Grupo_9_py_Pregunta1.ipynb

Kernel: Python 3 (ipykernel)

### Pregunta 1 #### Grupo 9 ####

from IPython.display import display, HTML

display(HTML(data="""
<style>
    div#notebook-container    { width: 75%; }
    div#menubar-container     { width: 95%; }
    div#maintoolbar-container { width: 65%; }a
</style>
"""))

#1.0 Set directorio
import numpy as np
import pandas as pd
from pandas import DataFrame,Series

#2.0 Cargar dataset de ENAHO
enaho01 = pd.read_stata( r"../../enaho//2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta")
sumaria = pd.read_stata(r"../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta")

#3.0 Juntar bases
        # _merge3 == 3 Mantener solo la intercepción

enaho_2020 = pd.merge(enaho01, sumaria,
                       on = ["conglome", "vivienda", "hogar"],
                       how = "left", 
                       suffixes=('', '_y'))

#4.0 Filtrar variables a usar

enaho_2020 = enaho_2020[["conglome", "vivienda", "hogar" ,"ubigeo", 
                   "aÑo" , "mieperho", "inghog1d", 
                   "gashog2d", "ld"]]

### Repetir procedimientos con data 2019
"2.0"
enaho01 = pd.read_stata(r"../../enaho/2019/687-Modulo01/687-Modulo01/enaho01-2019-100.dta")
sumaria = pd.read_stata(r"../../enaho/2019/687-Modulo34/687-Modulo34/sumaria-2019.dta")

"3.0"
enaho_2019 = pd.merge(enaho01, sumaria,
                       on = ["conglome", "vivienda", "hogar"],
                       how = "left", 
                       suffixes=('', '_y'))

"4.0"
enaho_2019 = enaho_2019[["conglome", "vivienda", "hogar" ,"ubigeo", 
                   "aÑo" , "mieperho", "inghog1d", 
                   "gashog2d", "ld"]]

# 5.0 Append de base 2019 y 2020
merge_append = enaho_2020.append(enaho_2019, 
                                 ignore_index = True)
    #ignore_index= True : no haya conflictos de indexing 
merge_append

C:\Users\acwe\AppData\Local\Temp\ipykernel_14456\1072011287.py:2: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  merge_append = enaho_2020.append(enaho_2019,

  #Año:
merge_append.rename(columns={"aÑo":"aniorec"}, 
                    inplace=True)
merge_append=merge_append.astype({'aniorec':float})
    # Nota, se tiene que convertir a float para luego hacer merge
merge_append["aniorec"]

0        2020.0
1        2020.0
2        2020.0
3        2020.0
4        2020.0
          ...  
97286    2019.0
97287    2019.0
97288    2019.0
97289    2019.0
97290    2019.0
Name: aniorec, Length: 97291, dtype: float64

  #Departamento:
merge_append['dpto'] = merge_append['ubigeo'].str[:2]
merge_append= merge_append.astype({'dpto':float}) 
    # Nota, se tiene que convertir a float para luego hacer merge
merge_append.head(10)

#6.0 Deflactar variables

    #6.1. Cargar base con deflactores
    
  #Deflactor espacial:
      # ld de base

  #Deflactor temporal:
deflactor = pd.read_stata(r"../../enaho/2020/737-Modulo34/737-Modulo34/ConstVarGasto-Metodologia actualizada/Gasto2020/Bases/deflactores_base2020_new.dta",)
deflactor = deflactor[ ["dpto", "aniorec", "i00" ]]
deflactor

    #6.2. Unir deflactor a la base.
enaho = pd.merge(merge_append, deflactor,
                           on = ["dpto", "aniorec"], 
                           how = 'left',
                           validate = "m:1")
enaho

#7.0 Dividir las variables de ingreso y gasto por mieperho, 12, id e i00

enaho['den']=enaho['mieperho']*enaho['ld']*enaho['i00']*12  #denominador

#Ingreso per cápita = ipc
enaho['ipc'] = enaho['inghog1d'] / enaho['den']   #mensual

#Gasto per cápita = gpc
enaho['gpc'] = enaho['gashog2d'] / enaho['den']   #mensual

#8.0 Mismos resultados que en R
enaho= enaho.sort_values(["aniorec", "conglome", "vivienda", "hogar"])
enaho