In [69]:

    

%load_ext autoreload
%autoreload 2
%matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np


    

    




The autoreload extension is already loaded. To reload it, use:
  %reload_ext autoreload

In [106]:

    

from utils import load_population_data
zipcode_pop = load_population_data("../resources/population_data.csv")


    

In [107]:

    

zipcode_pop.iloc[:10]


    

    
Out[107]:





11542    27633
11547      793
11545    12065
11548     2780
11549     2922
19390    13425
82443     4697
82442      732
82441      250
82440      145
dtype: int64

In [108]:

    

total_pop = zipcode_pop.sum(axis=0)
print total_pop


    

    




308722808

In [109]:

    

import numpy as np
pop_density = zipcode_pop / np.float64(total_pop)


    

In [110]:

    

pop_density.iloc[:10]


    

    
Out[110]:





11542    0.000090
11547    0.000003
11545    0.000039
11548    0.000009
11549    0.000009
19390    0.000043
82443    0.000015
82442    0.000002
82441    0.000001
82440    0.000000
dtype: float64

In [111]:

    

pop_density.index[:10]


    

    
Out[111]:





Index([u'11542', u'11547', u'11545', u'11548', u'11549', u'19390', u'82443', u'82442', u'82441', u'82440'], dtype='object')

In [135]:

    

from store import StoreGenerator


    

In [136]:

    

sg = StoreGenerator(zipcode_pop)


    

In [137]:

    

sg.create_stores(["01029", "03830", "05301", "10004"])


    

    
Out[137]:






  

    

      

      
id
      
pop_density
      
zipcode
    
  
  

    

      
01029
      
 0
      
 0.035368
      
 01029
    
    

      
03830
      
 1
      
 0.072171
      
 03830
    
    

      
05301
      
 2
      
 0.753990
      
 05301
    
    

      
10004
      
 3
      
 0.138471
      
 10004
    
  

4 rows × 3 columns

In [138]:

    

stores = sg.generate_n(10)


    

In [139]:

    

print stores


    

    




       id  pop_density zipcode
27958   0     0.060439   27958
30439   1     0.064806   30439
45424   2     0.297487   45424
77017   3     0.194001   77017
53185   4     0.110529   53185
46205   5     0.151073   46205
23517   6     0.026716   23517
40242   7     0.065122   40242
51462   8     0.006036   51462
95328   9     0.023791   95328

[10 rows x 3 columns]

In [140]:

    

from store import StoreSampler


    

In [141]:

    

ss = StoreSampler(stores)


    

In [142]:

    

ss.sample()


    

    
Out[142]:





id                     2
pop_density    0.2974875
zipcode            45424
Name: 45424, dtype: object

In [144]:

    

from customer import CustomerGenerator


    

In [155]:

    

cg = CustomerGenerator(stores)


    

In [156]:

    

customers = cg.generate_n(10)


    

In [157]:

    

customers


    

    
Out[157]:






  

    

      

      
id
      
name
      
pet_type
      
purchase_pdf
      
zipcode
    
  
  

    

      
0
      
 0
      
    Lisa Van Horn
      
 reptile
      
 0.187397
      
 45424
    
    

      
1
      
 1
      
         Lisa Doe
      
     cat
      
 0.134411
      
 46205
    
    

      
2
      
 2
      
      Susan Smith
      
  rabbit
      
 0.066788
      
 53185
    
    

      
3
      
 3
      
      Susan Smith
      
  rodent
      
 0.081256
      
 53185
    
    

      
4
      
 4
      
      Jay Houdini
      
  rodent
      
 0.010211
      
 45424
    
    

      
5
      
 5
      
 Marigold Houdini
      
  rodent
      
 0.094618
      
 45424
    
    

      
6
      
 6
      
      Chris Smith
      
  rabbit
      
 0.009195
      
 45424
    
    

      
7
      
 7
      
 Marigold Houdini
      
    fish
      
 0.107318
      
 45424
    
    

      
8
      
 8
      
      Lisa Danzig
      
 reptile
      
 0.001110
      
 45424
    
    

      
9
      
 9
      
      Lisa Danzig
      
     cat
      
 0.307695
      
 45424
    
  

10 rows × 5 columns

In [ ]: