样本聚类

样本聚类

%matplotlib inline

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pylab import mpl

mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
mpl.rcParams['font.size'] = 15 # 设置默认字体大小
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题

使用“cities_10.csv”数据集进行层次聚类

• 原始数据的可视化

cities = pd.read_csv('cities_10.csv', encoding='gbk')
cities

	AREA	X1	X2	X3	X4	X5	X6	X7	X8	X9
0	辽宁	5458.2	13000	1376.2	2258.4	1315.9	529.0	2258.4	123.7	399.7
1	山东	10550.0	11643	3502.5	3851.0	2288.7	1070.7	3181.9	211.1	610.2
2	河北	6076.6	9047	1406.7	2092.6	1161.6	597.1	1968.3	45.9	302.3
3	天津	2022.6	22068	822.8	960.0	703.7	361.9	941.4	115.7	171.8
4	江苏	10636.3	14397	3536.3	3967.2	2320.0	1141.3	3215.8	384.7	643.7
5	上海	5408.8	40627	2196.2	2755.8	1970.2	779.3	2035.2	320.5	709.0
6	浙江	7670.0	16570	2356.5	3065.0	2296.6	1180.6	2877.5	294.2	566.9
7	福建	4682.0	13510	1047.1	1859.0	964.5	397.9	1663.3	173.7	272.9
8	广东	11769.7	15030	4224.6	4793.6	3022.9	1275.5	5013.6	1843.7	1201.6
9	广西	2455.4	5062	367.0	995.7	542.2	352.7	1025.5	15.1	186.7

from sklearn.preprocessing import scale
from sklearn.decomposition import PCA, FactorAnalysis

scale_cities = scale(cities.iloc[:, 1:])
pca_scale_cities = PCA(n_components=2, whiten=True).fit_transform(scale_cities)
fa_scale_cities  = FactorAnalysis(n_components=2).fit_transform(scale_cities)

from sklearn.cluster import AgglomerativeClustering

ward = AgglomerativeClustering(n_clusters=3, linkage='ward', compute_full_tree=True)
ward.fit(pca_scale_cities)

AgglomerativeClustering(affinity='euclidean', compute_full_tree=True,
            connectivity=None, linkage='ward', memory=None, n_clusters=3,
            pooling_func=<function mean at 0x0000000004DDF2F0>)

cities['total'] = pca_scale_cities[:, 0]
cities['average'] = pca_scale_cities[:, 1]
cities['cluster'] = ward.labels_

fig, ax = plt.subplots(figsize=[5, 3])

for cluster, marker in zip(range(ward.n_clusters), ['x', 'o', 'd']):
    x_axis = cities['total'][cities['cluster'] == cluster]
    y_axis = cities['average'][cities['cluster'] == cluster]
    ax.scatter(x_axis, y_axis, marker=marker, color='b')

for x,y,s in np.vstack([cities['total'], cities['average'], cities['AREA']]).T