[python] 层次聚类 Agglomerative Clustering

层次聚类

下图中动物 就是一种层次分类

主要函数

cls = AgglomerativeClustering(n_clusters=group_size,linkage='ward')

linkage 参数说明:

1. ward (默认值)：每一个类簇的方差最小化
2. average：每一个类簇之间的距离的平均值最小
3. complete：每一个类簇之间的距离最大
4. single：每一个类簇之间的距离最小

linkage : {"ward", "complete", "average", "single"}, optional \
        (default="ward")
    Which linkage criterion to use. The linkage criterion determines which
    distance to use between sets of observation. The algorithm will merge
    the pairs of cluster that minimize this criterion.

    - ward minimizes the variance of the clusters being merged.
    - average uses the average of the distances of each observation of
      the two sets.
    - complete or maximum linkage uses the maximum distances between
      all observations of the two sets.
    - single uses the minimum of the distances between all observations
      of the two sets.

简单案例

import numpy as np
from sklearn.cluster import AgglomerativeClustering
import random
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import dendrogram, linkage

point_random = []
for i in range(10):
    rx = random.uniform(0, 10)
    ry = random.uniform(0, 10)
    point_random.append([rx, ry])

#  簇族 分组量
group_size = 3

cls = AgglomerativeClustering(n_clusters=group_size,linkage='ward')

cluster_group = cls.fit(np.array(point_random))

cnames = ['black', 'blue', 'red']


for point, gp_id in zip(point_random, cluster_group.labels_):
    # 放到 plt 中展示
    plt.scatter(point[0], point[1], s=5, c=cnames[gp_id], alpha=1)

plt.show()

进一步可视化

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

from scipy.cluster.hierarchy import dendrogram, linkage

data = np.random.randint(0,10,size=[10,2])

Z = linkage(data)

dendrogram(Z)  

• 至此我们做了一个随机数据的层次聚类 ，接下来进行一组年收入-年支出的数据分类

收入和支出的分类

• 部分数据表格

id	sex	age	annual_income	annual_expenditure
1	Male	19	15	13
2	Male	21	15	81
3	Female	20	16	13

#%%

import matplotlib.pyplot as plt  
import pandas as pd  
import numpy as np
import scipy.cluster.hierarchy as shc
customer_data = pd.read_csv(r'.\shopping_data.csv')  


# 获取收入和支出
data = customer_data.iloc[:, 3:5].values  


plt.figure(figsize=(10, 7))  
plt.title("Customer Dendograms")  
dend = shc.dendrogram(shc.linkage(data, method='ward'))  
plt.savefig("./收支-01.jpg")
plt.show()
#%%

from sklearn.cluster import AgglomerativeClustering

cluster = AgglomerativeClustering(n_clusters=5, affinity='euclidean', linkage='ward')  
cluster.fit_predict(data) 



plt.figure(figsize=(10, 7))  
plt.scatter(data[:,0], data[:,1], c=cluster.labels_, cmap='rainbow')  
plt.savefig("./收支-02.jpg")
plt.show()

• 年支出-年收入散点图
  
• 年支出-年收入层次聚类