CoCalc -- Grupo_8

GitHub Repository: robertopucp/1eco35_2022_2
Path: blob/main/Trabajo_grupal/WG7/Grupo_8_R.R
²⁷¹⁴ views
1
#TAREA 7
2
#Grupo 8
3

4
# clear environment
5
rm(list=ls(all=TRUE))
6
install.packages("readxl")
7
install.packages("lubridate")
8
install.packages("tidyverse")
9
library(reshape)
10
library(haven)
11
library(dplyr)
12
library("readxl")
13
library(stringr)
14

15

16
#------- Reshape -----------
17

18
"1.0 Set Directorio"
19

20
user <- Sys.getenv("USERNAME")  # username
21

22
setwd( paste0("C:/Users/",user,"/Documents/GitHub/1ECO35_2022_2/Lab8") ) # set directorio
23

24

25
# load dataset
26

27
data <- read_excel("../data/crime_data/data_administrativa.xlsx")
28

29
# nombres de variables en minúsculas
30
colnames(data) <- tolower(colnames(data))
31

32
# limpiar nombres
33
data$inst1 <- apply(data['nombre'],
34
                    1 ,
35
                    function(x) gsub("[0-9]", '', x))
36
data$inst2 <- apply(data['inst1'],
37
                    1 ,
38
                    function(x) gsub("\\-", '', x))
39
data$inst3 <- apply(data['inst2'],
40
                    1 ,
41
                    function(x) gsub("\\.", '', x))
42
data$inst4 <- apply(data['inst3'],
43
                    1 ,
44
                    function(x) gsub("\\/", '', x))
45

46
# limpiar born_date
47

48
data$date1 <- apply(data['born_date'],
49
                             1 ,
50
                             function(x) str_replace(x,'00:00',''))
51

52
data$date2 <- apply(data['date1'],
53
                    1 ,
54
                    function(x) str_replace(x,'"#%',''))
55

56
data$date3 <- apply(data['date2'],
57
                    1 ,
58
                    function(x) str_replace(x,'!',''))
59

60
# date como variable en formato fecha
61
data <- data |> dplyr::mutate(
62
  date = dmy( date3  )
63
)
64

65
# limpiar born_date
66

67
data$age1 <- apply(data['age'],
68
                    1 ,
69
                    function(x) str_extract(x,'[0-9]+'))
70

71
# limpiar rank
72
data$rank1 <- apply(data['rank'],
73
                    1 ,
74
                    function(x) str_replace(x,'extorsionador','extorsion'))
75

76
data$rank2 <- apply(data['rank1'],
77
                    1 ,
78
                    function(x) str_replace(x,'novto','novato'))
79

80
data$rank3 <- apply(data['rank2'],
81
                    1 ,
82
                    function(x) str_replace(x,'noato','novato'))
83

84
data$rank4 <- apply(data['rank3'],
85
                    1 ,
86
                    function(x) str_replace(x,'principiante','novato'))
87
# crear dummies
88

89
data1<- data %>% dplyr::mutate(dum1 = ifelse( rank == 'lider de la banda criminal',
90
                                                     1 ,
91
                                                     0 ) )%>%
92
  dplyr::mutate(dum2 = ifelse( rank == 'cabecilla local',
93
                               1 ,
94
                               0 ) )%>%                                     
95
dplyr::mutate(dum3 = ifelse( rank == 'cabecilla regional',
96
                             1 ,
97
                             0 ) )%>%   
98
  dplyr::mutate(dum4 = ifelse( rank == 'sicario',
99
                               1 ,
100
                               0 ) )%>%
101
  dplyr::mutate(dum5 = ifelse( rank == 'extorsion',
102
                               1 ,
103
                               0 ) )%>%
104
  dplyr::mutate(dum6 = ifelse( rank == 'miembro',
105
                               1 ,
106
                               0 ) )%>%
107
  dplyr::mutate(dum7 = ifelse( rank == 'novato',
108
                               1 ,
109
                               0 ) )
110

111
# extraer usuario de correo electronico
112
                   
113
data1$user<- apply(data1['correo_abogado'],
114
                    1 ,
115
                    function(x) str_match(x, "(\\w+)\\@.*")[2])
116

117
# extraer dni
118

119
data1$dni1 <- apply(data1['dni'],
120
                            1 ,
121
                            function(x) str_match(x,"\\.*(\\d+\\-\\d+)$")[2])
122
# crear variable crimen
123
data1$crimen <-apply(data1['observaciones'],
124
                      1 ,
125
                      function(x) str_match(x,"\\.*+[P/p]or\\s([\\w*\\s]*)")[2])           
126
# crear variable n_hijos
127
data1$n_hijos <-apply(data1['observaciones'],
128
                     1 ,
129
                     function(x) str_match(x,"\\d*[Tt]iene\\s([0-9]*)")[2])
130

131
# crear variable edad_inicio
132
data1$edad_inicio1 <-apply(data1['observaciones'],
133
                      1 ,
134
                      function(x) str_match(x,"\\.*+([\\w*\\s]*)\\s[A/a]ños")[2])
135

136
data1$edad_inicio <- apply(data1['edad_inicio1'],
137
                           1 ,
138
                           function(x) str_extract(x,"[0-9]+"))
139
Product

Resources

Company
