In [3]:

    

import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

%matplotlib inline


    

In [4]:

    

df = pd.read_pickle('../data_processeing/Yelp_Cuisine_Chinese.pkl')


    

In [41]:

    

df_spatial = df[['latitude', 'longitude', 'cuisine_Chinese']]


    

In [ ]:

    

11
#5F4690, #1D6996, #38A6A5, #0F8554, #73AF48, #EDAD08, #E17C05, #CC503E, #94346E, #6F4070, #666666


    

In [46]:

    

kmeans = KMeans(n_clusters=11, random_state=5).fit(df[['latitude', 'longitude']])


    

In [ ]:

    

for


    

In [47]:

    

df_spatial['label'] = kmeans.labels_


    

    




/gpfs1/cusp/xz1845/.conda/envs/myPy27/lib/python2.7/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  if __name__ == '__main__':

In [48]:

    

df_spatial[df_spatial['label'] == 0].plot(x='longitude', y='latitude', kind='scatter')


    

    
Out[48]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f5f1ccd7e10>






    

In [35]:

    

range(11)


    

    
Out[35]:





[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

In [49]:

    

for i in range(11):
    temp = df_spatial[df_spatial['cuisine_Chinese'] == 2]
    print len(temp[temp['label'] == i])


    

    




80
84
482
853
63
182
194
410
163
139
43

In [45]:

    

for i in range(11):
    temp = df_spatial[df_spatial['cuisine_Chinese'] == 2]
    print len(temp[temp['label'] == i])


    

    




80
84
482
163
63
194
182
410
853
139
43

In [39]:

    

for i in range(11):
    df_spatial[df_spatial['label'] == i].plot(x='longitude', y='latitude', kind='scatter')


    

In [29]:

    

df_spatial.plot(x='longitude', y='latitude', kind='scatter', c='#5F4690')


    

    
Out[29]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f5f222809d0>






    

In [26]:

    

kmeans.labels_


    

    
Out[26]:





array([8, 2, 5, ..., 1, 2, 0], dtype=int32)

In [50]:

    




    

    
Out[50]:





array([3, 2, 6, ..., 1, 2, 0], dtype=int32)

In [52]:

    

df_ = df_spatial.copy()


    

In [ ]:

    




    

In [54]:

    

df_ = df_[['label']]


    

In [57]:

    

df_.columns = ['spatial_label']


    

In [58]:

    

df_.to_pickle('../spatial_labels.pkl')


    

    
Out[58]:






  

    

      

      
spatial_label
    
  
  

    

      
EDqCEAGXVGCH4FJXgqtjqg
      
3
    
    

      
GDnbt3isfhd57T1QqU6flg
      
2
    
    

      
a1Ba6XeIOP48e64YFD0dMw
      
6
    
    

      
826djy6K_9Fp0ptqJ2_Yag
      
3
    
    

      
Mi5uhdFB9OJteXPd0_IKfw
      
2
    
    

      
Uxh0fXFH_QQBivRnIBpdiw
      
8
    
    

      
YPavuOh2XsnRbLfl0DH2lQ
      
2
    
    

      
hovoWva_UjbnyLWEbnFvBw
      
8
    
    

      
L_thK7r3K_h5M4tV7amEKQ
      
3
    
    

      
hEcn9k6ONd5n2mq0lB2aew
      
2
    
    

      
diXqpz9WOr4WLQq6uvARkg
      
3
    
    

      
se2a2QaJi8Yx_KjE1r-_sQ
      
8
    
    

      
J3H6VSIgUTlACkb_HPFA8w
      
2
    
    

      
Ja4stXdNYr39u5CZHMNtjw
      
2
    
    

      
TegeuAoYBVgQRUBiDLU7Mw
      
8
    
    

      
7caQImCyJKGHwSlsDNZHhA
      
1
    
    

      
ZUvAR3I1uhC27zQFcRXumw
      
8
    
    

      
A2pZTpFXWC38z506XIhnBQ
      
7
    
    

      
mRv3Z25F56qduMKnvnCkVA
      
3
    
    

      
Ir_QIzs-4o9ElOtiGuxJrw
      
6
    
    

      
QfWFxmXqRGixztgaZN0gOA
      
0
    
    

      
h7uxML49NQ_Wj-7zk0DSqg
      
5
    
    

      
IikkB8j2E-1QmujRsPh5wQ
      
3
    
    

      
q_KQbgnaYDlPx8EHTydcBQ
      
3
    
    

      
2px99IppAcnxR238eq_8_w
      
2
    
    

      
jDqaz1jKdeWk_fTVCzc1Pg
      
9
    
    

      
dFArFtgDj1rIahUDHU8L7Q
      
2
    
    

      
mvsnt4q3A5TzcbPFolpsZQ
      
2
    
    

      
Eq3qA7F5uZBUbcYXROzntA
      
8
    
    

      
Ld2hhA3q3cdkptwS1fsYEg
      
2
    
    

      
...
      
...
    
    

      
9Z_6rRy7Tl_C6HIgm7y6FA
      
2
    
    

      
WuPSEvu8pES752S92awAVQ
      
8
    
    

      
uB2By0pTXV2JeM_CsMg7xw
      
2
    
    

      
uLUl_dMl6a9m774LGReDVA
      
2
    
    

      
P0ytQBoqSbMG9S7Hx-PAdw
      
8
    
    

      
ofXqwIbHprYF6TP47XudOw
      
5
    
    

      
ORloM7z9R9eh-G-an5DQLA
      
8
    
    

      
fh6tKiiZlrGk6fRaxd8buA
      
2
    
    

      
2OVuHRbdb5GTHUqrCqV-Fg
      
2
    
    

      
UNG2-2YFN93Z9lIoCuGteg
      
1
    
    

      
tquWyW3Mm5ka8LJtzodALg
      
1
    
    

      
A-apTF3JfkUPR_oeazZC1Q
      
2
    
    

      
22RFH-U5gboNJgws_GBG3w
      
5
    
    

      
9iJMGMsTK-q6W5MB1_Ny3Q
      
3
    
    

      
J6tgF98vwUz4D8T-N72org
      
3
    
    

      
UkoseRjoLT4K2bEzvmyhYA
      
3
    
    

      
w5CSi-An5meLnxjKSFn0wQ
      
7
    
    

      
RzXSaz2BjPBHeJzEIUKoQw
      
2
    
    

      
Q3UkgxNNInsPcUFhsQFcrg
      
3
    
    

      
GIfZNMP0oIJCje_Xp0Bgrw
      
8
    
    

      
bVgRVpdPgwHBLa7RHb9CpQ
      
6
    
    

      
2hUENHFcBIqop8-uWvrf6A
      
5
    
    

      
J1RDyyPxhioqm8c_fi4P4Q
      
8
    
    

      
_BJ2lBc1TWwIfxNzXbaaBA
      
3
    
    

      
C_chktl5jFeRqu1C0rmScA
      
3
    
    

      
xowy4YxBXXGOYuajsxjwkA
      
7
    
    

      
g9gAuOEXBbWnLlu2uOftwA
      
2
    
    

      
-McKyjNSqS1h9dDJH3dyUA
      
1
    
    

      
eHLUQ2W_hXx61NmiL9kSVg
      
2
    
    

      
OgwN65jZebPRIPSmNpRP7A
      
0
    
  

27314 rows × 1 columns

In [ ]: