ICA分析-cities_10

使用cities_10.csv进行降维练习

import matplotlib.pyplot as plt
import os
import pandas as pd
%matplotlib inline

os.chdir('Q:/data')
pd.set_option('display.max_columns', None)

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.decomposition import PCA, FastICA

cities_ica = FastICA(n_components=2, whiten=True)
ica_trans = cities_ica.fit(cities.iloc[:, 1:])
cities_X_ica = ica_trans.transform(cities.iloc[:, 1:])
pd.DataFrame(cities_X_ica)

	0	1
0	0.117789	-0.114247
1	0.119293	0.357979
2	0.251025	-0.078474
3	-0.163078	-0.446406
4	0.023720	0.365038
5	-0.833090	-0.130078
6	-0.026661	0.104525
7	0.109146	-0.204617
8	-0.016233	0.542019
9	0.418088	-0.395740

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np

plt.scatter(cities_X_ica[:, 0], cities_X_ica[:, 1])

for x, y, s in np.vstack([cities_X_ica[:, 0], cities_X_ica[:, 1], np.arange(10)]).T:
    plt.text(x, y, s)
    
plt.show()

[外链图片转存(img-kGZbe9ui-1562726815212)(output_4_0.png)]