date: 23-09-2021

1 Introducción

El procedimiento de generación de tablas de contingencia trae problemas si se consideran varias tablas referidas por ejemplo a varios años, cuyas categorías de divergen.

Se intenta extraer todo tipo de subjetividad.

1.1 Aca se extraen solo las categorias unicas de cada año:

r1a_cod. ¿Cuál es esa otra nacionalidad? (código país)

Ésta pregunta sólo se comenzó a aplicar en la Casen del 2011 y hasta la versión 2017

casen_2006 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2006_c.rds")
casen_2006 <- mutate_if(casen_2006, is.factor, as.character)
casen_2009 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2009_c.rds")
casen_2009 <- mutate_if(casen_2009, is.factor, as.character)
casen_2011 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2011_c.rds")
casen_2011 <- mutate_if(casen_2011, is.factor, as.character)
casen_2013 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2013_c.rds")
casen_2013 <- mutate_if(casen_2013, is.factor, as.character)
casen_2015 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2015_c.rds")
casen_2015 <- mutate_if(casen_2015, is.factor, as.character)
casen_2017 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2017_c.rds")
casen_2017 <- mutate_if(casen_2017, is.factor, as.character)
casen_2020 <<- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/casen/casen_2020.rds")
casen_2020 <- mutate_if(casen_2020, is.factor, as.character)

cod_com <- readRDS("C:/Users/enamo/Desktop/Shiny-R/Casen_en_pandemia_2020/codigos_comunales_2006-2020.rds") 
names(cod_com)[2] <- "comuna"

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"

Homologación de etnia

fn_etnia <- function(union){
union$Etnia[union$Etnia == "Aimara" ]  <- "Aymara"
union$Etnia[union$Etnia == "No pertenece a ninguno de estos pueblos indígenas" ]  <-  "No pertenece a ningún pueblo indígena" 
union$Etnia[union$Etnia == "Mapuche"]  <- "Mapuche"
union$Etnia[union$Etnia == "Diaguita"]  <- "Diaguita"
union$Etnia[union$Etnia == "Atacameño" ]  <- "Atacameño"
union$Etnia[union$Etnia == "Atacameño (Likan-Antai)" ]  <- "Atacameño"
union$Etnia[union$Etnia == "Atacameño (Likán Antai)" ]  <- "Atacameño"
union$Etnia[union$Etnia == "Atacameño (Likán-Antai)" ]  <- "Atacameño"
union$Etnia[union$Etnia == "Quechua" ]  <- "Quechua"
union$Etnia[union$Etnia == "Yámana o Yagán" ]  <- "Yagán"
union$Etnia[union$Etnia == "Yagan" ]  <- "Yagán"
union$Etnia[union$Etnia == "Yagán (Yámana)" ]  <- "Yagán"
union$Etnia[union$Etnia == "Rapa-Nui o Pascuenses"]  <- "Pascuense"
union$Etnia[union$Etnia == "Rapa-Nui"]  <- "Pascuense"
union$Etnia[union$Etnia == "Rapa Nui (Pascuense)"]  <- "Pascuense"
union$Etnia[union$Etnia == "Rapa Nui"]  <- "Pascuense"
union$Etnia[union$Etnia == "Collas"]  <- "Coya"
union$Etnia[union$Etnia == "Kawashkar o Alacalufes" ]  <- "Alacalufe"
union$Etnia[union$Etnia == "Kawashkar" ]  <- "Alacalufe"
union$Etnia[union$Etnia == "Kawésqar (Alacalufes)" ]  <- "Alacalufe"
union$Etnia[union$Etnia == "Kawésqar" ]  <- "Alacalufe"
union$Etnia[union$Etnia == "Kawaskar" ]  <- "Alacalufe"
union$Etnia[union$Etnia == "Chango" ]  <- "Chango"
union$Etnia[union$Etnia ==  "Sin dato"]  <- NA
union$Etnia[union$Etnia ==  "NS/NR"   ]  <- NA
union$Etnia[union$Etnia == "No sabe/no responde" ]  <- NA 

union <<- union
}

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

1.2 Se obtiene el universo de categorías para r1a_cod cada año

ab <- casen_2011
unique_d_2011 <- unique(ab$h11e_esp)
 
ab <- casen_2013
unique_d_2013 <- unique(ab$r1a_cod)
 
ab <- casen_2015
unique_d_2015 <- unique(ab$r1aesp_cod)
 
ab <- casen_2017
unique_d_2017 <- unique(ab$r1a_cod)

2 Diccionario

Se unen todas las categorías de respuesta, se excluyen las repetidas y se les asocia un código:

unique_d_2011 <- as.data.frame(unique_d_2011)
colnames(unique_d_2011)[1] <- "superduper"
unique_d_2013 <- as.data.frame(unique_d_2013)
colnames(unique_d_2013)[1] <- "superduper"
unique_d_2015 <- as.data.frame(unique_d_2015)
colnames(unique_d_2015)[1] <- "superduper"
unique_d_2017 <- as.data.frame(unique_d_2017)
colnames(unique_d_2017)[1] <- "superduper" 
 
el_total <- rbind( unique_d_2011, unique_d_2013, unique_d_2015, unique_d_2017 )
 
el_total_final <- unique(el_total) 
 
el_total_final$observation <- 1:nrow(el_total_final) 
datatable(el_total_final, 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_Diccionario'),
          list(extend='pdf',
            filename= 'tabla_Diccionario')),
          text = 'Download')), scrollX = TRUE))

dataf1 <- data.frame()
for (n in 1:nrow(el_total_final)) { 
  dataf1 <- rbind(dataf1,paste0("m['r1a_cod'][m['r1a_cod'] ==  '",el_total_final[n,1],"']"," <- '",el_total_final[n,2],"'"))
}
dataf1 <- as.data.frame(dataf1)
write_xlsx(dataf1,"el_total_final.xlsx")
 
la_correccion <- function(m) {

m['r1a_cod'][m['r1a_cod'] ==  'NA'] <- '1'
m['r1a_cod'][m['r1a_cod'] ==  'Ecuador'] <- '2'
m['r1a_cod'][m['r1a_cod'] ==  'Argentina'] <- '3'
m['r1a_cod'][m['r1a_cod'] ==  'Perú'] <- '4'
m['r1a_cod'][m['r1a_cod'] ==  'Bolivia'] <- '5'
m['r1a_cod'][m['r1a_cod'] ==  'Colombia'] <- '6'
m['r1a_cod'][m['r1a_cod'] ==  'Brasil'] <- '7'
m['r1a_cod'][m['r1a_cod'] ==  'No bien especificado'] <- '8'
m['r1a_cod'][m['r1a_cod'] ==  'Marruecos'] <- '9'
m['r1a_cod'][m['r1a_cod'] ==  'Paraguay'] <- '10'
m['r1a_cod'][m['r1a_cod'] ==  'Alemania'] <- '11'
m['r1a_cod'][m['r1a_cod'] ==  'Uruguay'] <- '12'
m['r1a_cod'][m['r1a_cod'] ==  'Guatemala'] <- '13'
m['r1a_cod'][m['r1a_cod'] ==  'Venezuela'] <- '14'
m['r1a_cod'][m['r1a_cod'] ==  'República Dominicana'] <- '15'
m['r1a_cod'][m['r1a_cod'] ==  'México'] <- '16'
m['r1a_cod'][m['r1a_cod'] ==  'Holanda'] <- '17'
m['r1a_cod'][m['r1a_cod'] ==  'Estados Unidos'] <- '18'
m['r1a_cod'][m['r1a_cod'] ==  'No contesta'] <- '19'
m['r1a_cod'][m['r1a_cod'] ==  'España'] <- '20'
m['r1a_cod'][m['r1a_cod'] ==  'Costa Rica'] <- '21'
m['r1a_cod'][m['r1a_cod'] ==  'Francia'] <- '22'
m['r1a_cod'][m['r1a_cod'] ==  'Canadá'] <- '23'
m['r1a_cod'][m['r1a_cod'] ==  'Japón'] <- '24'
m['r1a_cod'][m['r1a_cod'] ==  'Italia'] <- '25'
m['r1a_cod'][m['r1a_cod'] ==  'Bélgica'] <- '26'
m['r1a_cod'][m['r1a_cod'] ==  'Noruega'] <- '27'
m['r1a_cod'][m['r1a_cod'] ==  'Suiza'] <- '28'
m['r1a_cod'][m['r1a_cod'] ==  'Rumanía'] <- '29'
m['r1a_cod'][m['r1a_cod'] ==  'Cuba'] <- '30'
m['r1a_cod'][m['r1a_cod'] ==  'Honduras'] <- '31'
m['r1a_cod'][m['r1a_cod'] ==  'Rusia'] <- '32'
m['r1a_cod'][m['r1a_cod'] ==  'Hungría'] <- '33'
m['r1a_cod'][m['r1a_cod'] ==  'India'] <- '34'
m['r1a_cod'][m['r1a_cod'] ==  'Filipinas'] <- '35'
m['r1a_cod'][m['r1a_cod'] ==  'Pakistán'] <- '36'
m['r1a_cod'][m['r1a_cod'] ==  'China'] <- '37'
m['r1a_cod'][m['r1a_cod'] ==  'Indonesia'] <- '38'
m['r1a_cod'][m['r1a_cod'] ==  'Panamá'] <- '39'
m['r1a_cod'][m['r1a_cod'] ==  'Otro país de Europa'] <- '40'
m['r1a_cod'][m['r1a_cod'] ==  'Otro país de Asia'] <- '41'
m['r1a_cod'][m['r1a_cod'] ==  'Reino Unido'] <- '42'
m['r1a_cod'][m['r1a_cod'] ==  'Irlanda'] <- '43'
m['r1a_cod'][m['r1a_cod'] ==  'Australia'] <- '44'
m['r1a_cod'][m['r1a_cod'] ==  'Austria'] <- '45'
m['r1a_cod'][m['r1a_cod'] ==  'Polonia'] <- '46'
m['r1a_cod'][m['r1a_cod'] ==  'Haití'] <- '47'
m['r1a_cod'][m['r1a_cod'] ==  'El Salvador'] <- '48'
m['r1a_cod'][m['r1a_cod'] ==  'Libia'] <- '49'
m['r1a_cod'][m['r1a_cod'] ==  'Kenia'] <- '50'
m['r1a_cod'][m['r1a_cod'] ==  'Grecia'] <- '51'
m['r1a_cod'][m['r1a_cod'] ==  'Eslovenia'] <- '52'
m['r1a_cod'][m['r1a_cod'] ==  'Suecia'] <- '53'
m['r1a_cod'][m['r1a_cod'] ==  'Siria'] <- '54'
m['r1a_cod'][m['r1a_cod'] ==  'Portugal'] <- '55'
m['r1a_cod'][m['r1a_cod'] ==  'Serbia'] <- '56'
m['r1a_cod'][m['r1a_cod'] ==  'Líbano'] <- '57'
m['r1a_cod'][m['r1a_cod'] ==  'Ucrania'] <- '58'
m['r1a_cod'][m['r1a_cod'] ==  'Otro país de Africa'] <- '59'
m['r1a_cod'][m['r1a_cod'] ==  'Tailandia'] <- '60'
m['r1a_cod'][m['r1a_cod'] ==  'Nicaragua'] <- '61'
m['r1a_cod'][m['r1a_cod'] ==  'Puerto Rico'] <- '62'
m['r1a_cod'][m['r1a_cod'] ==  'Corea del Sur'] <- '63'
m['r1a_cod'][m['r1a_cod'] ==  'Kirguistán'] <- '64'
m['r1a_cod'][m['r1a_cod'] ==  'Nueva Zelanda'] <- '65'
m['r1a_cod'][m['r1a_cod'] ==  'Turquía'] <- '66'
m['r1a_cod'][m['r1a_cod'] ==  'Croacia'] <- '67'
m['r1a_cod'][m['r1a_cod'] ==  'Israel'] <- '68'
m['r1a_cod'][m['r1a_cod'] ==  'Jordania'] <- '69'
m['r1a_cod'][m['r1a_cod'] ==  'Albania'] <- '70'
m['r1a_cod'][m['r1a_cod'] ==  'Qatar'] <- '71'
m['r1a_cod'][m['r1a_cod'] ==  'Lituania'] <- '72'
m['r1a_cod'][m['r1a_cod'] ==  'Dinamarca'] <- '73'
m['r1a_cod'][m['r1a_cod'] ==  'Argelia'] <- '74'
m['r1a_cod'][m['r1a_cod'] ==  'Angola'] <- '75'
m['r1a_cod'][m['r1a_cod'] ==  'Egipto'] <- '76'
m['r1a_cod'][m['r1a_cod'] ==  'República Checa'] <- '77'
m['r1a_cod'][m['r1a_cod'] ==  'Eslovaquia'] <- '78'
m['r1a_cod'][m['r1a_cod'] ==  'Etiopía'] <- '79'
m['r1a_cod'][m['r1a_cod'] ==  'No Responde'] <- '80'
m['r1a_cod'][m['r1a_cod'] ==  'República Democrática Del Congo'] <- '81'
m['r1a_cod'][m['r1a_cod'] ==  'Palestina'] <- '82'
m['r1a_cod'][m['r1a_cod'] ==  'Sri Lanka'] <- '83'
m['r1a_cod'][m['r1a_cod'] ==  'No Bien Especificado'] <- '84'
m['r1a_cod'][m['r1a_cod'] ==  'Sudáfrica'] <- '85'
m['r1a_cod'][m['r1a_cod'] ==  'Corea Del Sur'] <- '86'
m['r1a_cod'][m['r1a_cod'] ==  'Finlandia'] <- '87'
m['r1a_cod'][m['r1a_cod'] ==  'Nigeria'] <- '88'
m['r1a_cod'][m['r1a_cod'] ==  'Ghana'] <- '89'


 
mm <<- m 
}

3 Etnia