date: 20-01-2022

casen_2006 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2006_c.rds")
casen_2006 <- mutate_if(casen_2006, is.factor, as.character)
casen_2009 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2009_c.rds")
casen_2009 <- mutate_if(casen_2009, is.factor, as.character)
casen_2011 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2011_c.rds")
casen_2011 <- mutate_if(casen_2011, is.factor, as.character)
casen_2013 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2013_c.rds")
casen_2013 <- mutate_if(casen_2013, is.factor, as.character)
casen_2015 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2015_c.rds")
casen_2015 <- mutate_if(casen_2015, is.factor, as.character)
casen_2017 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2017_c.rds")
casen_2017 <- mutate_if(casen_2017, is.factor, as.character)
casen_2020 <- readRDS(file = "C:/Users/chris/Desktop/archivos grandes/casen_2020_c.rds")
casen_2020 <- mutate_if(casen_2020, is.factor, as.character)

vv <- c("O4","O4","o6","o6","o6","o6","o6") # <<<<<<------- cambiar variables

casen_2006 <- casen_2006[,c("EXPC", "COMUNA"          ,vv[1],            "T4","SEXO","E1")]
casen_2009 <- casen_2009[,c("EXPC", "COMUNA"          ,vv[2],            "T5","SEXO","E1")]
casen_2011 <- casen_2011[,c("expc_full", "comuna"     ,vv[3],            "r6","sexo","e1","r2p_cod")]
casen_2013 <- casen_2013[,c("expc", "comuna"          ,vv[4],            "r6","sexo","e1","r2_p_cod")]
casen_2015 <- casen_2015[,c("expc_todas", "comuna"    ,vv[5],            "r3","sexo","e1","r2espp_cod")]
casen_2017 <- casen_2017[,c("expc", "comuna"          ,vv[6],            "r3","sexo","e1","r2_p_cod")]
casen_2020 <- casen_2020[,c("expc", "comuna"          ,vv[7],            "r3","sexo","e1","r2_pais_esp")]

Homologación de alfabetismo

casen_2006$E1[casen_2006$E1 == "No sabe /Sin dato"] <- NA
casen_2011$e1[casen_2011$e1 == "Sí, lee y escribe"] <- "Sí"
casen_2011$e1[casen_2011$e1 == "No, sólo lee"] <- "No"
casen_2011$e1[casen_2011$e1 == "No, ninguno"] <- "No"
casen_2011$e1[casen_2011$e1 == "No, sólo escribe"] <- "No"
casen_2013$e1[casen_2013$e1 == "Sí, lee y escribe"] <- "Sí"
casen_2013$e1[casen_2013$e1 == "No, ninguno"] <- "No"
casen_2013$e1[casen_2013$e1 == "No, sólo lee"] <- "No"
casen_2013$e1[casen_2013$e1 == "No, sólo escribe"] <- "No"
casen_2013$e1[casen_2013$e1 == "NS/NR"] <- NA
casen_2015$e1[casen_2015$e1 == "Sí, lee y escribe"] <- "Sí"
casen_2015$e1[casen_2015$e1 == "No, ninguno"] <- "No"
casen_2015$e1[casen_2015$e1 == "No, sólo lee"] <- "No"
casen_2015$e1[casen_2015$e1 == "No, sólo escribe"] <- "No"
casen_2017$e1[casen_2017$e1 == "Sí, lee y escribe"] <- "Sí"
casen_2017$e1[casen_2017$e1 == "No, sólo lee"] <- "No"
casen_2017$e1[casen_2017$e1 == "No, ninguno"] <- "No"
casen_2017$e1[casen_2017$e1 == "No sabe/responde"] <- NA
casen_2017$e1[casen_2017$e1 == "No, sólo escribe"] <- "No"
casen_2020$e1[casen_2020$e1 == 1] <- "Sí"
casen_2020$e1[casen_2020$e1 == 0] <- "No"

Homologación de etnia

variable_etnia <- function(dataset){
  
  variable <- switch(i,"T4","T5","r6","r6","r3","r3","r3")
  
  
dataset[,variable][dataset[,variable] == "Aimara" ]  <- "Aymara"
dataset[,variable][dataset[,variable] == "No pertenece a ninguno de estos pueblos indígenas" ]  <-  "No pertenece a ningún pueblo indígena" 
dataset[,variable][dataset[,variable] == "Mapuche"]  <- "Mapuche"
dataset[,variable][dataset[,variable] == "Diaguita"]  <- "Diaguita"
dataset[,variable][dataset[,variable] == "Atacameño (Likan-Antai)" ]  <- "Atacameño"
dataset[,variable][dataset[,variable] == "Atacameño (Likán Antai)" ]  <- "Atacameño"
dataset[,variable][dataset[,variable] == "Atacameño (Likán-Antai)" ]  <- "Atacameño"
dataset[,variable][dataset[,variable] == "Yámana o Yagán" ]  <- "Yagán"
dataset[,variable][dataset[,variable] == "Yagan" ]  <- "Yagán"
dataset[,variable][dataset[,variable] == "Yagán (Yámana)" ]  <- "Yagán"
dataset[,variable][dataset[,variable] == "Rapa-Nui o Pascuenses"]  <- "Pascuense"
dataset[,variable][dataset[,variable] == "Rapa-Nui"]  <- "Pascuense"
dataset[,variable][dataset[,variable] == "Rapa Nui (Pascuense)"]  <- "Pascuense"
dataset[,variable][dataset[,variable] == "Rapa Nui"]  <- "Pascuense"
dataset[,variable][dataset[,variable] == "Collas"]  <- "Coya"
dataset[,variable][dataset[,variable] == "Kawashkar o Alacalufes" ]  <- "Alacalufe"
dataset[,variable][dataset[,variable] == "Kawashkar" ]  <- "Alacalufe"
dataset[,variable][dataset[,variable] == "Kawésqar (Alacalufes)" ]  <- "Alacalufe"
dataset[,variable][dataset[,variable] == "Kawésqar" ]  <- "Alacalufe"
dataset[,variable][dataset[,variable] == "Kawaskar" ]  <- "Alacalufe"
dataset[,variable][dataset[,variable] ==  "Sin dato"]  <- NA
dataset[,variable][dataset[,variable] ==  "NS/NR"   ]  <- NA
dataset[,variable][dataset[,variable] == "No sabe/no responde" ]  <- NA 
# df <<- dataset

  
    switch(i,
        case =  casen_2006 <<- dataset,
        case =  casen_2009 <<- dataset,
        case =  casen_2011 <<- dataset,
        case =  casen_2013 <<- dataset,
        case =  casen_2015 <<- dataset,
        case =  casen_2017 <<- dataset,
        case =  casen_2020 <<- dataset 
)
}

for (i in 1:7) {
  
  switch(i,
        case = casen <- casen_2006,
        case = casen <- casen_2009,
        case = casen <- casen_2011,
        case = casen <- casen_2013,
        case = casen <- casen_2015,
        case = casen <- casen_2017,
        case = casen <- casen_2020
)
  
  variable_etnia(casen)
  
}

Homologación de migración

for (i in unique(casen_2020$r2_pais_esp)) {
  pais <- gsub("(^[[:space:]]+|[[:space:]]+$)", "", i)
  pais <- tolower(pais)
  casen_2020$r2_pais_esp[casen_2020$r2_pais_esp == i] <- str_to_title(pais) 
} 

casen_2011$r2p_cod[casen_2011$r2p_cod == "No contesta"] <- "NS/NR"
casen_2013$r2_p_cod[casen_2013$r2_p_cod == "No contesta"] <- "NS/NR"
casen_2015$r2espp_cod[casen_2015$r2espp_cod == "No contesta"] <- "NS/NR"
casen_2017$r2_p_cod[casen_2017$r2_p_cod == "No Bien Especificado"] <- "NS/NR"
casen_2017$r2_p_cod[casen_2017$r2_p_cod == "No Responde"] <- "NS/NR"
casen_2020$r2_pais_esp[casen_2020$r2_pais_esp == "No Bien Especificado"] <- "NS/NR"
casen_2020$r2_pais_esp[casen_2020$r2_pais_esp == ""] <- NA
casen_2020$r2_pais_esp[casen_2020$r2_pais_esp == "No Responde"] <- "NS/NR"

Homologación de variable

variable_en_estudio <- function(dataset){
  
  variable <- switch(i,vv[1],vv[2],vv[3],vv[4],vv[5],vv[6],vv[7])
   
dataset[,variable][dataset[,variable] ==  'NA'] <- 'No Aplica'
dataset[,variable][dataset[,variable] ==  'No'] <- 'No'
dataset[,variable][dataset[,variable] ==  'Sí'] <- 'Sí'

    switch(i,
        case =  casen_2006 <<- dataset,
        case =  casen_2009 <<- dataset,
        case =  casen_2011 <<- dataset,
        case =  casen_2013 <<- dataset,
        case =  casen_2015 <<- dataset,
        case =  casen_2017 <<- dataset,
        case =  casen_2020 <<- dataset 
)
}

for (i in 1:7) {
  
  switch(i,
        case = casen <- casen_2006,
        case = casen <- casen_2009,
        case = casen <- casen_2011,
        case = casen <- casen_2013,
        case = casen <- casen_2015,
        case = casen <- casen_2017,
        case = casen <- casen_2020
)
  
  variable_en_estudio(casen)
  
}

# carrera <- read_xlsx("C:/Users/enamo/Desktop/Shiny-R/ttcc_zoho/diccionarios/5/tabla 5.5.xlsx")
# # carrera <- carrera[-c(1:1),c(1,3)]
# carrera <- carrera[-c(1:1),c(3,4)]
# # names(carrera)[2] <- "Homologacion_002"
# carrera
# 
# #
# dataf1 <- data.frame()
# for (n in 1:nrow(carrera)) {
#   # dataf1 <- rbind(dataf1,paste0("dataset[,variable][dataset[,variable] ==  '",carrera[n,1],"']"," <- '",carrera[n,2],"'"))
#   dataf1 <- rbind(dataf1,paste0("dataset[,'cod_variable'][dataset[,'cod_variable'] ==  '",carrera[n,1],"']"," <- '",carrera[n,2],"'"))  # <- codigo numerico
# }
# dataf1 <- as.data.frame(dataf1)
# write_xlsx(dataf1,"el_total_final.xlsx")

0.0.1 2006

ab <- casen_2006

b <- ab$COMUNA
c <- ab[,c(vv[1])]
d <- ab$T4
e <- ab$SEXO
f <- ab$E1

cross_tab =  xtabs(ab$EXPC ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$EXPC ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2006"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2006 <- d

0.0.2 2009

ab <- casen_2009

b <- ab$COMUNA
c <- ab[,c(vv[2])]
d <- ab$T5
e <- ab$SEXO
f <- ab$E1

cross_tab =  xtabs(ab$EXPC ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$EXPC ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2009"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2009 <- d

0.0.3 2011

ab <- casen_2011

b <- ab$comuna
c <- ab[,c(vv[3])]
d <- ab$r6
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc_full ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc_full ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2011"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2011 <- d

0.0.4 2013

ab <- casen_2013

b <- ab$comuna
c <- ab[,c(vv[4])]
d <- ab$r6
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2013"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2013 <- d

0.0.5 2015

ab <- casen_2015

b <- ab$comuna
c <- ab[,c(vv[5])]
d <- ab$r3
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc_todas ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc_todas ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2015"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2015 <- d

0.0.6 2017

ab <- casen_2017

b <- ab$comuna
c <- ab[,c(vv[6])]
d <- ab$r3
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2017"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2017 <- d

0.0.7 2020

ab <- casen_2020

b <- ab$comuna
c <- ab[,c(vv[7])]
d <- ab$r3
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2020"
      
names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Etnia"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2020 <- d

Unimos y desplegamos la tabla corregida:

1 Tabla final etnia homologada

union_etnia <- rbind( d_2006,d_2009,d_2011,d_2013,d_2015, d_2017, d_2020)
union_etnia <- mutate_if(union_etnia, is.factor, as.character)

#fn_etnia(union)

cod_com <- readRDS("C:/Users/chris/Desktop/archivos grandes/codigos_comunales_2006-2020.rds") 







names(cod_com)[2] <- "comuna"
tab_f <- merge(x=union_etnia, y=cod_com, by="comuna") 








tab_f$cod_etnia[tab_f$Etnia == "Alacalufe" ]  <- "01"
tab_f$cod_etnia[tab_f$Etnia == "Atacameño" ]  <- "02"
tab_f$cod_etnia[tab_f$Etnia == "Aymara" ]  <- "03"
tab_f$cod_etnia[tab_f$Etnia == "Chango" ]  <- "04"
tab_f$cod_etnia[tab_f$Etnia == "Coya" ]  <- "05"
tab_f$cod_etnia[tab_f$Etnia == "Diaguita" ]  <- "06"
tab_f$cod_etnia[tab_f$Etnia == "Mapuche" ]  <- "07"
tab_f$cod_etnia[tab_f$Etnia == "Pascuense" ]  <- "08"
tab_f$cod_etnia[tab_f$Etnia == "Quechua" ]  <- "09" 
tab_f$cod_etnia[tab_f$Etnia == "Yagán" ]  <- "10"
tab_f$cod_etnia[tab_f$Etnia == "No pertenece a ningún pueblo indígena" ]  <- "11"
tab_f$cod_etnia[tab_f$Etnia == NA ]  <- "12"








tab_f$cod_sexo <- tab_f$Sexo
tab_f$cod_sexo[tab_f$cod_sexo == "Hombre"] <- "01"
tab_f$cod_sexo[tab_f$cod_sexo == "Mujer"] <- "02"

tab_f$cod_alfa <- tab_f$`Sabe leer?`
tab_f$cod_alfa[tab_f$cod_alfa == "Sí"] <- "01"
tab_f$cod_alfa[tab_f$cod_alfa == "No"] <- "02"


tab_f$cod_variable <- tab_f$variable
dataset <- tab_f

dataset[,'cod_variable'][dataset[,'cod_variable'] ==  'No'] <- '1'
dataset[,'cod_variable'][dataset[,'cod_variable'] ==  'No sabe o no responde'] <- '2'
dataset[,'cod_variable'][dataset[,'cod_variable'] ==  'No sabe o no responde'] <- '2'
dataset[,'cod_variable'][dataset[,'cod_variable'] ==  'No sabe o no responde'] <- '2'
dataset[,'cod_variable'][dataset[,'cod_variable'] ==  'No sabe o no responde'] <- '2'
dataset[,'cod_variable'][dataset[,'cod_variable'] ==  'Sí'] <- '3'




datatable(dataset, extensions = 'Buttons', escape = FALSE, rownames = FALSE,
          options = list(dom = 'Bfrtip',
          buttons = list('colvis', list(extend = 'collection',
          buttons = list(
          list(extend='copy'),
          list(extend='excel',
            filename = 'tabla'),
          list(extend='pdf',
            filename= 'tabla')),
          text = 'Download')), scrollX = TRUE))

2 MIGRA

2.0.1 2011

Generamos las tablas de contingencia tal como acostumbramos:

ab <- casen_2011

b <- ab$comuna
c <- ab[,c(vv[3])]
d <- ab$r2p_cod
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc_full ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc_full ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2011"

names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2011 <- d

2.0.2 2013

ab <- casen_2013

b <- ab$comuna
c <- ab[,c(vv[4])]
d <- ab$r2_p_cod 
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean)) 
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2013"

names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"
d_2013 <- d

2.0.3 2015

 ab <- casen_2015

b <- ab$comuna 
c <- ab[,c(vv[5])]
d <- ab$r2espp_cod 
e <- ab$sexo 
f <- ab$e1 

 cross_tab =  xtabs(ab$expc_todas ~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc_todas ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
 tabla <- as.data.frame(cross_tab)
 d <-tabla[!(tabla$Freq == 0),] 
 d$anio <- "2015"

names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año" 

 d_2015 <- d

2.0.4 2017

ab <- casen_2017

b <- ab$comuna
c <- ab[,c(vv[6])]
d <- ab$r2_p_cod
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2017"

names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2017 <- d

2.0.5 2020

ab <- casen_2020

b <- ab$comuna
c <- ab[,c(vv[7])]
d <- ab$r2_pais_esp
e <- ab$sexo
f <- ab$e1

cross_tab =  xtabs(ab$expc~   unlist(b) + unlist(c)  + unlist(d) + unlist(e)  + unlist(f),aggregate(ab$expc ~  unlist(b) + unlist(c) + unlist(d) + unlist(e) + unlist(f) ,ab,mean))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2020"

names(d)[1] <- "comuna"
names(d)[2] <- "variable"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2020 <- d