Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
robertopucp
GitHub Repository: robertopucp/1eco35_2022_2
 Path: blob/main/Trabajo_grupal/WG6/Grupo_3_py_Ejercicio1.py
2714 views
1
#!pip install weightedcalcs

2


3
import os   # for usernanme y set direcotrio

4
import pandas as pd

5
import numpy as np

6
from tqdm import tqdm  # controlar el tiempo en un loop

7


8


9
user = os.getlogin()

10


11
os.chdir(f"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf") # Set directorio

12


13


14
" AÑO 2020"

15


16
enaho_2020 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta")

17


18
enaho01 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta",

19
                           convert_categoricals=False)

20


21
labels01 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta",

22
                           convert_categoricals=False, iterator=True)

23
labels01.variable_labels()

24


25
labels01.value_labels().keys()

26


27
labels01.value_labels()['p110']

28


29
"Modulo 34 Sumaria 2020"

30


31
enaho34 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta",

32
                           convert_categoricals=False)

33


34
labels34 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta",

35
                           convert_categoricals=False, iterator=True)

36


37
labels34.variable_labels()

38


39
"Merge 01 + 34"

40


41


42
num = ["34"]

43


44
merge_hog2020 = enaho01

45


46
for i in tqdm(num):

47
    merge_hog2020 = pd.merge(merge_hog2020, globals()[f'enaho{i}'], 

48
                         on = ["conglome", "vivienda", "hogar"],

49
                       how = "left", 

50
                       suffixes=('', '_y'),

51
                       validate = "1:1")

52
"AÑO 2019"

53
    

54
enaho0119 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2019/687-Modulo01/687-Modulo01/enaho01-2019-100.dta",

55
                           convert_categoricals=False)

56


57
labels0119 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2019/687-Modulo01/687-Modulo01/enaho01-2019-100.dta",

58
                           convert_categoricals=False, iterator=True)

59
labels0119.variable_labels()

60


61
labels0119.value_labels().keys()

62


63
labels0119.value_labels()['p110']

64


65
"Modulo 34 sumaria 2019"

66


67
enaho3419 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2019/687-Modulo34/687-Modulo34/sumaria-2019.dta",

68
                           convert_categoricals=False)

69


70
labels3419 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2019/687-Modulo34/687-Modulo34/sumaria-2019.dta",

71
                           convert_categoricals=False, iterator=True)

72


73
labels3419.variable_labels()

74


75
num = ["34"]

76


77
merge_hog2019 = enaho0119

78
for i in tqdm(num):

79
    merge_hog2019 = pd.merge(merge_hog2019, globals()[f'enaho{i}'], 

80
                         on = ["conglome", "vivienda", "hogar"],

81
                       how = "left", 

82
                       suffixes=('', '_y'),

83
                       validate = "1:1")

84
    

85
"Append"

86
    

87
merge_append = merge_hog2020.append(merge_hog2019, ignore_index = True)

88


89


90


91


92
"INGRESO Y GASTO MENNSUAL"

93


94
merge_append["ingreso_month"] = merge_append["inghog1d"]/(12*merge_append["mieperho"])

95


96
merge_append["gasto_month"]  = merge_append["gashog2d"]/(12*merge_append["mieperho"])

97


98
"DEFLACTOR ESPACIAL Y TEMPORAL"

99


100
"ESPACIAL"

101
merge_append["gasto_month_defl"]  = merge_append["gasto_month"]*(merge_append["ld"])

102


103
"TEMPORAL"

104


105
deflactor = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo34/737-Modulo34/Gasto2020/Bases/deflactores_base2020_new.dta",

106
                           convert_categoricals=False)

107
num = ["34"]

108


109
merge_base = merge_append

110


111
merge_append['dpto'] = merge_append.ubigeo.str.slice(0,2)

112


113
merge_append['aniorec'] = merge_append['aÑo']

114


115
merge_append['dpto']=merge_append['dpto'].astype(int)

116
merge_append['aniorec']=merge_append['aniorec'].astype(int)

117
merge_append = merge_append.merge(deflactor, how='inner', on=None, left_on=['dpto', 'aniorec'], right_on=['dpto', 'aniorec'], left_index=False, right_index=False, sort=False, suffixes=('_x', '_y'), copy=True, indicator=False, validate=None)

118


119
"DIVIDA POR mieperho, 12, LD e i00"

120


121
merge_append["ingreso_month_def"] = merge_append["ingreso_month"]/(merge_append["mieperho"])

122
merge_append["ingreso_month_def2"] = merge_append["ingreso_month"]/12

123
merge_append["ingreso_month_def3"] = merge_append["ingreso_month"]/(merge_append["ld"])

124
merge_append["ingreso_month_def4"] = merge_append["ingreso_month"]/(merge_append["i00"])

125


126
merge_append["gasto_month_def"] = merge_append["gasto_month"]/(merge_append["mieperho"])

127
merge_append["gasto_month_def2"] = merge_append["gasto_month"]/12

128
merge_append["gasto_month_def3"] = merge_append["gasto_month"]/(merge_append["ld"])

129
merge_append["gasto_month_def4"] = merge_append["gasto_month"]/(merge_append["i00"])

130


131
print(merge_append)

132


133
"Groupby"

134


135
enaho02 = pd.read_stata(r"C:/Users/oscar/OneDrive/Desktop/PARCIAL MADATA/enahodf/datos/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta",

136
                           convert_categoricals=False)

137


138
groupby = enaho02.groupby(['p208a'])[['hogar']].head()

139