In [1]:

    

import numpy as np, pandas as pd, os


    

In [2]:

    

hh = pd.read_csv('c://users//janowicz//desktop//drcog_new_households.csv')
persons = pd.read_csv('c://users//janowicz//desktop//drcog_new_persons.csv')


    

In [4]:

    

hh = hh.set_index('household_id')
persons = persons.set_index('person_id')


    

In [9]:

    

hh.describe()


    

    
Out[9]:






  

    

      

      
age_of_head
      
cars
      
children
      
income
      
persons
      
tenure
      
workers
      
serialno
      
taz
      
building_id
    
  
  

    

      
count
      
 1160869.000000
      
 1160869.000000
      
 1160869.000000
      
 1160869.000000
      
 1160869.000000
      
 1160869.000000
      
 1160869.000000
      
 1.160869e+06
      
 1160869.00000
      
 1160869.000000
    
    

      
mean
      
      46.663054
      
       1.809641
      
       0.758610
      
   82869.044468
      
       2.450459
      
       1.334716
      
       1.329384
      
 2.009001e+12
      
  377636.07443
      
  473059.299294
    
    

      
std
      
      15.610260
      
       1.071603
      
       0.837915
      
   81489.992173
      
       1.460441
      
       0.471891
      
       1.007229
      
 1.426441e+09
      
  170954.09554
      
  294924.760137
    
    

      
min
      
      15.000000
      
       0.000000
      
       0.000000
      
  -17254.156200
      
       1.000000
      
       1.000000
      
       0.000000
      
 2.007000e+12
      
  101020.00000
      
       1.000000
    
    

      
25%
      
      35.000000
      
       1.000000
      
       0.000000
      
   31720.496880
      
       1.000000
      
       1.000000
      
       1.000000
      
 2.008000e+12
      
  211180.00000
      
  191967.000000
    
    

      
50%
      
      46.000000
      
       2.000000
      
       1.000000
      
   61603.338500
      
       2.000000
      
       1.000000
      
       1.000000
      
 2.009001e+12
      
  405010.00000
      
  466724.000000
    
    

      
75%
      
      56.000000
      
       2.000000
      
       1.000000
      
  107322.179800
      
       3.000000
      
       2.000000
      
       2.000000
      
 2.010001e+12
      
  506240.00000
      
  711175.000000
    
    

      
max
      
      93.000000
      
       6.000000
      
      11.000000
      
 1124531.898000
      
      15.000000
      
       2.000000
      
       8.000000
      
 2.011002e+12
      
  803120.00000
      
 1015771.000000
    
  

In [8]:

    

store = pd.HDFStore('c:\\urbansim\\data\\drcog.h5')


    

In [10]:

    

store['households_previous'] = store['households']


    

In [11]:

    

store['households'] = hh
store['persons'] = persons


    

In [12]:

    

store.close()