In jmss70/dispocen: Analysis of disponibility lexical tests

pag 12

install.packages("devtools")
library(devtools)
install_github("jmss70/dispocen")

pag 13

library(dispocen)

set_flextable_defaults(fonts_ignore=TRUE)

data <- read.dispocen("datos.txt")
data %>%
  head() %>%
  flextable() %>% autofit() %>%
  theme_booktabs()

pag 14

disponibilidad <- build.lopezstrass.availability(data)

head(disponibilidad) %>%
  flextable() %>%
  set_header_labels(centers = "Centro de interés",
                    words = "Palabra",
                    order = "Orden",
                    availability = "Disponibilidad",
                    freq.abs = "Frecuencia absoluta",
                    freq.abs.cum = "Frecuencia absoluta acumulada",
                    freq.rel = "Frecuencia relativa",
                    freq.rel.cum = "Frecuencia relativa acumulada") %>%
  colformat_double(j=c(4,6,8), digits=6) %>%
  width(j=c(1,3,5,7), width=.65) %>%
  width(j=c(2,4,6,8), width=.9) %>%
  theme_booktabs()

pag 15

disponibilidad %>%
  filter(centers=="03") %>%
  arrange(-availability) %>%
  head(10) %>%
  flextable() %>%
  set_header_labels(centers = "Centro de interés",
                    words = "Palabra",
                    order = "Orden",
                    availability = "Disponibilidad",
                    freq.abs = "Frecuencia absoluta",
                    freq.abs.cum = "Frecuencia absoluta acumulada",
                    freq.rel = "Frecuencia relativa",
                    freq.rel.cum = "Frecuencia relativa acumulada") %>%
  colformat_double(j=c(4,6,8), digits=6) %>%
  width(j=c(1,3,5,7), width=.65) %>%
  width(j=c(2,4,6,8), width=.9) %>%
  theme_booktabs()

pag 16

disponibilidad %>%
  filter(centers == "03") %>%
  arrange(-availability) %>%
  ggplot(aes(x=order, y=availability)) + geom_line() +
  xlab("Sucesión de palabras") + ylab("Disponibilidad")

pag 17

disponibilidad <- build.avilasanchez.availability(data)

disponibilidad %>%
  filter(centers=="03") %>%
  arrange(-availability) %>%
  head(10) %>%
  flextable() %>%
  set_header_labels(centers = "Centro de interés",
                    words = "Palabra",
                    order = "Orden",
                    availability = "Disponibilidad",
                    freq.abs = "Frecuencia absoluta",
                    freq.abs.cum = "Frecuencia absoluta acumulada",
                    freq.rel = "Frecuencia relativa",
                    freq.rel.cum = "Frecuencia relativa acumulada") %>%
  colformat_double(j=c(4,6,8), digits=6) %>%
  width(j=c(1,3,5,7), width=.65) %>%
  width(j=c(2,4,6,8), width=.9) %>%
  theme_booktabs()

pag 18

disponibilidad %>%
  filter(centers=="03") %>%
  arrange(-availability) %>%
  ggplot(aes(x=order, y=availability)) + geom_line() +
  xlab("Sucesión de palabras") + ylab("Disponibilidad")

pag 19-20

disponibilidad <- build.avilasanchez.availability(data, k = 0.1)

disponibilidad %>%
  filter(centers == "03") %>%
  arrange(-availability) %>%
  ggplot(aes(x=order, y=availability)) + geom_line() +
  xlab("Sucesión de palabras") + ylab("Disponibilidad")

disponibilidad <- build.avilasanchez.availability(data, k = 2)

disponibilidad %>%
  filter(centers=="03") %>%
  arrange(-availability) %>%
  ggplot(aes(x=seq_along(availability), y=availability)) + geom_line() +
  xlab("Sucesión de palabras") + ylab("Disponibilidad")

pag 21

disponibilidad <- build.avilasanchez.availability(data)
levels <- classify.availability.levels(disponibilidad)
levels %>%
  head(20) %>%
  arrange(-availability) %>%
  select(-order) %>%
  flextable() %>%
  set_header_labels(centers = "Centro de interés",
                    words = "Palabra",
                    availability = "Disponibilidad",
                    level = "Nivel de disponibilidad",
                    cutlevel = "Nivel de corte",
                    freq.abs = "Frecuencia absoluta",
                    freq.abs.cum = "Frecuencia absoluta acumulada",
                    freq.rel = "Frecuencia relativa",
                    freq.rel.cum = "Frecuencia relativa acumulada") %>%
   colformat_double(j=c(5,7,9), digits=5) %>%
   width(j=c(1,4,6,8), width=.65) %>%
   width(j=c(2,3,5,6,7,9), width=.75) %>%
   theme_booktabs()

pag 22

levels %>%
  filter(centers=="01") %>%
  arrange(-availability) %>%
  filter(level > 0) %>%
  select(-order) %>%
  flextable() %>%
  set_header_labels(centers = "Centro de interés",
                    words = "Palabra",
                    availability = "Disponibilidad",
                    level = "Nivel de disponibilidad",
                    cutlevel = "Nivel de corte",
                    freq.abs = "Frecuencia absoluta",
                    freq.abs.cum = "Frecuencia absoluta acumulada",
                    freq.rel = "Frecuencia relativa",
                    freq.rel.cum = "Frecuencia relativa acumulada") %>%
  colformat_double(j=c(3,5,7,9), digits=5) %>%
  width(j=c(1,4,6,8), width=.65) %>%
  width(j=c(2,3,5,6,7,9), width=.75) %>%
  theme_booktabs()

pag 23

levels %>%
  filter(centers=="04") %>%
  mutate(level=factor(level)) %>%
  arrange(-availability) %>%
  ggplot(aes(x=order, y=availability, color=level)) + geom_line() +
  xlab("Posición del término en el centro de interés") +
  ylab("Disponibilidad") +
  theme_bw() + scale_colour_grey()

pag 24 (la columna de Recuento, no sé porqué, está entera en 1. Estos son los resultados correctos)

clasificacion <- build.availability.levels(levels)
clasificacion %>%
  filter(level> 0) %>% filter(centers %in% c("01","02","03","04")) %>%
  flextable() %>%
  set_header_labels(centers = "Centro de interés",
                    words = "Palabras",
                    level = "Nivel de disponibilidad",
                    count = "Recuento") %>%
  width(j=c(1,2,3), width=.75) %>%
  width(j=4, width=4) %>%
  align(i=4, align="right") %>%
  theme_booktabs()

pag 25

levels %>%
  mutate(level = factor(level)) %>%
  filter(centers %in% c("01","02","03","04")) %>%
  arrange(-availability) %>%
  ggplot(aes(x=order, y=availability, color=level)) + geom_line() + facet_wrap(~centers) +
  xlab("Secuencia de palabras (por grado descendente de compatibilidad)") +
  ylab("Disponibilidad") +
  theme_bw() + scale_colour_grey()

pag 26

library(dispocen)
dispocen::runUtility()

pag 27

bs <- read.csv("BaseSociologica.csv", colClasses = "character")
bs <- bs %>%
  mutate(EDAD = strtoi(EDAD),
         AÑOSDEESTUDIO = strtoi(AÑOSDEESTUDIO)) %>%
  rename(GENERO = SEXO)
bs %>%
  head() %>%
  select(SUJETO, GENERO, EDAD, AÑOSDEESTUDIO) %>%
  flextable() %>%
  autofit()

pag 28

idHombres <- bs %>%
  filter(GENERO == "1") %>%
  select(SUJETO) %>%
  unlist()
idHombres

idMujeres <-  bs %>%
  filter(GENERO == "0") %>%
  select(SUJETO) %>%
  unlist()
idMujeres

data %>%
  filter(users %in% idMujeres) %>%
  head()

pag 29

data %>%
  filter(users %in% idHombres) %>%
  head()

disponibilidadHombres <- 
  build.avilasanchez.availability(data %>%
                                    filter(users %in% idHombres))

head(disponibilidadHombres) %>%
  select(centers, words, availability) %>%
  flextable() %>%
  autofit()

disponibilidadMujeres <- 
  build.avilasanchez.availability(data %>%
                                    filter(users %in% idMujeres))

head(disponibilidadMujeres) %>%
  select(centers, words, availability) %>%
  flextable() %>%
  autofit()

pag 30

dispComp <-
  inner_join(disponibilidadHombres %>%
               select(centers, words, availability) %>%
               rename(avHombres = availability),
             disponibilidadMujeres %>%
               select(centers, words, availability) %>%
               rename(avMujeres = availability),
             by = c("centers", "words"))
dispComp %>%
  head() %>%
  flextable() %>%
  autofit()

pag 31

dispComp %>%
  ggplot(aes(x=avHombres, y=avMujeres, color=centers)) + geom_point() +
  theme_bw() + scale_colour_grey()

pag 31-32

levelsHombres <- 
  classify.availability.levels(disponibilidadHombres)
clasificacionHombres <- build.availability.levels(levelsHombres)

levelsMujeres <- 
  classify.availability.levels(disponibilidadMujeres)
clasificacionMujeres <- build.availability.levels(levelsMujeres)

clasificacionGenero <-
  inner_join(clasificacionHombres %>%
               select(centers, level, words) %>%
               rename(wordsHombres = words),
             clasificacionMujeres %>%  
               select(centers, level, words) %>%
               rename(wordsMujeres = words), 
           by=c("centers","level")) 

clasificacionGenero %>%
  filter(level> 0)  %>%
  filter(centers %in% c("01", "02", "03", "04")) %>%
  flextable() %>% 
  set_header_labels(centers = "Centro de interés", 
                    wordsHombres = "Palabras hombres", 
                    wordsMujeres = "Palabras mujeres", 
                    level = "Nivel de disponibilidad",
                    count = "Recuento") %>%
  width(j=c(1,2), width=.75) %>%
  width(j=c(3,4), width=2.5) %>%
  align(j=c(3,4), align="right") %>%
  theme_booktabs()

pag 34

levelsGenero <-
  inner_join(levelsHombres %>%
               select(centers, level, words, availability) %>%
               rename(avHombre = availability, levelHombre=level),
             levelsMujeres %>%  
               select(centers, level, words, availability) %>%
               rename(avMujer = availability, levelMujer = level), 
           by=c("centers", "words")) 
levelsGenero %>%
  filter(levelHombre != levelMujer) %>%
  mutate(diffLevel = factor(abs(levelHombre - levelMujer))) %>%
  ggplot(aes(x=avHombre, y=avMujer, color=diffLevel)) + geom_point() +
  theme_bw() + scale_colour_grey()

diffs <- tapply(levelsGenero$levelHombre == levelsGenero$levelMujer,
                levelsGenero$centers, mean) * 100
diffs

pag 35

summary(diffs)

jmss70/dispocen documentation built on April 18, 2023, 1:31 p.m.