CoCalc -- Grupo_3

GitHub Repository: robertopucp/1eco35_2022_2
Path: blob/main/Trabajo_grupal/WG6/Grupo_3_R.R
²⁷¹⁴ views
1
# TAREA 6
2

3

4
pacman::p_load(haven,dplyr,stringr, fastDummies,srvyr)
5

6
user <- Sys.getenv("fdcc0")
7

8
setwd( paste0("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho") )
9

10
# 
11

12
enaho01_2019 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2019/687-Modulo01/687-Modulo01/enaho01-2019-100.dta")
13

14
enaho01_2020 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2020/737-Modulo01/737-Modulo01/enaho01-2020-100.dta")
15

16

17
enaho34_2019 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2019/687-Modulo34/687-Modulo34/sumaria-2019.dta")
18

19
enaho34_2020 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta")
20

21

22
deflactor_temporal <- read_dta("D:/PYTHON/2020/737-Modulo34/737-Modulo34/ConstVarGasto-Metodologia actualizada/Gasto2020/Bases/deflactores_base2020_new.dta")
23

24
# 1. MERGE DATASET 
25

26
enaho_merge2019 <- merge(enaho34_2019, enaho01_2019,
27
                         by = c("conglome", "vivienda", "hogar"),
28
                         all.x = T
29
)
30

31

32
enaho_merge2020 <- merge(enaho34_2020, enaho01_2020,
33
                         by = c("conglome", "vivienda", "hogar"),
34
                         all.x = T
35
)
36

37
# juntamos las bases 2019 y 2020
38
enaho_append <- append(enaho_merge2019, enaho_merge2020) 
39

40
# ingreso y gasto mensual
41
enaho_append$ingreso_mensual <- enaho_append$inghog1d / (12*enaho_append$mieperho)
42

43
enaho_append$gasto_mensual <- enaho_append$gashog2d / (12*enaho_append$mieperho)
44

45
# deflactando las variables (deflactor espacial y temporal)
46

47
# espacial
48
enaho_append$ingreso_mensual_defl <- enaho_append$ingreso_mensual * enaho_append$ld
49

50
enaho_append$gasto_mensual_defl <- enaho_append$gasto_mensual * enaho_append$ld
51

52
# temporal
53

54

55
##############################3#
56

57
# 2. Salario por hora del trabajador dependiente
58

59
enaho01_500 <- read_dta("D:/PYTHON/2020/737-Modulo05/737-Modulo05/enaho01a-2020-500.dta")
60

61
# salario anual del primer y segundo empleo
62

63
enaho01_500$ingreso_anual <- enaho01_500$i524e1 + enaho01_500$i538e1
64

65
# cantidad de hrs trabajadas a la semana 
66

67
enaho01_500$horas_trab_sem <- enaho01_500$i513t + enaho01_500$i518
68

69
# salario por hora del trabajador dependiente
70

71
enaho01_500$salarioxhora <- enaho01_500$ingreso_anual / (enaho01_500$horas_trab_sem*52)
72

73
# reemplazamos los NA por valores cero 
74

75
enaho01_500$salarioxhora[is.na(enaho01_500$salarioxhora)] = 0
76

77

78
  # GROUPBY 
79

80
# personas con 65 o más años que puedan participar del programa Juntos
81
enaho01_200_2019 <- read_dta("D:/PYTHON/2019/687-Modulo02/687-Modulo02/enaho01-2019-200.dta")
82
enaho01_200_2020 <- read_dta("D:/PYTHON/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta")
83

84
enaho_200_append <- append(enaho01_200_2019, enaho01_200_2020) 
85

86
enaho_200_append$mayor_65 <- enaho_200_append$p208a >= 65
87

88

89

90

91
# GROUPBY 
92

93
# personas con 65 o más años que puedan participar del programa pensión 65
94

95
enaho01_200_2019 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2019/687-Modulo02/687-Modulo02/enaho01-2019-200.dta")
96
enaho01_200_2020 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2020/737-Modulo02/737-Modulo02/enaho01-2020-200.dta")
97

98

99

100
enaho01_200_2019 <- enaho01_200_2019[ , c("conglome", "vivienda", "hogar" , "codperso",
101
                                          "ubigeo", "dominio" ,"estrato" ,"p208a", "p209",
102
                                          "p207", "p203", "p201p" , "p204",  "facpob07")]
103

104

105
enaho_merge2019 <- merge(enaho34_2019, enaho01_200_2019,
106
                         by = c("conglome", "vivienda", "hogar"),
107
                         all.x = T)
108

109

110
enaho_merge2019 <- enaho_merge2019[ , c("conglome", "vivienda", "hogar" , "codperso",
111
                                        "pobreza" ,"p208a")] %>% 
112
  mutate(dummy_pobreza = ifelse(enaho_merge2019$pobreza == 3,0,1)) %>% 
113
  filter(enaho_merge2019$p208a >= 65)
114

115
# INDICADORES
116

117
# halle el porcentaje que hogares a nivel departamental que se beneficia del programa.
118

119
enaho01_37_2020 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2020/737-Modulo37/737-Modulo37/enaho01-2020-700.dta")
120

121
# Creamos la variable departamental
122

123
enaho01_37_2020["cod_departamento"] = paste(str_sub(enaho01_37_2020$ubigeo,1,2))
124

125
survey_enaho37 <- enaho01_37_2020 %>% as_survey_design(ids = conglome,
126
                                                       strata = estrato,
127
                                                       weight = factor07)
128

129
indicador1 <- survey_enaho37 %>%
130
  group_by(cod_departamento) %>%
131
  summarise (beneficiario = survey_mean(p710_04))
132

133
# muestre el promedio del porcentaje de gasto en salud a nivel región
134

135

136
enaho34_2020 <- read_dta("C:/Users/fdcc0/Desktop/PUCP/2022-2/R-PYTHON/TAREA 6/enaho/2020/737-Modulo34/737-Modulo34/sumaria-2020.dta")
137

138
# Creamos la variable departamental
139

140
enaho34_2020["cod_departamento"] = paste(str_sub(enaho34_2020$ubigeo,1,2))
141

142
survey_enaho34 <- enaho34_2020 %>% as_survey_design(ids = conglome,
143
                                                    strata = estrato,
144
                                                    weight = factor07)
145

146

147
indicador2 <- survey_enaho34 %>% mutate(gastosalud = 
148
                                          enaho34_2020$gru51hd/
149
                                          enaho34_2020$gashog2d) %>% 
150
  group_by(cod_departamento) %>%
151
  summarise (beneficiario = survey_median(gastosalud))
152

153

154

155

156

157

158

159

160
Product

Resources

Company
