casen_2006 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2006_c.rds")
casen_2006 <- mutate_if(casen_2006, is.factor, as.character)
casen_2009 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2009_c.rds")
casen_2009 <- mutate_if(casen_2009, is.factor, as.character)
casen_2011 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2011_c.rds")
casen_2011 <- mutate_if(casen_2011, is.factor, as.character)
casen_2013 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2013_c.rds")
casen_2013 <- mutate_if(casen_2013, is.factor, as.character)
casen_2015 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2015_c.rds")
casen_2015 <- mutate_if(casen_2015, is.factor, as.character)
casen_2017 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2017_c.rds")
casen_2017 <- mutate_if(casen_2017, is.factor, as.character)
casen_2020 <- readRDS(file = "C:/Users/chris/OneDrive/Documentos/archivos_grandes/casen_2020_e1.rds")
casen_2020 <- mutate_if(casen_2020, is.factor, as.character)

casen_2006 <- casen_2006[,c("EXPC", "COMUNA","EDUC","T4","SEXO","E1")]
casen_2009 <- casen_2009[,c("EXPC", "COMUNA","EDUC","T5","SEXO","E1")]
casen_2011 <- casen_2011[,c("expc_full", "comuna","e6a","r6","sexo","e1","r2p_cod")]
casen_2013 <- casen_2013[,c("expc", "comuna","e6a","r6","sexo","e1","r2_p_cod")]
casen_2015 <- casen_2015[,c("expc_todas", "comuna","e6a","r3","sexo","e1","r2espp_cod")]
casen_2017 <- casen_2017[,c("expc", "comuna","e6a","r3","sexo","e1","r2_p_cod")]
casen_2020 <- casen_2020[,c("expc", "comuna","e6a","r3","sexo","e1","r2_pais_esp")]

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] == "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 

    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)
  
}

variable_alfa <- function(dataset){
    
variable <- switch(i,"E1","E1","e1","e1","e1","e1","e1")   
    
dataset[,variable][dataset[,variable] == "No sabe /Sin dato" ]  <- NA
dataset[,variable][dataset[,variable] == "Sí, lee y escribe" ]  <- "Sí"  
dataset[,variable][dataset[,variable] == "No, sólo lee" ]  <- "No"
dataset[,variable][dataset[,variable] == "No, ninguno" ]  <-"No"
dataset[,variable][dataset[,variable] == "No, sólo escribe" ]  <- "No"
#dataset_1 <<- 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 1:6) {
  
  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_alfa(casen)
}

variable_en_estudio <- function(dataset){
    
variable <- switch(i,"EDUC","EDUC","e6a","e6a","e6a","e6a","e6a")       
    
dataset[,variable][dataset[,variable]== 'BASICA COMPL.' ] <-    'basica'
dataset[,variable][dataset[,variable]== 'BASICA INCOM.' ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Básica Incompleta' ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Básica Completa'   ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Primaria/Preparatoria (sistema antiguo)'   ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Educación Básica'  ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Primaria o Preparatoria (Sistema Antiguo)' ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Primaria o Preparatoria (Sistema antiguo)' ] <-    'basica'
dataset[,variable][dataset[,variable]== 'Educación especial (diferencial)'  ] <-    'diferencial'
dataset[,variable][dataset[,variable]== 'Educación Especial (Diferencial)'  ] <-    'diferencial'
dataset[,variable][dataset[,variable]== 'Kinder/Pre-kinder' ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'Jardín infantil/Sala cuna' ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'Prekinder / Kinder (Transición menor y Transición Mayor)'  ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'Jardín Infantil (Medio menor y Medio mayor)'   ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'Sala cuna' ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'Prekinder/Kinder (Transición menor y Transición Mayor)'    ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'Prekínder / Kínder (Transición menor y Transición Mayor)'  ] <-    'kinder'
dataset[,variable][dataset[,variable]== 'M.HUM. INCOMPLETA' ] <-    'media'
dataset[,variable][dataset[,variable]== 'M.TEC COMPLETA'    ] <-    'media'
dataset[,variable][dataset[,variable]== 'M.TEC.PROF. INCOMPLETA'    ] <-    'media'
dataset[,variable][dataset[,variable]== 'M.HUM. COMPLETA'   ] <-    'media'
dataset[,variable][dataset[,variable]== 'Media Humanista Completa'  ] <-    'media'
dataset[,variable][dataset[,variable]== 'Media Humanista Incompleta'    ] <-    'media'
dataset[,variable][dataset[,variable]== 'Media Técnico Completa'    ] <-    'media'
dataset[,variable][dataset[,variable]== 'Media Técnico Profesional Incompleta'  ] <-    'media'
dataset[,variable][dataset[,variable]== 'Humanidades (sistema antiguo)' ] <-    'media'
dataset[,variable][dataset[,variable]== 'Educación Media Científico-Humanista'  ] <-    'media'
dataset[,variable][dataset[,variable]== 'Educación Media Técnica Profesional'   ] <-    'media'
dataset[,variable][dataset[,variable]== 'Humanidades (Sistema Antiguo)' ] <-    'media'
dataset[,variable][dataset[,variable]== ''  ] <-    'NA'
dataset[,variable][dataset[,variable]== 'SIN EDUC. FORMAL'  ] <-    'NA'
dataset[,variable][dataset[,variable]== 'SIN DATO'  ] <-    'NA'
dataset[,variable][dataset[,variable]== 'Sin Educación Formal'  ] <-    'NA'
dataset[,variable][dataset[,variable]== 'Nunca asistió' ] <-    'NA'
dataset[,variable][dataset[,variable]== 'NS/NR' ] <-    'NA'
dataset[,variable][dataset[,variable]== 'sin dato'  ] <-    'NA'
dataset[,variable][dataset[,variable]== 'No sabe/no responde'   ] <-    'NA'
dataset[,variable][dataset[,variable]== 'TECNICA  O UNIV. COMPLETA' ] <-    'superior'
dataset[,variable][dataset[,variable]== 'TEC. O UNIV.  INCOMPLETA.' ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnica o Universitaria Completa'  ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnica ó Universitaria Incompleta'    ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Profesional'   ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnico Nivel Superior'    ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Postgrado' ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnica, Comercial, Industrial o Normalista'   ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnico Nivel Superior (carreras de 1 a 3 años)'   ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Profesional (carreras de 4 o más años)'    ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnica, Comercial, Industrial o Normalista (sistema antiguo)' ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Profesional Completo (Carreras 4 ó más años)'  ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnico Nivel Superior Completo (Carreras 1 a 3 años)' ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Profesional Incompleto (Carreras 4 ó más años)'    ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnica, Comercial, Industrial o Normalista (Sistema Antiguo'  ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnico Nivel Superior Incompleto (Carreras 1 a 3 años)'   ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Postgrado Completo'    ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Postgrado Incompleto'  ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Profesional Incompleto (Carreras 4  o más años)'   ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Profesional Completo (Carreras 4 o más años)'  ] <-    'superior'
dataset[,variable][dataset[,variable]== 'Técnica Comercial, Industrial o Normalista (Sistema Antiguo)'  ] <-    'superior'


  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)
}

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"

ab <- casen_2011

b <- ab$comuna
c <- ab$e6a
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] <- "Estudios"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2011 <- d

ab <- casen_2013

b <- ab$comuna
c <- ab$e6a
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] <- "Estudios"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"
d_2013 <- d

 ab <- casen_2015

b <- ab$comuna 
c <- ab$e6a 
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] <- "Estudios" 
 names(d)[3] <- "Origen" 
 names(d)[4] <- "Sexo" 
 names(d)[5] <- "Sabe leer?" 
 names(d)[6] <- "Frecuencia" 
 names(d)[7] <- "Año" 

 d_2015 <- d 

ab <- casen_2017

b <- ab$comuna
c <- ab$e6a
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] <- "Estudios"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"

d_2017 <- d

ab <- casen_2020

b <- ab$comuna
c <- ab$e6a
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] <- "Estudios"
names(d)[3] <- "Origen"
names(d)[4] <- "Sexo"
names(d)[5] <- "Sabe leer?"
names(d)[6] <- "Frecuencia"
names(d)[7] <- "Año"
d_2020 <- d