notebook.community

Edit and run



In [1]:

    
from synthpop.recipes.starter import Starter
from synthpop.synthesizer import synthesize_all, enable_logging 
import os
import pandas as pd



In [2]:

    
starter = Starter(os.environ["CENSUS"], "CA", "Santa Clara County")



In [ ]:

    
ind = pd.Series(["06", "085", "508203", "3"], index=["state", "county", "tract", "block group"])



In [12]:

    
%time households, persons, fit = synthesize_all(starter, indexes=[ind])









    



Synthesizing at geog level: 'block_group' (number of geographies is 1075)
Synthesizing geog id:
state              06
county            085
tract          508203
block group         3
dtype: object
Drawing 884 households
CPU times: user 1.79 s, sys: 28.5 ms, total: 1.82 s
Wall time: 1.83 s



In [7]:

    
households.head(3)









    Out[7]:






  
    
      
      serialno
      RT
      DIVISION
      PUMA00
      PUMA10
      REGION
      ST
      ADJHSG
      ADJINC
      WGTP
      ...
      WGTP76
      WGTP77
      WGTP78
      WGTP79
      WGTP80
      cars
      workers
      children
      income
      cat_id
    
  
  
    
      0
       2012000030460
       H
       9
      -9
       08502
       4
       06
       1000000
       1010207
       18
      ...
        5
       27
       21
       16
        6
       two or more
       one
       yes
            gt100
       45
    
    
      1
       2012000776236
       H
       9
      -9
       08502
       4
       06
       1000000
       1010207
       17
      ...
       33
       15
       34
       30
       16
               one
       one
       yes
       gt35-lt100
       28
    
    
      2
       2012001433300
       H
       9
      -9
       08502
       4
       06
       1000000
       1010207
       22
      ...
        6
       21
       24
       10
       35
               one
       one
       yes
            gt100
       27
    
  

3 rows × 208 columns



In [8]:

    
persons.head(3)









    Out[8]:






  
    
      
      serialno
      RT
      SPORDER
      PUMA00
      PUMA10
      ST
      ADJINC
      PWGTP
      AGEP
      CIT
      ...
      PWGTP76
      PWGTP77
      PWGTP78
      PWGTP79
      PWGTP80
      age
      race
      sex
      cat_id
      hh_id
    
  
  
    
      0
       2012000030460
       P
       1
      -9
       08502
       06
       1010207
       18
       46
       4
      ...
       5
       28
       21
       16
       6
       35 to 60
       asian
       female
       16
        0
    
    
      1
       2012000030460
       P
       1
      -9
       08502
       06
       1010207
       18
       46
       4
      ...
       5
       28
       21
       16
       6
       35 to 60
       asian
       female
       16
        6
    
    
      2
       2012000030460
       P
       1
      -9
       08502
       06
       1010207
       18
       46
       4
      ...
       5
       28
       21
       16
       6
       35 to 60
       asian
       female
       16
       20
    
  

3 rows × 295 columns



In [9]:

    
fit









    Out[9]:





{BlockGroupID(state='06', county='085', tract='508203', block_group='3'): FitQuality(household_chisq=1033957.2104660122, household_p=0.0, people_chisq=86.359051234185131, people_p=4.0257811248627773e-07)}



In [13]:

    
starter = Starter(os.environ["CENSUS"], "MD", "Montgomery County")



In [15]:

    
ind = pd.Series(["24", "031", "700101", "1"], index=["state", "county", "tract", "block group"])



In [17]:

    
%time households, persons, fit = synthesize_all(starter, indexes=[ind])









    



Synthesizing at geog level: 'block_group' (number of geographies is 614)
Synthesizing geog id:
state              24
county            031
tract          700101
block group         1
dtype: object
Drawing 548 households
CPU times: user 873 ms, sys: 39.7 ms, total: 913 ms
Wall time: 929 ms



In [ ]:

	serialno	RT	DIVISION	PUMA00	PUMA10	REGION	ST	ADJHSG	ADJINC	WGTP	...	WGTP76	WGTP77	WGTP78	WGTP79	WGTP80	cars	workers	children	income	cat_id
0	2012000030460	H	9	-9	08502	4	06	1000000	1010207	18	...	5	27	21	16	6	two or more	one	yes	gt100	45
1	2012000776236	H	9	-9	08502	4	06	1000000	1010207	17	...	33	15	34	30	16	one	one	yes	gt35-lt100	28
2	2012001433300	H	9	-9	08502	4	06	1000000	1010207	22	...	6	21	24	10	35	one	one	yes	gt100	27