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

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

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

plt.style.use('ggplot')

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

<matplotlib.collections.PathCollection at 0x11084cf60>

from sklearn.cluster import KMeans

y_pred = KMeans(n_clusters=2).fit_predict(data)

y_pred

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)

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

<matplotlib.collections.PathCollection at 0x1a15f51b70>

from sklearn import metrics

metrics.calinski_harabaz_score(data, y_pred)

651.578135407151

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

440.2030577799353

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

422.21475785975883

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

data

data.columns

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

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

y_pred

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)

y_pre = pd.Series(y_pred)
y_pre

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

y_pre.unique()

array([2, 0, 1])

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

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

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

data_p['acc'] = data_p.y_pre == data_p.y

data_p

data_p.acc.sum()/len(data_p)

0.8952380952380953