sklearn skmeans 小麦聚类

github地址： github.com/yangjinghit…

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
复制代码

data1 = pd.DataFrame({'X':np.random.randint(1,50,100), 'Y':np.random.randint(1,50, 100)})
复制代码

data = pd.concat([data1 + 50, data1])
复制代码

plt.style.use('ggplot')
复制代码

plt.scatter(data['X'], data['Y'])
复制代码

<matplotlib.collections.PathCollection at 0x11084cf60>
复制代码

from sklearn.cluster import KMeans

复制代码

y_pred = KMeans(n_clusters=2).fit_predict(data)
复制代码

y_pred
复制代码

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1], dtype=int32)
复制代码

plt.scatter(data.X, data.Y, c=y_pred)
复制代码

<matplotlib.collections.PathCollection at 0x1a15f51b70>
复制代码

from sklearn import metrics
复制代码

metrics.calinski_harabaz_score(data, y_pred)
复制代码

651.578135407151
复制代码

y_pred_three = KMeans(n_clusters=3).fit_predict(data)
metrics.calinski_harabaz_score(data, y_pred_three)
复制代码

440.2030577799353
复制代码

y_pred_four = KMeans(n_clusters=4).fit_predict(data)
metrics.calinski_harabaz_score(data, y_pred_four)
复制代码

422.21475785975883
复制代码

data = pd.read_csv('seeds_dataset.txt', header=None, delim_whitespace=True, names=['x1','x2','x3','x4','x5','x6','x7','y'])
复制代码

data
复制代码

	x1	x2	x3	x4	x5	x6	x7	y
0	15.26	14.84	0.8710	5.763	3.312	2.2210	5.220	1
1	14.88	14.57	0.8811	5.554	3.333	1.0180	4.956	1
2	14.29	14.09	0.9050	5.291	3.337	2.6990	4.825	1
3	13.84	13.94	0.8955	5.324	3.379	2.2590	4.805	1
4	16.14	14.99	0.9034	5.658	3.562	1.3550	5.175	1
5	14.38	14.21	0.8951	5.386	3.312	2.4620	4.956	1
6	14.69	14.49	0.8799	5.563	3.259	3.5860	5.219	1
7	14.11	14.10	0.8911	5.420	3.302	2.7000	5.000	1
8	16.63	15.46	0.8747	6.053	3.465	2.0400	5.877	1
9	16.44	15.25	0.8880	5.884	3.505	1.9690	5.533	1
10	15.26	14.85	0.8696	5.714	3.242	4.5430	5.314	1
11	14.03	14.16	0.8796	5.438	3.201	1.7170	5.001	1
12	13.89	14.02	0.8880	5.439	3.199	3.9860	4.738	1
13	13.78	14.06	0.8759	5.479	3.156	3.1360	4.872	1
14	13.74	14.05	0.8744	5.482	3.114	2.9320	4.825	1
15	14.59	14.28	0.8993	5.351	3.333	4.1850	4.781	1
16	13.99	13.83	0.9183	5.119	3.383	5.2340	4.781	1
17	15.69	14.75	0.9058	5.527	3.514	1.5990	5.046	1
18	14.70	14.21	0.9153	5.205	3.466	1.7670	4.649	1
19	12.72	13.57	0.8686	5.226	3.049	4.1020	4.914	1
20	14.16	14.40	0.8584	5.658	3.129	3.0720	5.176	1
21	14.11	14.26	0.8722	5.520	3.168	2.6880	5.219	1
22	15.88	14.90	0.8988	5.618	3.507	0.7651	5.091	1
23	12.08	13.23	0.8664	5.099	2.936	1.4150	4.961	1
24	15.01	14.76	0.8657	5.789	3.245	1.7910	5.001	1
25	16.19	15.16	0.8849	5.833	3.421	0.9030	5.307	1
26	13.02	13.76	0.8641	5.395	3.026	3.3730	4.825	1
27	12.74	13.67	0.8564	5.395	2.956	2.5040	4.869	1
28	14.11	14.18	0.8820	5.541	3.221	2.7540	5.038	1
29	13.45	14.02	0.8604	5.516	3.065	3.5310	5.097	1
...	...	...	...	...	...	...	...	...
180	11.41	12.95	0.8560	5.090	2.775	4.9570	4.825	3
181	12.46	13.41	0.8706	5.236	3.017	4.9870	5.147	3
182	12.19	13.36	0.8579	5.240	2.909	4.8570	5.158	3
183	11.65	13.07	0.8575	5.108	2.850	5.2090	5.135	3
184	12.89	13.77	0.8541	5.495	3.026	6.1850	5.316	3
185	11.56	13.31	0.8198	5.363	2.683	4.0620	5.182	3
186	11.81	13.45	0.8198	5.413	2.716	4.8980	5.352	3
187	10.91	12.80	0.8372	5.088	2.675	4.1790	4.956	3
188	11.23	12.82	0.8594	5.089	2.821	7.5240	4.957	3
189	10.59	12.41	0.8648	4.899	2.787	4.9750	4.794	3
190	10.93	12.80	0.8390	5.046	2.717	5.3980	5.045	3
191	11.27	12.86	0.8563	5.091	2.804	3.9850	5.001	3
192	11.87	13.02	0.8795	5.132	2.953	3.5970	5.132	3
193	10.82	12.83	0.8256	5.180	2.630	4.8530	5.089	3
194	12.11	13.27	0.8639	5.236	2.975	4.1320	5.012	3
195	12.80	13.47	0.8860	5.160	3.126	4.8730	4.914	3
196	12.79	13.53	0.8786	5.224	3.054	5.4830	4.958	3
197	13.37	13.78	0.8849	5.320	3.128	4.6700	5.091	3
198	12.62	13.67	0.8481	5.410	2.911	3.3060	5.231	3
199	12.76	13.38	0.8964	5.073	3.155	2.8280	4.830	3
200	12.38	13.44	0.8609	5.219	2.989	5.4720	5.045	3
201	12.67	13.32	0.8977	4.984	3.135	2.3000	4.745	3
202	11.18	12.72	0.8680	5.009	2.810	4.0510	4.828	3
203	12.70	13.41	0.8874	5.183	3.091	8.4560	5.000	3
204	12.37	13.47	0.8567	5.204	2.960	3.9190	5.001	3
205	12.19	13.20	0.8783	5.137	2.981	3.6310	4.870	3
206	11.23	12.88	0.8511	5.140	2.795	4.3250	5.003	3
207	13.20	13.66	0.8883	5.236	3.232	8.3150	5.056	3
208	11.84	13.21	0.8521	5.175	2.836	3.5980	5.044	3
209	12.30	13.34	0.8684	5.243	2.974	5.6370	5.063	3

210 rows × 8 columns

data.columns
复制代码

Index(['x1', 'x2', 'x3', 'x4', 'x5', 'x6', 'x7', 'y'], dtype='object')
复制代码

y_pred = KMeans(n_clusters=3).fit_predict(data[['x1', 'x2', 'x3', 'x4', 'x5', 'x6', 'x7']])
复制代码

y_pred
复制代码

array([2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 0, 2, 2,
       2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 0, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 0, 0, 2, 2,
       2, 2, 2, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1,
       2, 2, 2, 2, 1, 2, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0], dtype=int32)
复制代码

y_pre = pd.Series(y_pred)
y_pre
复制代码

0      2
1      2
2      2
3      2
4      2
5      2
6      2
7      2
8      2
9      2
10     2
11     2
12     2
13     2
14     2
15     2
16     0
17     2
18     2
19     0
20     2
21     2
22     2
23     2
24     2
25     2
26     0
27     2
28     2
29     2
      ..
180    0
181    0
182    0
183    0
184    0
185    0
186    0
187    0
188    0
189    0
190    0
191    0
192    0
193    0
194    0
195    0
196    0
197    0
198    0
199    0
200    0
201    2
202    0
203    0
204    0
205    0
206    0
207    0
208    0
209    0
Length: 210, dtype: int32
复制代码

y_pre.unique()
复制代码

array([2, 0, 1])
复制代码

y_pre = y_pre.map({2:1, 1:2, 0:3})
y_pre
复制代码

0      1
1      1
2      1
3      1
4      1
5      1
6      1
7      1
8      1
9      1
10     1
11     1
12     1
13     1
14     1
15     1
16     3
17     1
18     1
19     3
20     1
21     1
22     1
23     1
24     1
25     1
26     3
27     1
28     1
29     1
      ..
180    3
181    3
182    3
183    3
184    3
185    3
186    3
187    3
188    3
189    3
190    3
191    3
192    3
193    3
194    3
195    3
196    3
197    3
198    3
199    3
200    3
201    1
202    3
203    3
204    3
205    3
206    3
207    3
208    3
209    3
Length: 210, dtype: int64
复制代码

data_p = pd.DataFrame({'y_pre':y_pre, 'y':data.y})
复制代码

data_p['acc'] = data_p.y_pre == data_p.y
复制代码

data_p
复制代码

	y	y_pre	acc
0	1	1	True
1	1	1	True
2	1	1	True
3	1	1	True
4	1	1	True
5	1	1	True
6	1	1	True
7	1	1	True
8	1	1	True
9	1	1	True
10	1	1	True
11	1	1	True
12	1	1	True
13	1	1	True
14	1	1	True
15	1	1	True
16	1	3	False
17	1	1	True
18	1	1	True
19	1	3	False
20	1	1	True
21	1	1	True
22	1	1	True
23	1	1	True
24	1	1	True
25	1	1	True
26	1	3	False
27	1	1	True
28	1	1	True
29	1	1	True
...	...	...	...
180	3	3	True
181	3	3	True
182	3	3	True
183	3	3	True
184	3	3	True
185	3	3	True
186	3	3	True
187	3	3	True
188	3	3	True
189	3	3	True
190	3	3	True
191	3	3	True
192	3	3	True
193	3	3	True
194	3	3	True
195	3	3	True
196	3	3	True
197	3	3	True
198	3	3	True
199	3	3	True
200	3	3	True
201	3	1	False
202	3	3	True
203	3	3	True
204	3	3	True
205	3	3	True
206	3	3	True
207	3	3	True
208	3	3	True
209	3	3	True

210 rows × 3 columns

data_p.acc.sum()/len(data_p)
复制代码

0.8952380952380953
复制代码