In-class EX02

pacman::p_load(ggdist, ggridges, ggthemes,
               colorspace, tidyverse)

exam <- read_csv("data/Exam_data.csv")

# Ensure that the 'ENGLISH' column is numeric
exam$ENGLISH <- as.numeric(as.character(exam$ENGLISH))

# Check if there are any NAs introduced by the conversion, which would indicate non-numeric values in the original column
sum(is.na(exam$ENGLISH))

[1] 6

# If NAs are present, they must be addressed before plotting
# For instance, you can remove the rows with NA values
exam <- exam[!is.na(exam$ENGLISH), ]

# Now try the plot again
ggplot(exam, 
       aes(x = ENGLISH, 
           y = CLASS)) +
  geom_density_ridges(
    scale = 3,
    rel_min_height = 0.01,
    bandwidth = 3.4,
    fill = lighten("#7097BB", .3),
    color = "white"
  ) +
  scale_x_continuous(
    name = "English grades",
    expand = c(0, 0)
  ) +
  scale_y_discrete(
    name = NULL, 
    expand = expansion(add = c(0.2, 2.6))
  ) +
  theme_ridges()

ggplot(exam, 
       aes(x = ENGLISH, 
           y = CLASS,
           fill = stat(x))) +
  geom_density_ridges_gradient(
    scale = 3,
    rel_min_height = 0.01) +
  scale_fill_viridis_c(name = "Temp. [F]",
                       option = "C") +
  scale_x_continuous(
    name = "English grades",
    expand = c(0, 0)
  ) +
  scale_y_discrete(name = NULL, expand = expansion(add = c(0.2, 2.6))) +
  theme_ridges()

ggplot(exam,
       aes(x = ENGLISH, 
           y = CLASS, 
           fill = 0.5 - abs(0.5-stat(ecdf)))) +
  stat_density_ridges(geom = "density_ridges_gradient", 
                      calc_ecdf = TRUE) +
  scale_fill_viridis_c(name = "Tail probability",
                       direction = -1) +
  theme_ridges()

ggplot(exam,
       aes(x = ENGLISH, 
           y = CLASS, 
           fill = factor(stat(quantile))
           )) +
  stat_density_ridges(
    geom = "density_ridges_gradient",
    calc_ecdf = TRUE, 
    quantiles = 4,
    quantile_lines = TRUE) +
  scale_fill_viridis_d(name = "Quartiles") +
  theme_ridges()

ggplot(exam,
       aes(x = ENGLISH, 
           y = CLASS, 
           fill = factor(stat(quantile))
           )) +
  stat_density_ridges(
    geom = "density_ridges_gradient",
    calc_ecdf = TRUE, 
    quantiles = c(0.025, 0.975)
    ) +
  scale_fill_manual(
    name = "Probability",
    values = c("#FF0000A0", "#A0A0A0A0", "#0000FFA0"),
    labels = c("(0, 0.025]", "(0.025, 0.975]", "(0.975, 1]")
  ) +
  theme_ridges()

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA)

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA) +
  geom_boxplot(width = .20,
               outlier.shape = NA) +
  stat_dots(side = "left", 
            justification = 1.2, 
            binwidth = .5,
            dotsize = 2)

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA) +
  geom_boxplot(width = .20,
               outlier.shape = NA) +
  stat_dots(side = "left", 
            justification = 1.2, 
            binwidth = .5,
            dotsize = 1.5) +
  coord_flip() +
  theme_economist()