Introduction

Question

Variation

Visualizing distrubution

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

diamonds %>%
    ggplot(mapping = aes(x = carat)) +
    geom_histogram(binwidth = 0.5)

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = 0.5)

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

##Typicla values

diamonds %>%
    
    # Filter out diamonds > than 3
    filter(carat < 3) %>%
    
    # Plot
    ggplot(aes(x = carat)) + 
    geom_histogram(binwidth = 0.01)

faithful %>%
    ggplot(aes(eruptions)) +
    geom_histogram(binwidth = 0.25)

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`.

Missisng values

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

Covariation

A categorical and continous varibles

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

Two catagorical varibles

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

Two continous varibles

diamonds %>%
    ggplot() +
    geom_point(mapping = aes(x = carat, y = price), alpha = 1 / 100)

diamonds %>%
    ggplot() +
    geom_bin2d(mapping = aes(x = carat, y = price))

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat, y = price)) +
    geom_boxplot(aes(group = cut_width(carat, 0.1)))

Patterns and models

library(modelr)
mod <- lm(log(price) ~ log(carat), data = diamonds)

diamonds2 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

diamonds2 %>%
    ggplot(aes(carat, resid)) + 
    geom_point()

diamonds2 %>%
    ggplot(aes(cut, resid)) + 
    geom_boxplot()