CoCalc -- Grupo_4

GitHub Repository: robertopucp/1eco35_2022_2
Path: blob/main/Trabajo_grupal/WG6/Grupo_4_py.py
²⁷¹⁴ views
1
# -*- coding: utf-8 -*-
2
"""
3
###############################################################################
4
#                                                                             #
5
#                             WG#6 - Grupo 4                                  #
6
#                                                                             #
7
###############################################################################
8

9
Integrantes:
10
    
11
    Luana Morales
12
    Seidy Ascensios
13
    Marcela Quintero
14
    Flavia Oré
15
    
16
"""
17

18
#%% Pregunta 1 y 2 (Merge dataset Y Salario por hora del trabajador dependiente)
19

20

21
!pip install weightedcalcs
22
import os   # for usernanme y set direcotrio
23
import pandas as pd
24
import numpy as np
25
import weightedcalcs as wc # ponderador
26
from tqdm import tqdm  # controlar el tiempo en un loop
27

28
"1) Set Directorio"
29

30
user = os.getlogin()   # Username
31

32

33
os.chdir(f"C:/Users/{user}/Documents/GitHub/1ECO35_2022_2/Trabajo_grupal/WG6") # Set directorio
34

35

36

37
"ENAHO 2020"
38

39
"2) Load dataset de ENAHO"
40

41

42

43
enaho_2020 = pd.read_stata(r"../../../../enaho/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta")
44

45

46
enaho01 = pd.read_stata(r"../../../../enaho/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta",
47
                           convert_categoricals=False)
48

49

50
labels01 = pd.read_stata(r"../../../../enaho/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta",
51
                           convert_categoricals=False, iterator=True)
52

53

54

55

56
enaho34 = pd.read_stata(r"../../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta",
57
                           convert_categoricals=False)
58

59

60
labels34 = pd.read_stata(r"../../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta",
61
                           convert_categoricals=False, iterator=True)
62

63

64

65

66
"4) Merge section"
67

68
"Left merge"
69

70
#enaho34: master data
71
#enaho01: using data
72

73
enaho_merge_2020 = pd.merge(enaho34, enaho01,
74
                       on = ["conglome", "vivienda", "hogar"],
75
                       how = "left", 
76
                       validate = "m:1")
77
                       suffixes=('', '_y'),
78
)
79

80
index_columns = np.where( merge_base_2020.columns.str.contains('_y$', regex=True))[0]
81

82
merge_base_2020.drop(merge_base_2020.columns[index_columns], axis = 1, inplace = True)
83

84

85
"ENAHO 2019"
86

87
enaho_2019 = pd.read_stata(r"../../../../enaho/2019/737-Modulo01/737-Modulo01/enaho01-2019-100.dta")
88

89

90
enaho01_1 = pd.read_stata(r"../../../../enaho/2019/737-Modulo01/737-Modulo01/enaho01-2019-100.dta",
91
                           convert_categoricals=False)
92

93

94
labels01_1 = pd.read_stata(r"../../../../enaho/2019/737-Modulo01/737-Modulo01/enaho01-2019-100.dta",
95
                           convert_categoricals=False, iterator=True)
96

97

98

99

100
enaho34_1 = pd.read_stata(r"../../../../enaho/2019/737-Modulo34/737-Modulo34/sumaria-2019.dta",
101
                           convert_categoricals=False)
102

103

104
labels34_1 = pd.read_stata(r"../../../../enaho/2019/737-Modulo34/737-Modulo34/sumaria-2019.dta",
105
                           convert_categoricals=False, iterator=True)
106

107
"4) Merge section"
108

109
"Left merge"
110

111
#enaho34_1: master data
112
#enaho01_1: using data
113

114
enaho_merge_2019 = pd.merge(enaho34_1, enaho01_1,
115
                       on = ["conglome", "vivienda", "hogar"],
116
                       how = "left", 
117
                       validate = "m:1")
118
                       suffixes=('', '_y'),
119
)
120

121
index_columns = np.where( merge_base_2019.columns.str.contains('_y$', regex=True))[0]
122

123
merge_base_2019.drop(merge_base_2019.columns[index_columns], axis = 1, inplace = True)
124

125

126
# Append
127

128

129
merge_append = merge_base_2020.append(merge_base_2019, ignore_index = True)
130

131
merge_append['dpto'] = merge_append['ubigeo'].str[:2]
132

133
#ignore_index= True : no haya conflictos de indexing 
134

135
merge_append.to_stata("append_enaho.dta", write_index = False)
136

137
# Deflactar
138

139
deflactores_base2020_new = pd.read_stata(r"../../../../enaho/2020/737-Modulo34/737-Modulo34/ConstVarGasto-Metodologia actualizada/Gasto2020/Bases/deflactores_base2020_new.dta",
140
                           convert_categoricals=False)
141

142

143
"4) Merge section deflactores"
144

145

146
# merge usando como llaves a las variables dpto y aniorec. 
147
#merge_append: master data
148
#deflactores_base2020_new: using data
149

150
merge_append_deflac = pd.merge(merge_append, deflactores_base2020_new,
151
                       on = ["dpto", "aNo"],
152
                       how = "left", 
153
                       validate = "m:1")
154

155

156
merge_append_deflac["ingreso_month"] = merge_append_deflac["inghog1d"]/(12*merge_append_deflac["mieperho"]*merge_append_deflac[ld]*merge_append_deflac[i00])
157

158
merge_append_deflac["gasto_month"]  = merge_append_deflac["gashog2d"]/(12*merge_append_deflac["mieperho"]*merge_append_deflac[ld]*merge_append_deflac[i00])
159

160
#%% Pregunta 3 - Group by
161

162
#Importamos los programas necesarios 
163

164
import pandas as pd
165
from pandas import DataFrame,Series
166
import numpy as np
167
import weightedcalcs as wc 
168
from tqdm import tqdm
169
import re 
170
import os  
171

172
# Seteamos el directorio
173

174
os.chdir(f"C:/Users/Marcela Quintero/Documents/GitHub/1ECO35_2022_2/Lab7")
175

176
#Leemos la base de datos
177

178
enaho_2 = pd.read_stata(r"../../../enaho/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta", convert_categoricals=False)
179

180
#Vemos la base de datos
181

182
enaho_2
183

184

185
#Vemos los labels antes de realizar el groupby
186

187
labels2 = pd.read_stata(r"../../../enaho/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta",
188
                           convert_categoricals=False, iterator=True)
189

190
labels2.variable_labels()
191

192
labels2.value_labels().keys()
193

194
enaho_2.keys()
195

196

197
#Utilizamos group by para seleccionar la mayor edad de cada hogar
198

199

200
hogares =  enaho_2.groupby(['conglome','vivienda','hogar'],as_index=False).p208a.max()
201

202

203
print(hogares)
204

205

206
#Hacemos un merge con el módulo 34 para obtener los datos que nos faltan (pobreza)
207

208
#Para ello primero cargamos la base de datos (módulo 34) y obtenemos sus labels
209

210
enaho34 = pd.read_stata(r"../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta",
211
                           convert_categoricals=False)
212

213
labels34 = pd.read_stata(r"../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta",
214
                           convert_categoricals=False, iterator=True)
215

216
labels34.variable_labels()
217

218
labels34.value_labels().keys()
219

220
enaho34.keys()
221

222

223
#Ahora filtramos la base con groupby para quedarnos solo con lo que necesitamos (el estado de pobreza)
224

225
hogares34 =  enaho34.groupby(['conglome','vivienda','hogar'],as_index=False).pobreza.sum()
226

227
print (hogares34)
228

229

230
#Ahora, procedemos a realizar el merge entre hogares y hogares 34
231

232
enaho_merge = pd.merge(hogares, hogares34, 
233
                         on = ["conglome", "vivienda", "hogar"],
234
                       how = "inner", 
235
                       validate = "1:1")
236

237
print (enaho_merge)
238

239

240
#Procedemos a crear la dummy que verifica si el hogar es pobre y cuenta con algún miembro del hogar mayor a 65 años.
241

242
enaho_merge['dummy_pension'] = (enaho_merge['p208a'] >= 65) & (enaho_merge['pobreza'] < 3)
243

244

245
#VIsualizamos la dummy que es true si se cumplen ambas condiciones y false si no se cumplen
246

247
print(enaho_merge['dummy_pension'])
248

249

250

251

252

253

254

255

256

257

258
Product

Resources

Company
