In [33]:

    

import pandas as pd
import numpy as np
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))


    

In [34]:

    

df = pd.read_csv('../../data/processed/complaints-3-29-scrape.csv')


    

In [35]:

    

id_name = df[['facility_id','online_fac_name']][df['online_fac_name'].notnull()].drop_duplicates().rename(columns={'online_fac_name':'online_name'})


    

In [36]:

    

id_name.head()


    

    
Out[36]:






  

    

      

      
facility_id
      
online_name
    
  
  

    

      
1
      
385008
      
PRESBYTERIAN COMMUNITY CARE CENTER
    
    

      
24
      
385010
      
LAURELHURST VILLAGE REHABILITATION CENTER
    
    

      
30
      
385010
      
LAURELHURST VILLAGE
    
    

      
76
      
385015
      
REGENCY GRESHAM NURSING & REHABILITATION CENTER
    
    

      
82
      
385015
      
REST HARBOR REHABILITATION & EXTENDED CARE
    
  

In [37]:

    

names_per_id = id_name.groupby('facility_id').count().reset_index()


    

In [38]:

    

names_per_id.head()


    

    
Out[38]:






  

    

      

      
facility_id
      
online_name
    
  
  

    

      
0
      
385008
      
1
    
    

      
1
      
385010
      
2
    
    

      
2
      
385015
      
2
    
    

      
3
      
385018
      
1
    
    

      
4
      
385024
      
2
    
  

In [39]:

    

names_per_id[names_per_id['online_name']>1].count()[0]


    

    
Out[39]:





168