In [25]:

    

%matplotlib inline
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans


    

In [10]:

    

X, y = make_blobs(n_samples=1000, centers=3, n_features=2)
df = pd.DataFrame(X)
df = df.rename(columns={0: 'x1', 1: 'x2'})
df['y'] = y
df.head()


    

    
Out[10]:






  

    

      

      
x1
      
x2
      
y
    
  
  

    

      
0
      
3.515992
      
5.718453
      
2
    
    

      
1
      
0.979406
      
6.933223
      
2
    
    

      
2
      
8.014965
      
-6.052760
      
1
    
    

      
3
      
0.714026
      
5.140077
      
2
    
    

      
4
      
6.871349
      
0.790905
      
0
    
  

In [31]:

    

k_means = KMeans(init='k-means++', n_clusters=3, n_init=10)
k_means.fit(df[['x1', 'x2']])
df['y_pred'] = k_means.labels_
k_means.cluster_centers_


    

    
Out[31]:





array([[ 6.14040257, -0.49850067],
       [ 2.01084733,  5.8233732 ],
       [ 9.04113487, -4.90957409]])

In [32]:

    

sns.pairplot(df, hue='y_pred', vars=('x1', 'x2'), diag_kind="kde", plot_kws=dict(alpha=0.1, edgecolor=None))


    

    
Out[32]:





<seaborn.axisgrid.PairGrid at 0x12640b6d8>