Code Along 6

Introduction

Data Visual

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 = 0.3)

diamonds %>% 
    ggplot(aes(x = carat, color = cut)) + 
    geom_freqpoly()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Typical Values

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

Missing Values

diamonds %>%
    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()`).

Continued & Continuous

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()

Two Continuous

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, 0.1)))

Patterns and Models

library(modelr)

## Warning: package 'modelr' was built under R version 4.4.3

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

diamonds4 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

diamonds4 %>%
    ggplot(aes(carat, resid)) + 
    geom_point()

diamonds4 %>%
    ggplot(aes(cut, resid)) + 
    geom_boxplot()