CoCalc -- Grupo_4

GitHub Repository: robertopucp/1eco35_2022_2
Path: blob/main/Trabajo_grupal/WG6/Grupo_4_r.R
²⁷¹⁴ views
1

2
###############################  WG # 6 ######################################
3

4
# Grupo 4
5

6
# Seidy Ascencios - 20191622
7
# Luana Morales - 20191240
8
# Marcela Quintero - 20191445
9
# Flavia Or� - 20191215
10

11
##############################################################################
12
#                                                                            #
13
#                                 PREGUNTA 1                                 #
14
#                                                                            #
15
##############################################################################
16

17

18
#install.packages("stringr")
19

20

21
library(haven)  # leer archivos spss, stata, dbf, etc
22
library(dplyr)  # limpieza de datos
23
library(stringr)   # grep for regular expression
24
library(fastDummies) # crear dummy
25
library(srvyr)  # libreria para declarar el diseño muestral de una encuesta
26
library(survey)
27

28
"1) Set Directorio"
29

30
user <- Sys.getenv("USERNAME")  
31

32
setwd( paste0("C:/Users/",user,"/Documents/GitHub/1ECO35_2022_2/Trabajo_grupal/WG6") ) # set directorio
33

34

35
"ENAHO 2020"
36

37
"2) Load dataset de ENAHO"
38

39
enaho01 <- read_dta("../../../../enaho/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta")
40

41

42
enaho34 <- read_dta("../../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta")
43

44

45
enaho01<- data.frame(
46
  
47
  read_dta("../../../../enaho/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta")
48
  
49
)
50

51
enaho34 = data.frame(
52
  read_dta("../../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta")
53
)
54

55

56
"4) Merge section"
57

58
"Left merge"
59

60
#enaho34: master data
61
#enaho01: using data
62

63
enaho_merge <- merge(enaho34, enaho01,
64
                     by = c("conglome", "vivienda", "hogar"),
65
                     all.x = T
66
)
67

68

69
index <- grep(".y$", colnames(enaho_merge))  # Regular regular 
70

71
# $ el texto finaliza con .y
72

73
merge_base_2020 <- enaho_merge[, - index]
74

75

76
"ENAHO 2019"
77

78

79
enaho01_1 <- read_dta("../../../../enaho/2019/687-Modulo01/687-Modulo01/enaho01-2019-100.dta")
80

81

82
enaho34_1 <- read_dta("../../../../enaho/2019/687-Modulo34/687-Modulo34/sumaria-2019.dta")
83

84

85
"4) Merge section"
86

87
"Left merge"
88

89
#enaho34_1: master data
90
#enaho01_1: using data
91

92
enaho_merge_1 <- merge(enaho34_1, enaho01_1,
93
                       by = c("conglome", "vivienda", "hogar"),
94
                       all.x = T
95
)
96

97

98
index_1 <- grep(".y$", colnames(enaho_merge_1))  # Regular regular 
99

100
# $ el texto finaliza con .y
101

102
merge_base_2019 <- enaho_merge_1[, - index_1]
103

104

105
colnames(merge_base_2020)
106

107
#----------------------- Append -----------------------------------
108

109
merge_append <-  bind_rows(merge_base_2019, merge_base_2020) # bind_rows from dyplr 
110

111
unique(merge_append$aÑo)
112

113

114
#rename 
115

116
merge_append <- merge_append %>% dplyr::rename(aÑo = aÑo.x,ubigeo = ubigeo.x)
117

118

119
# sibstr permite sustraer digitos de un string, texto, caracter
120

121
merge_append['ubigeo_dep'] = substr(merge_append$ubigeo, 1, 2)
122

123
#----------------------- Deflactar -----------------------------------
124

125
deflactores_base2020_new <- read_dta("../../../../enaho/2020/737-Modulo34/737-Modulo34/ConstVarGasto-Metodologia actualizada/Gasto2020/Bases/deflactores_base2020_new.dta")
126

127

128
deflactores_base2020_new <- deflactores_base2020_new %>% dplyr::rename(aÑo = aniorec)
129

130

131
names(deflactores_base2020_new)
132

133
"4) Merge section deflactores"
134

135

136
# merge usando como llaves a las variables dpto y aniorec. 
137
#merge_append: master data
138
#deflactores_base2020_new: using data
139

140

141
enaho_merge_defla <- merge(merge_append, deflactores_base2020_new,
142
                           by = c("dpto", "aÑo"),
143
                           all.x = T, suffixes = c("","")
144
)
145

146
colnames(enaho_merge_defla)
147

148
enaho_merge_defla <- enaho_merge_defla %>%
149
  mutate(ingreso_month_pc = enaho_merge_defla$inghog1d/(12*enaho_merge_defla$mieperho*enaho_merge_defla$ld*enaho_merge_defla$i00),
150
         gasto_month_pc = enaho_merge_defla$gashog2d/(12*enaho_merge_defla$mieperho*enaho_merge_defla$ld*enaho_merge_defla$i00)
151
  )
152

153

154

155

156

157
#------------------------------------------------------------------------------#
158
#                                                                              #
159
#                           PREGUNTA 2 - GROUP BY                              # 
160
#                                                                              #
161
#------------------------------------------------------------------------------#
162

163
#Importamos los programas necesarios 
164

165

166
library(haven)  
167
library(dplyr)  
168
library(stringr)   
169
library(fastDummies) 
170
library(srvyr)  
171
library(survey)
172

173
# Seteamos el directorio
174

175
user <- Sys.getenv("USERNAME")  
176

177
setwd( paste0("C:/Users/",user,"/Documents/GitHub/1ECO35_2022_2/Trabajo_grupal/WG6") ) # set directorio
178

179
#Leemos la base de datos
180

181
enaho_2 <-  read_dta(r"../../../enaho/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta")
182

183
#Vemos la base de datos
184

185
enaho_2$dominio
186

187
enaho_2 <- data.frame(
188
  
189
  read_dta("../../../enaho/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta")
190
  
191
)
192

193

194
#Vemos los labels antes de realizar el groupby
195

196
names(enaho_2)
197

198

199
#Seleccionamos las variables que usaremos
200

201
hogares <- enaho_2[ , c("conglome", "vivienda", "hogar", "p208a") ]
202

203

204
#Hacemos un merge con el modulo 34 para obtener los datos que nos faltan (pobreza)
205

206
#Para ello primero cargamos la base de datos (modulo 34) y obtenemos sus labels
207

208

209
enaho34 = data.frame(
210
  read_dta("../../../enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta")
211
)
212

213
names(enaho34)
214

215
#Ahora filtramos la base con groupby para quedarnos solo con lo que necesitamos (el estado de pobreza)
216

217
hogares34 <- enaho34[ , c("conglome", "vivienda", "hogar", "pobreza") ]
218

219

220
#Ahora, procedemos a realizar el merge entre hogares y hogares 34
221

222
enaho_merge <- merge(hogares, hogares34,
223
                           by = c("conglome", "vivienda", "hogar")
224
)
225

226
print (enaho_merge)
227

228

229

230
#Procedemos a crear la dummy que verifica si el hogar es pobre y cuenta con algun miembro del hogar mayor a 65 a�os.
231

232
enaho_merge['dummypension'] <- (enaho_merge['p208a'] >= 65) & (enaho_merge['pobreza'] < 3)*1
233
## Se puede obtener la dummy mediante la funci�n if_else(), as.numeric() o multiplicando por 1 lo que deseamos evaluar, 
234
## en este caso, pobreza del hogar y el requisito de la edad.
235

236

237
#Visualizamos la dummy, la cual ser� true (1) si se cumplen ambas condiciones y false (0) si no se cumplen
238

239
print(enaho_merge['dummypension'])
240

241

242

243

244

245

246

247
#------------------------------------------------------------------------------#
248
#                                                                              #
249
#                        PREGUNTA 4 - indicadores                              # 
250
#                                                                              #
251
#------------------------------------------------------------------------------#
252

253
#Insatalamos los paquetes necesarios 
254

255
pacman::p_load(haven,dplyr, stringr, fastDummies,srvyr )
256

257
library(reshape)
258
library(haven)
259
library(dplyr)
260
library (srvyr)
261
library(survey)
262

263
#insertamos las bases de datos
264
user <- Sys.getenv("USERNAME") 
265

266
setwd( paste0("C:/Users/",user,"/Documents/data_enaho") )
267

268
enaho.700 <- read_dta("C:/Users/seibe/OneDrive/Documents/DATA_STATA/enaho01-2020-700.dta")
269
View(enaho.700)
270

271
enaho.sumaria <- read_dta("C:/Users/seibe/OneDrive/Documents/DATA_STATA/sumaria-2020-12g.dta")
272
View(enaho.sumaria)
273

274
#Especificamos el diseño muestral 
275
survey_enaho <- enaho.700%>% as_survey_design(ids = conglome, strata = estrato, 
276
                                              weight = factor07)
277

278
View (survey_enaho)
279

280
survey_enaho_2 <- enaho.sumaria%>% as_survey_design(ids = conglome, strata = estrato, 
281
                                                    weight = factor07)
282

283
View (survey_enaho_2)
284

285
#Creamos la variable region para ambas muestras
286

287
enaho.700['ubigeo'] = substr(enaho.700$ubigeo, 1, 2)
288

289
enaho.700 <- enaho.700 %>% 
290
  mutate(region = case_when(ubigeo == "01" ~ "Amazonas",
291
                            ubigeo == "02" ~ "Ancash",
292
                            ubigeo == "03" ~ "Apurimac",
293
                            ubigeo == "04" ~ "Arequipa", 
294
                            ubigeo == "05" ~ "Ayacucho",
295
                            ubigeo == "06" ~ "Cajamarca",
296
                            ubigeo == "07" ~ "Callao",
297
                            ubigeo == "08" ~ "CUsco",
298
                            ubigeo == "09" ~ "Huancavelica",
299
                            ubigeo == "10" ~ "Huanuco",
300
                            ubigeo == "11" ~ "Ica",
301
                            ubigeo == "12" ~ "Junin", 
302
                            ubigeo == "13" ~ "La Libertad",
303
                            ubigeo == "14" ~ "Lambayeque",
304
                            ubigeo == "15" ~ "Lima",
305
                            ubigeo == "16" ~ "Loreto",
306
                            ubigeo == "17" ~ "Madre de Dios",
307
                            ubigeo == "18" ~ "Moquegua",
308
                            ubigeo == "19" ~ "Pasco", 
309
                            ubigeo == "20" ~ "Piura",
310
                            ubigeo == "21" ~ "Puno",
311
                            ubigeo == "22" ~ "San Martin",
312
                            ubigeo == "23" ~ "Tacna",
313
                            ubigeo == "24" ~ "Tumbes",
314
                            ubigeo == "25" ~ "Ucayali", ))
315

316
View(enaho.700[, c("region")]) 
317

318

319
enaho.sumaria['ubigeo'] = substr(enaho.sumaria$ubigeo, 1, 2)
320

321
enaho.sumaria <- enaho.sumaria %>% 
322
  mutate(region = case_when(ubigeo == "01" ~ "Amazonas",
323
                            ubigeo == "02" ~ "Ancash",
324
                            ubigeo == "03" ~ "Apurimac",
325
                            ubigeo == "04" ~ "Arequipa", 
326
                            ubigeo == "05" ~ "Ayacucho",
327
                            ubigeo == "06" ~ "Cajamarca",
328
                            ubigeo == "07" ~ "Callao",
329
                            ubigeo == "08" ~ "CUsco",
330
                            ubigeo == "09" ~ "Huancavelica",
331
                            ubigeo == "10" ~ "Huanuco",
332
                            ubigeo == "11" ~ "Ica",
333
                            ubigeo == "12" ~ "Junin", 
334
                            ubigeo == "13" ~ "La Libertad",
335
                            ubigeo == "14" ~ "Lambayeque",
336
                            ubigeo == "15" ~ "Lima",
337
                            ubigeo == "16" ~ "Loreto",
338
                            ubigeo == "17" ~ "Madre de Dios",
339
                            ubigeo == "18" ~ "Moquegua",
340
                            ubigeo == "19" ~ "Pasco", 
341
                            ubigeo == "20" ~ "Piura",
342
                            ubigeo == "21" ~ "Puno",
343
                            ubigeo == "22" ~ "San Martin",
344
                            ubigeo == "23" ~ "Tacna",
345
                            ubigeo == "24" ~ "Tumbes",
346
                            ubigeo == "25" ~ "Ucayali", ))
347

348
View(enaho.sumaria[, c("region")]) 
349

350
# Se halla el porcentaje que hogares a nivel departamental (o region) que se beneficia del programa.
351

352
bene_prog <- enaho.700 %>% group_by(ubigeo, region) %>% 
353
  summarise(porc_bene_pro = mean(p710_04, na.rm = T), .groups = "keep" ) 
354

355

356
View(bene_prog)
357

358
# Se muestra el promedio del porcentaje de gasto en salud realizado por los hogares a nivel de region
359

360
enaho.sumaria<-mutate(enaho.sumaria, gasto_anual_hogar=gru51hd/gashog2d)
361

362
View(enaho.sumaria[, c("gasto_anual_hogar", "region")]) 
363

364
gasto_salud <- enaho.sumaria %>% group_by(ubigeo, region) %>% 
365
  summarise(porc_gasto_salud = mean(gasto_anual_hogar, na.rm = T), .groups = "keep" )
366

367
View(gasto_salud)
368

369
Product

Resources

Company
