterData
# 显示结果
def showCluster(data, k, centroids, clusterData):
numSamples, dim = data.shape
if dim != 2:
print("dimension of your data is not 2!")
return 1
# 用不同颜色形状来表示各个类别
mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr', '<r', 'pr']
if k > len(mark):
print("Your k is too large!")
return 1
# 画样本点
for i in range(numSamples):
markIndex = int(clusterData[i, 0])
plt.plot(data[i, 0], data[i, 1], mark[markIndex])
# 用不同颜色形状来表示各个类别
mark = ['*r', '*b', '*g', '*k', '^b', '+b', 'sb', 'db', '<b', 'pb']
# 画质心点
for i in range(k):
plt.plot(centroids[i, 0], centroids[i, 1], mark[i], markersize = 20)
plt.show()
list_lost = []
for k in range(2,10):
min_loss = 10000
min_loss_centroids = np.array([])
min_loss_clusterData = np.array([])
for i in range(50):
# centroids 簇的中心点
# cluster Data样本的属性,第一列保存该样本属于哪个簇,第二列保存该样本跟它所属簇的误差
centroids, clusterData = kmeans(data, k)
loss = sum(clusterData[:,1])/data.shape[0]
if loss < min_loss:
min_loss = loss
min_loss_centroids = centroids
min_loss_clusterData = clusterData
list_lost.append(min_loss)
print(list_lost)
# print('loss',min_loss)
# print('cluster complete!')
# centroids = min_loss_centroids
# clusterData = min_loss_clusterData
# 显示结果
# showCluster(data, k, centroids, clusterData)
输出:
# 画图
plt.plot(range(2,10),list_lost)
plt.xlabel('k')
plt.ylabel('loss')
plt.show()
输出:
数据集:“kmeans.txt”:
1.658985 4.285136
-3.453687 3.424321
4.838138 -1.151539
-5.379713 -3.362104
0.972564 2.924086
-3.567919 1.531611
0.450614 -3.302219
-3.487105 -1.724432
2.668759 1.594842
-3.156485 3.191137
3.165506 -3.999838
-2.786837 -3.099354
4.208187 2.984927
-2.123337 2.943366
0.704199 -0.479481
-0.392370 -3.963704
2.831667 1.574018
-0.790153 3.343144
2.943496 -3.357075
-3.195883 -2.283926
2.336445 2.875106
-1.786345 2.554248
2.190101 -1.906020
-3.403367 -2.778288
1.778124 3.880832
-1.688346 2.230267
2.592976 -2.054368
-4.007257 -3.207066
2.257734 3.387564
-2.679011 0.785119
0.939512 -4.023563
-3.674424 -2.261084
2.046259 2.735279
-3.189470 1.780269
4.372646 -0.822248
-2.579316 -3.497576
1.889034 5.190400
-0.798747 2.185588
2.836520 -2.658556
-3.837877 -3.253815
2.096701 3.886007
-2.709034 2.923887
3.367037 -3.184789
-2.121479 -4.232586
2.329546 3.179764
-3.284816 3.273099
3.091414 -3.815232
-3.762093 -2.432191
3.542056 2.778832
-1.736822 4.241041
2.127073 -2.983680
-4.323818 -3.938116
3.792121 5.135768
-4.786473 3.358547
2.624081 -3.260715
-4.009299 -2.978115
2.493525 1.963710
-2.513661 2.642162
1.864375 -3.176309
-3.171184 -3.572452
2.894220 2.489128
-2.562539 2.884438
3.491078 -3.947487
-2.565729 -2.012114
3.332948 3.983102
-1.616805 3.573188
2.280615 -2.559444
-2.651229 -3.103198
2.321395 3.154987
-1.685703 2.939697
3.031012 -3.620252
-4.599622 -2.185829
4.196223 1.126677
-2.133863 3.093686
4.668892 -2.562705
-2.793241 -2.149706
2.884105 3.043438
-2.967647 2.848696
4.479332 -1.764772
-4.905566 -2.911070