Introduction

Questions

Variation

Visualizing distribution

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(x = 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()

summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Covariation

A categorical and continues 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()

### Two continueos variables

library(hexbin)
diamonds %>%
    ggplot(aes(x = carat, y = price)) +
    geom_hex()

diamonds %>%
    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)

 diamonds4 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))
 
 diamonds4 %>%
     ggplot(aes(carat, resid)) + 
     geom_point()

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

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.