In [5]:

    

import pandas as pd

data_311 = pd.read_csv('df_311_ready_to_join.csv', na_values=['-'])
data_311 = data_311.where((pd.notnull(data_311)), None)
data_311['311-reports'] = data_311['reports']
data_311= data_311.drop('reports', 1)
data_311.head()


    

    
Out[5]:






  

    

      

      
tuple
      
311-reports
    
  
  

    

      
0
      
 (35649504.880880885, 37.79586636966667, -122.5...
      
 [{'Category': 'General Requests', 'TimeBin': 3...
    
    

      
1
      
 (127406469.14814816, 37.710130254333336, -122....
      
 [{'Category': 'SFHA Requests', 'TimeBin': 1274...
    
    

      
2
      
 (87098222.15215217, 37.68155154922223, -122.51...
      
 [{'Category': 'Tree Maintenance', 'TimeBin': 8...
    
    

      
3
      
 (126798807.13313314, 37.76728766455556, -122.5...
      
 [{'Category': 'Street and Sidewalk Cleaning', ...
    
    

      
4
      
 (137331615.3933934, 37.68155154922223, -122.51...
      
 [{'Category': 'Abandoned Vehicle', 'TimeBin': ...
    
  

In [2]:

    

data_911 = pd.read_csv('data_911_ready_to_join.csv', na_values=['-'])
data_911 = data_911.where((pd.notnull(data_911)), None)
data_911.head()


    

    
Out[2]:






  

    

      

      
911-reports
      
tuple
    
  
  

    

      
0
      
 [{'Category': 'LARCENY/THEFT', 'TimeBin': 4008...
      
 (40088030.270270266, -122.49704362578936, 37.7...
    
    

      
1
      
 [{'Category': 'OTHER OFFENSES', 'TimeBin': 397...
      
 (39716844.804804794, -122.4805689517237, 37.74...
    
    

      
2
      
 [{'Category': 'LARCENY/THEFT', 'TimeBin': 7071...
      
 (70710831.17117117, -122.44761960359234, 37.79...
    
    

      
3
      
 [{'Category': 'FORGERY/COUNTERFEITING', 'TimeB...
      
 (118593756.2162162, -122.4311449295267, 37.769...
    
    

      
4
      
 [{'Category': 'SUSPICIOUS OCC', 'TimeBin': 434...
      
 (43428699.459459454, -122.4805689517237, 37.75...
    
  

In [11]:

    

joined_df = data_311.merge(data_911, how='left', on='tuple')
#joined_df.to_csv("joined_data.csv", index_label=False)

joined_df['911-reports'].count()


    

    
Out[11]:





0

In [ ]: