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

ggplot(data = faithful, mapping = aes(x = eruptions)) + 
  geom_histogram(binwidth = 0.25)

###Unusual Values

ggplot(diamonds) + 
  geom_histogram(mapping = aes(x = y), binwidth = 0.5)  +
  coord_cartesian(ylim = c(0, 50))

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 (`geom_point()`).

Covariariation

A categorial and contrinuous variable

ggplot(data = diamonds, mapping = aes(x = cut, y = price)) +
  geom_boxplot()

Two categorial vairable

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

Two continous variable

library(hexbin)

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)

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

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

ggplot(data = diamonds2) + 
  geom_point(mapping = aes(x = carat, y = resid))

ggplot(data = diamonds2) + 
  geom_boxplot(mapping = aes(x = cut, y = resid))