Week 7: Code Along 6

R for Data Science: Chapter 6

Introduction

Questions

Variation

Visualizing distributions

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`.

Typical values

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

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

Unusual values

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)) %>%
    
    # plot
    ggplot(aes(x = x, y = y)) +
    geom_point()

## Warning: Removed 9 rows containing missing values or values outside the scale range
## (`geom_point()`).