Estudio de la palabra del día con tildes

Este cuaderno visualiza los patrones que siguen la palabra del día de tildes

Cargar librerías

if(!"tidyverse" %in% installed.packages()) {install.packages("tidyverse")}
if(!"koRpus" %in% installed.packages()) {install.packages("koRpus")}
if (!"koRpus.lang.es" %in% installed.packages()) {install.packages("koRpus.lang.es", repos="https://undocumeantit.github.io/repos/l10n/")}
library("tidyverse")
library("koRpus")
library("koRpus.lang.es")
library("sylly.es")
library(ggtext)          # Dar color a los textos de las leyendas

locale(date_names = "es", date_format = "%AD", time_format = "%AT",
  decimal_mark = ",", grouping_mark = ".", tz = "Europe/Berlin",
  encoding = "UTF-8", asciify = FALSE)

## <locale>
## Numbers:  123.456,78
## Formats:  %AD / %AT
## Timezone: Europe/Berlin
## Encoding: UTF-8
## <date_names>
## Days:   domingo (dom.), lunes (lun.), martes (mar.), miércoles (mié.), jueves
##         (jue.), viernes (vie.), sábado (sáb.)
## Months: enero (ene.), febrero (feb.), marzo (mar.), abril (abr.), mayo (may.),
##         junio (jun.), julio (jul.), agosto (ago.), septiembre (sept.),
##         octubre (oct.), noviembre (nov.), diciembre (dic.)
## AM/PM:  a. m./p. m.

Sys.setlocale(category = "LC_ALL", locale = "spanish")

## [1] "LC_COLLATE=Spanish_Spain.1252;LC_CTYPE=Spanish_Spain.1252;LC_MONETARY=Spanish_Spain.1252;LC_NUMERIC=C;LC_TIME=Spanish_Spain.1252"

Plantilla diseño

my_theme <- function(
  base_size = 11,
  base_color = "#5a5856",
  base_family = "sans"
  )
{
  # Establecemos la proporción del tamaño de la letra de cada uno de los elementos
  template <- 
    theme_bw(base_size=base_size, base_family = base_family) +
    theme(
      panel.border = element_rect(colour = base_color),
      panel.grid.major = element_blank(),
      panel.grid.minor = element_blank(),
      plot.title = element_text(
        size = base_size+2,
        face = "bold",
        color = base_color,
        vjust = 1.25, 
        hjust = 0.5),
      plot.subtitle = element_text(size=base_size + 2, color = base_color, hjust = 0.5),
      plot.caption = element_text(hjust = 1, size=base_size - 1, color = base_color),
      legend.position ="top",
      legend.margin =  margin(0,0,0,0,unit="pt"),
      legend.text = element_text(size=base_size + 1),
      text = element_text(size=base_size, color = base_color),
      axis.title.x = element_text(
        size=base_size + 1,
        vjust=0,
        color = base_color,
        margin = unit(c(3, 0, 0, 0), "mm")
      ),
      axis.title.y = element_text(
        size=base_size + 1, 
        vjust=1.25,
        color = base_color,
        margin = unit(c(0, 3, 0, 0), "mm")
      ),
      axis.title.y.right=element_text(
        size=base_size + 1,
        color = base_color,
        margin = unit(c(0, 0, 0, 3), "mm")
      ),
      axis.text.x = element_text(size=base_size - 1, color = base_color),
      axis.text.y = element_text(size=base_size-1,color = base_color),
      strip.text = element_text(size=base_size + 2, color = base_color),
      strip.text.x = element_text(size=base_size + 1, color = base_color),
      strip.text.y = element_text(size=base_size + 1, color = base_color),
      strip.background = element_rect(color = NA, fill = NA)
    )
  return(template)
}

Leer y preparar datos

url_palabras_tilde <-  "https://raw.githubusercontent.com/congosto/congosto.github.io/master/datos/tildes.txt"
palabras_tilde <- read_csv (url_palabras_tilde ) %>%
  # trabajar con minúsculas
  mutate (palabras_con_tilde = tolower(palabras_con_tilde)) %>%
  mutate(silabas = hyphen(palabras_con_tilde, hyph.pattern = "es",quiet = TRUE)@hyphen$word) %>%
  # corregir hiato simple que lo hace mal la librería
  mutate (silabas = gsub("([a | e | o])([a | e | o])", "\\1-\\2", silabas)) %>%
  # corregir Hiato acentual que lo hace mal la librería
  mutate (silabas = gsub("([í | ú ])([a | e | o])", "\\1-\\2", silabas)) %>%
  mutate (silabas = gsub("([a | e | o])([í | ú ])", "\\1-\\2", silabas)) %>%
  # corregir palabras que empiezan por vocal que lo hace mal la librería
  mutate (silabas = gsub("([aeiouáéíóú])([bcdfghjklmnpqrstvwxyz])([aeiouáéíóú])","\\1-\\2\\3", silabas)) %>%
  # calcular número de sílabas
  mutate(num_silabas = str_count(silabas, "-") + 1) %>%
  # calcular número de letras
  mutate(num_letras = nchar(palabras_con_tilde)) %>%
  # Obtenerla tilde
  mutate(tilde = str_extract(silabas, "[á|é|í|ó|ú]")) %>%
  # calcular cuantas silabas tiene por delante de la tilde
  mutate(silaba_tilde = str_extract(silabas, "[á|é|í|ó|ú].*")) %>%
  mutate(num_silabas_post_tilde = str_count(silaba_tilde, "-") + 1) %>%
  mutate(tipo_acentuacion = case_when(
    grepl("([í | ú ])([a | e | o])", palabras_con_tilde) ~ "Hiato acentual",
    grepl("([a | e | o])([í | ú ])", palabras_con_tilde)  ~ "Hiato acentual",
    grepl("ón$", palabras_con_tilde)  ~ "Terminación ón"
  ) ) %>%
  mutate(tipo_acentuacion = ifelse(is.na(tipo_acentuacion),"Otros", tipo_acentuacion)) %>%
  # Calcular el tipo de acento
  mutate(acentuacion =  case_when(
    num_silabas_post_tilde == 1 ~ "Aguda",
    num_silabas_post_tilde == 2 ~ "Llana",
    num_silabas_post_tilde >= 3 ~ "Esdrújula"
  ) ) %>%
  #Añadir orden de la palabra
  rownames_to_column() %>%
  rename ("orden" = "rowname") %>%
  mutate ("orden" = as.numeric(orden)) %>%
  # Contar cuantas palabras hay de cada longitud
  group_by(num_letras) %>%
  mutate (total_num_letras = n()) %>%
  ungroup()
# ordenar por acentuación
orden_acentuacion <- c("Esdrújula","Llana","Aguda")
palabras_tilde$acentuacion <- factor(palabras_tilde$acentuacion, levels = orden_acentuacion )
# ordenar el tipo de acento
orden_tipo_acentuacion <- c("Hiato acentual","Terminación ón", "Otros")
palabras_tilde$tipo_acentuacion <- factor(palabras_tilde$tipo_acentuacion, levels = orden_tipo_acentuacion )

Tildes vs. número de letras

tilde  <- palabras_tilde %>%
  group_by (tilde, num_letras) %>%
  summarise(
    n = n(),
    percent = round (n / total_num_letras * 100, 1)
  ) %>%
  ungroup() %>% 
  distinct (tilde, num_letras,percent) %>%
  complete(tilde, num_letras) %>%
  mutate(percent = ifelse(is.na(percent), 0, percent))

ggplot(data = tilde) +
  geom_tile(
    aes(
      x = tilde, y = as.character(num_letras),
      fill = percent
    ),
    color = "white"
  ) +
  geom_label(
    aes(
      x = tilde, y = as.character(num_letras),
      label = paste0(percent, "%")
    ),
    color = "#5a5856",
    label.size = 0
  ) +
  scale_x_discrete(
    expand =  c(0, 0),
    position = "top"
  ) +
  scale_y_discrete(expand =  c(0, 0)) +
  scale_fill_gradient(
    na.value = "grey90",
    low = "#DDEAFA",
    high = "#036DFA",
    guide = guide_legend()
  ) +
  labs(
    title = "Tildes vs. Número de letras",
    x = "",
    y = "Número de letras",
    color = "% Casos"
  ) +
  coord_fixed() +
  my_theme() +
  theme(
    legend.position = "None",
    panel.background = element_rect(fill = "grey90", color = "grey50")
  )

Acentuación vs. múmero de letras

acentuacion  <- palabras_tilde %>%
  group_by (acentuacion, num_letras) %>%
  summarise(
    n = n(),
    percent = round (n / total_num_letras  * 100, 1),
  ) %>%
  ungroup() %>% 
  distinct (acentuacion, num_letras,percent) %>%
  complete(acentuacion, num_letras) %>%
  mutate(percent = ifelse(is.na(percent), 0, percent))

ggplot(data = acentuacion) +
  geom_tile(
    aes(
      x = acentuacion, y = as.character(num_letras),
      fill = percent
    ),
    color = "white"
  ) +
  geom_label(
    aes(
      x = acentuacion, y = as.character(num_letras),
      label = paste0(percent,"%")
    ),
    color = "#5a5856",
    label.size = 0
  ) +
  scale_x_discrete(
      expand =  c(0,0),
      position = "top"
  ) +
  scale_y_discrete(expand =  c(0, 0)) +
  scale_fill_gradient(
    low = "#DDEAFA",
    high = "#036DFA",
    guide = guide_legend()
  ) +
  labs(
    title = "Acentuación vs. Número de letras",
    x = "",
    y = "Número de letras",
    color = "% Casos"
  ) +
  coord_fixed() +
  my_theme() +
  theme(
    legend.position = "None",
  )

Hiato acentual y terminación “ón” vs. múmero de letras

hiato_on  <- palabras_tilde %>%
  group_by (tipo_acentuacion, num_letras) %>%
  summarise(
    n = n(),
    percent = round (n / total_num_letras  * 100, 1),
  ) %>%
  ungroup() %>% 
  distinct (tipo_acentuacion, num_letras,percent) %>%
  complete(tipo_acentuacion, num_letras) %>%
  mutate(percent = ifelse(is.na(percent), 0, percent))

ggplot(data = hiato_on) +
  geom_tile(
    aes(
      x = tipo_acentuacion, y = as.character(num_letras),
      fill = percent
    ),
    color = "white") +
  geom_label(
    aes(
      x = tipo_acentuacion, y = as.character(num_letras),
      label = paste0(percent, "%")
    ),
    color = "#5a5856",
    label.size = 0
   ) +
  scale_x_discrete(
      expand =  c(0, 0),
      position = "top"
  ) +
  scale_y_discrete(expand =  c(0, 0)) +
  scale_fill_gradient(
    low = "#DDEAFA",
    high = "#036DFA",
    guide = guide_legend()
  ) +
  labs(
    title = 'Hiato acentual y terminación "ón" vs. múmero de letras',
    x = "",
    y = "Número de letras",
    color = "% Casos"
  ) +
  coord_fixed() +
  my_theme() +
  theme(
    legend.position="None"
  )

Patrón de tildes

color_tildes <- c("á" = "blue", "é" = "darkgreen", "í" = "darkred", "ó" = "orange", "ú" = "purple")
orden_tildes <- c("á","é","í","ó","ú")
df <- palabras_tilde %>%
 distinct (orden, num_letras, tilde) %>%
 complete(orden, num_letras)  

ggplot(data = df) +
  geom_tile(
    aes(x = as.character(orden), y = as.character(num_letras)),
    show.legend = FALSE,
    fill = "white",
    color = "grey"
  ) +
  geom_text(
    aes(
      x = orden, y = as.character(num_letras),
      label = tilde,
      color = tilde
    ),
    show.legend = FALSE
  ) +
  scale_x_discrete(
      expand =  c(0, 0),
      position = "top"
  ) +
  scale_y_discrete(expand =  c(0, 0)) +
  scale_color_manual(
    values = color_tildes,
    na.value = "white"
  ) +
  labs(
    title = "Patrón de tildes",
    x = "",
    y = "N. de letras"
  ) +
  coord_fixed(ratio = 2) +
  my_theme() +
  theme(
    axis.text.x = element_blank(),
    axis.ticks = element_blank(),
    legend.text = element_markdown(size = 9),
    legend.key.width = unit(0.2, "cm"),
    legend.key.height= unit(0.2, "cm")
  ) 

Patrón de acentuación

color_acentos <- c("Esdrújula" = "blue", "Llana" = "darkgreen", "Aguda" = "darkred")
df <- palabras_tilde %>%
 distinct (orden, num_letras, acentuacion) %>%
 complete(orden, num_letras)  

ggplot(data = df) +
  geom_tile(
    aes(
      x = as.character(orden), y = as.character(num_letras),
      fill = acentuacion
    ),
    color = "grey",
    alpha = 0.5
  ) +
  scale_x_discrete(
      expand =  c(0, 0),
      position = "top"
  ) +
  scale_y_discrete(expand =  c(0, 0)) +
  scale_fill_manual(
    values = color_acentos,
    labels = paste(
        "<span style='color:",
        color_acentos,
        "'>",
        orden_acentuacion,
        "</span>"), 
    na.value = "white",
    drop = FALSE
  ) +
  labs(
    title = "Patrón de acentuación",
    x = "",
    y = "N. de letras",
    fill = "Acentuación") +
  coord_fixed(ratio = 2) +
  my_theme() +
  theme(
    axis.text.x = element_blank(),
    axis.ticks = element_blank(),
    legend.text = element_markdown(size = 9),
    legend.key.width = unit(0.2, "cm"),
    legend.key.height= unit(0.2, "cm")
  ) 

Patrón hiato acentual y terminación “ón”

color_tipo_acentos <- c("Hiato acentual" = "blue", "Terminación ón" = "darkgreen", "Otros" = "grey50")

df <- palabras_tilde %>%
 distinct (orden, num_letras, tipo_acentuacion) %>%
 complete(orden, num_letras)  

ggplot(data = df) +
  geom_tile(
    aes(
      x = as.character(orden), y = as.character(num_letras),
      fill = tipo_acentuacion
    ),
    color = "grey",
    alpha = 0.7
  ) +
  scale_x_discrete(
      expand =  c(0, 0),
      position = "top"
  ) +
  scale_y_discrete(expand =  c(0, 0)) +
  scale_fill_manual(
    values = color_tipo_acentos,
    labels = paste(
        "<span style='color:",
        color_tipo_acentos,
        "'>",
        orden_tipo_acentuacion,
        "</span>"), 
    na.value = "white",
    drop = FALSE
  ) +
  labs(
    title = 'Patrón hiato acentual y terminación "ón"',
    x = "",
    y = "N. de letras",
    fill = "Tipo de Acentuación") +
  coord_fixed(ratio = 2) +
  my_theme() +
  theme(
    axis.text.x = element_blank(),
    axis.ticks = element_blank(),
    legend.text=element_markdown(size=9),
    legend.key.width = unit(0.2,"cm"),
    legend.key.height= unit(0.2,"cm")
  )