Variation

###Visualizing distributions

diamonds %>%
    ggplot(aes(x = cut)) +
    geom_bar()

diamonds %>%
    ggplot(mapping = aes(x = carat)) +
    geom_histogram(binwidth = 0.075)

diamonds %>%
    filter(carat < 3) %>%

ggplot(aes(x = carat)) +
    geom_histogram(binwith = .5)
## Warning in geom_histogram(binwith = 0.5): Ignoring unknown parameters:
## `binwith`
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

diamonds %>%
    ggplot(aes(x = carat, color = cut)) +
    geom_freqpoly()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

###Typical values

diamonds %>%
    
# filter out diamonds > 3 carats
    filter(carat < 3) %>%
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = .01)

faithful %>%
    ggplot(aes(eruptions)) +
    geom_histogram(binwidth = .25)

###Unusual values

diamonds %>%
    ggplot(aes(y)) +
    geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

diamonds %>%
    ggplot(aes(y)) +
    geom_histogram() +
    coord_cartesian(ylim = c(0,50))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Missing values

diamonds %>%
    # filter(y < 3 | y > 20) %>%
    mutate(y = ifelse(y < 3 | y > 20, NA, y)) %>%
    ggplot(aes(x = x, y = y)) +
    geom_point()
## Warning: Removed 9 rows containing missing values or values outside the scale range
## (`geom_point()`).

Covariation

Categorical and continuous variable

diamonds %>%
    ggplot(aes(x = cut, y = price)) +
    geom_boxplot()

Two categorical variables

diamonds %>%
    count(color, cut) %>%
    ggplot(aes(x = color, y = cut, fill = n)) +
    geom_tile()

Twos continuous variables

library(hexbin)
## Warning: package 'hexbin' was built under R version 4.4.3
diamonds %>%
    ggplot(aes(x = carat,y = price)) +
    geom_hex()

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat,y = price)) +
    geom_boxplot(aes(group = cut_width(carat, .1)))

Patterns and models

library(modelr)
## Warning: package 'modelr' was built under R version 4.4.3
mod <- lm(log(price) ~ log(carat), data = diamonds)

diamonds_mod <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

diamonds_mod %>%
    ggplot(aes(carat, resid)) +
    geom_point()

diamonds_mod %>%
    ggplot(aes(cut, resid)) +
    geom_boxplot()