Python实现聚类K-means算法详解

# 下面的内容保存在 melons.txt 中
# 第一列为西瓜的密度；第二列为西瓜的含糖率。我们要把这30个西瓜分为3类
0.697 0.460
0.774 0.376
0.634 0.264
0.608 0.318
0.556 0.215
0.403 0.237
0.481 0.149
0.437 0.211
0.666 0.091
0.243 0.267
0.245 0.057
0.343 0.099
0.639 0.161
0.657 0.198
0.360 0.370
0.593 0.042
0.719 0.103
0.359 0.188
0.339 0.241
0.282 0.257
0.748 0.232
0.714 0.346
0.483 0.312
0.478 0.437
0.525 0.369
0.751 0.489
0.532 0.472
0.473 0.376
0.725 0.445
0.446 0.459

import random
import numpy as np
import matplotlib.pyplot as plt

k = 3 # 要分的簇数
rnd = 0 # 轮次，用于控制迭代次数（见上文）
ROUND_LIMIT = 100 # 轮次的上限
THRESHOLD = 1e-10 # 单轮改变距离的阈值，若改变幅度小于该阈值，算法终止
melons = [] # 西瓜的列表
clusters = [] # 簇的列表，clusters[i]表示第i簇包含的西瓜

f = open('melons.txt', 'r')
for line in f:
	# 把字符串转化为numpy中的float64类型
    melons.append(np.array(line.split(' '), dtype = np.string_).astype(np.float64))

# random的sample函数从列表中随机挑选出k个样本（不重复）。我们在这里把这些样本作为均值向量
mean_vectors = random.sample(melons, k)

# 这个while对应上面算法的2-17行
while True:
    rnd += 1 # 轮次增加
    change = 0 # 把改变幅度重置为0

	# 清空对簇的划分，对应上面算法的第3行
    clusters = []
    for i in range(k):
        clusters.append([])
    # 这个for对应上面算法的4-8行
    for melon in melons:
    	'''
    	argmin 函数找出容器中最小的下标，在这里这个目标容器是
    	list(map(lambda vec: np.linalg.norm(melon - vec, ord = 2), mean_vectors)),
    	它表示melon与mean_vectors中所有向量的距离列表。
    	(numpy.linalg.norm计算向量的范数,ord = 2即欧几里得范数，或模长)
    	'''
        c = np.argmin(
            list(map( lambda vec: np.linalg.norm(melon - vec, ord = 2), mean_vectors))
        )
        clusters[c].append(melon)
	# 这个for对应上面算法的9-16行
    for i in range(k):
    	# 求每个簇的新均值向量
        new_vector = np.zeros((1,2))
        for melon in clusters[i]:
            new_vector += melon
        new_vector /= len(clusters[i])

        # 累加改变幅度并更新均值向量
        change += np.linalg.norm(mean_vectors[i] - new_vector, ord = 2)
        mean_vectors[i] = new_vector
	# 若超过设定的轮次或者变化幅度<预先设定的阈值，结束算法
    if rnd > ROUND_LIMIT or change < THRESHOLD:
        break
print('最终迭代%d轮'%rnd)

colors = ['red', 'green', 'blue']

# 每个簇换一下颜色，同时迭代簇和颜色两个列表
for i, col in zip(range(k), colors):
    for melon in clusters[i]:
    	# 绘制散点图
        plt.scatter(melon[0], melon[1], color = col)
plt.show()

import random
import numpy as np
import matplotlib.pyplot as plt

k = 3
rnd = 0
ROUND_LIMIT = 10
THRESHOLD = 1e-10
melons = []
clusters = []
f = open('melons.txt', 'r')
for line in f:
    melons.append(np.array(line.split(' '), dtype = np.string_).astype(np.float64))
mean_vectors = random.sample(melons, k)

while True:
    rnd += 1
    change = 0
    clusters = []
    for i in range(k):
        clusters.append([])
    for melon in melons:
        c = np.argmin(
            list(map( lambda vec: np.linalg.norm(melon - vec, ord = 2), mean_vectors))
        )
        clusters[c].append(melon)
    for i in range(k):
        new_vector = np.zeros((1,2))
        for melon in clusters[i]:
            new_vector += melon
        new_vector /= len(clusters[i])

        change += np.linalg.norm(mean_vectors[i] - new_vector, ord = 2)
        mean_vectors[i] = new_vector

    if rnd > ROUND_LIMIT or change < THRESHOLD:
        break
print('最终迭代%d轮'%rnd)
colors = ['red', 'green', 'blue']
for i, col in zip(range(k), colors):
    for melon in clusters[i]:
        plt.scatter(melon[0], melon[1], color = col)
plt.show()

>>> from sklearn.cluster import KMeans
>>> import numpy as np
>>> X = np.array([[1, 2], [1, 4], [1, 0],
...               [10, 2], [10, 4], [10, 0]])
>>> kmeans = KMeans(n_clusters=2, random_state=0).fit(X)
>>> kmeans.labels_
array([1, 1, 1, 0, 0, 0], dtype=int32)
>>> kmeans.predict([[0, 0], [12, 3]])
array([1, 0], dtype=int32)
>>> kmeans.cluster_centers_
array([[10.,  2.],
       [ 1.,  2.]])

import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

X = []
f = open('melons.txt', 'r')
for line in f:
    X.append(np.array(line.split(' '), dtype = np.string_).astype(np.float64))
kmeans = KMeans(n_clusters = 3, random_state = 0).fit(X)
colors = ['red', 'green', 'blue']
for i, cluster in enumerate(kmeans.labels_):
    plt.scatter(X[i][0], X[i][1], color = colors[cluster])
plt.show()