notebook.community

Edit and run



In [1]:

    
import pandas as pd
import numpy as np
import os
import sys
import simpledbf
from getEPH import getEPHdbf



In [2]:

    
## select the trimester that you like to download ex. t311, t310
trimestre = 't311'
getEPHdbf(trimestre)









    



('Downloading', 't311')
file in place, creating CSV file
csv file cleanDataHousehold t311 .csv successfully created in folder data/
csv file cleanData t311 .csv successfully created in folder data/



In [3]:

    
ind = pd.read_csv('data/cleanData' + trimestre + '.csv')
ind.head()









    Out[3]:






  
    
      
      CODUSU
      NRO_HOGAR
      COMPONENTE
      AGLOMERADO
      PONDERA
      familyRelation
      female
      age
      schoolLevel
      finishedYear
      lastYear
      activity
      empCond
      unempCond
      ITF
      IPCF
      P47T
    
  
  
    
      0
      300641
      1
      1
      33
      1481
      1
      2
      51
      2
      2
      3.0
      3
      0
      4
      1200
      300.00
      1200
    
    
      1
      300641
      1
      2
      33
      1481
      10
      1
      12
      3
      2
      6.0
      3
      0
      3
      1200
      300.00
      0
    
    
      2
      300641
      1
      3
      33
      1481
      10
      2
      9
      3
      2
      3.0
      4
      0
      3
      1200
      300.00
      0
    
    
      3
      300641
      1
      4
      33
      1481
      10
      2
      14
      3
      2
      7.0
      3
      0
      3
      1200
      300.00
      0
    
    
      4
      300647
      1
      1
      33
      2452
      1
      1
      55
      2
      1
      NaN
      1
      3
      0
      13502
      4500.67
      3500



In [4]:

    
ind2 = pd.read_csv('data/cleanDataHouseHold' + trimestre + '.csv')
ind2.head()









    Out[4]:






  
    
      
      CODUSU
      NRO_HOGAR
      REGION
      PONDERA
      HomeType
      HomeTypeesp
      RoomsNumber
      FloorMaterial
      FloorMaterialesp
      RoofMaterial
      ...
      HouseMembers
      Memberless10
      Membermore10
      TotalHouseHoldIncome
      DomesticService1
      DomesticService2
      DomesticService3
      DomesticService4
      DomesticService5
      DomesticService6
    
  
  
    
      0
      303878
      1
      1
      1365
      2
      NaN
      3
      1
      NaN
      1
      ...
      1
      0
      1
      7700
      1
      0
      98
      0
      0
      0
    
    
      1
      305757
      1
      1
      1481
      2
      NaN
      3
      1
      NaN
      9
      ...
      1
      0
      1
      650
      96
      0
      98
      0
      0
      0
    
    
      2
      307861
      1
      1
      1627
      2
      NaN
      2
      1
      NaN
      1
      ...
      4
      1
      3
      4400
      1
      2
      98
      0
      0
      0
    
    
      3
      308762
      1
      1
      1549
      2
      NaN
      4
      1
      NaN
      9
      ...
      1
      0
      1
      5200
      1
      0
      98
      0
      0
      0
    
    
      4
      307029
      1
      1
      1585
      1
      NaN
      4
      1
      NaN
      9
      ...
      1
      0
      1
      700
      96
      0
      98
      0
      0
      0
    
  

5 rows × 44 columns



In [ ]:

	CODUSU	NRO_HOGAR	COMPONENTE	AGLOMERADO	PONDERA	familyRelation	female	age	schoolLevel	finishedYear	lastYear	activity	empCond	unempCond	ITF	IPCF	P47T
0	300641	1	1	33	1481	1	2	51	2	2	3.0	3	0	4	1200	300.00	1200
1	300641	1	2	33	1481	10	1	12	3	2	6.0	3	0	3	1200	300.00	0
2	300641	1	3	33	1481	10	2	9	3	2	3.0	4	0	3	1200	300.00	0
3	300641	1	4	33	1481	10	2	14	3	2	7.0	3	0	3	1200	300.00	0
4	300647	1	1	33	2452	1	1	55	2	1	NaN	1	3	0	13502	4500.67	3500

	CODUSU	NRO_HOGAR	REGION	PONDERA	HomeType	HomeTypeesp	RoomsNumber	FloorMaterial	FloorMaterialesp	RoofMaterial	...	HouseMembers	Memberless10	Membermore10	TotalHouseHoldIncome	DomesticService1	DomesticService2	DomesticService3
0	303878	1	1	1365	2	NaN	3	1	NaN	1	...	1	0	1	7700	1	0	98
1	305757	1	1	1481	2	NaN	3	1	NaN	9	...	1	0	1	650	96	0	98
2	307861	1	1	1627	2	NaN	2	1	NaN	1	...	4	1	3	4400	1	2	98
3	308762	1	1	1549	2	NaN	4	1	NaN	9	...	1	0	1	5200	1	0	98
4	307029	1	1	1585	1	NaN	4	1	NaN	9	...	1	0	1	700	96	0	98