7-2基于Kmeans和DBSCAN算法的啤酒成分分析实战

beer数据集 聚类分析

import pandas as pd

beer = pd.read_csv('./data/data.txt', sep=' ')
print(beer)

                    name  calories  sodium  alcohol  cost
0              Budweiser       144      15      4.7  0.43
1                Schlitz       151      19      4.9  0.43
2              Lowenbrau       157      15      0.9  0.48
3            Kronenbourg       170       7      5.2  0.73
4               Heineken       152      11      5.0  0.77
5          Old_Milwaukee       145      23      4.6  0.28
6             Augsberger       175      24      5.5  0.40
7   Srohs_Bohemian_Style       149      27      4.7  0.42
8            Miller_Lite        99      10      4.3  0.43
9        Budweiser_Light       113       8      3.7  0.40
10                 Coors       140      18      4.6  0.44
11           Coors_Light       102      15      4.1  0.46
12        Michelob_Light       135      11      4.2  0.50
13                 Becks       150      19      4.7  0.76
14                 Kirin       149       6      5.0  0.79
15     Pabst_Extra_Light        68      15      2.3  0.38
16                 Hamms       139      19      4.4  0.43
17   Heilemans_Old_Style       144      24      4.9  0.43
18   Olympia_Goled_Light        72       6      2.9  0.46
19         Schlitz_Light        97       7      4.2  0.47

X = beer[['calories', 'sodium', 'alcohol', 'cost']]

K-means聚类算法

from sklearn.cluster import KMeans

km = KMeans(n_clusters=3).fit(X)
km2 = KMeans(n_clusters=2).fit(X)

km.labels_

array([0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 0, 2, 0, 0, 0, 1, 0, 0, 1, 2])

beer['cluster'] = km.labels_
beer['cluster2'] = km2.labels_
beer.sort_values('cluster')

	name	calories	sodium	alcohol	cost	cluster	cluster2
0	Budweiser	144	15	4.7	0.43	0	0
1	Schlitz	151	19	4.9	0.43	0	0
2	Lowenbrau	157	15	0.9	0.48	0	0
3	Kronenbourg	170	7	5.2	0.73	0	0
4	Heineken	152	11	5.0	0.77	0	0
5	Old_Milwaukee	145	23	4.6	0.28	0	0
6	Augsberger	175	24	5.5	0.40	0	0
7	Srohs_Bohemian_Style	149	27	4.7	0.42	0	0
17	Heilemans_Old_Style	144	24	4.9	0.43	0	0
10	Coors	140	18	4.6	0.44	0	0
16	Hamms	139	19	4.4	0.43	0	0
12	Michelob_Light	135	11	4.2	0.50	0	0
13	Becks	150	19	4.7	0.76	0	0
14	Kirin	149	6	5.0	0.79	0	0
18	Olympia_Goled_Light	72	6	2.9	0.46	1	1
15	Pabst_Extra_Light	68	15	2.3	0.38	1	1
9	Budweiser_Light	113	8	3.7	0.40	2	1
8	Miller_Lite	99	10	4.3	0.43	2	1
11	Coors_Light	102	15	4.1	0.46	2	1
19	Schlitz_Light	97	7	4.2	0.47	2	1

from pandas.tools.plotting import scatter_matrix
%matplotlib inline

cluster_centers = km.cluster_centers_
cluster2_centers = km2.cluster_centers_

beer.groupby('cluster').mean()