Introduction

Questions

Variation

Visualizing Distributions

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

diamonds %>%
    ggplot(mapping = aes(x = carat)) +
    geom_histogram(binwidth = .5)

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat)) + 
    geom_histogram(binwidth = .05)

diamonds %>% 
    ggplot(mapping = 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 = .01)

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

Covariation

A categorical and Continuous 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 Continuous Varibles

library(hexbin)
## Warning: package 'hexbin' was built under R version 4.2.2
diamonds %>%
    ggplot(aes(x = carat, y = price)) + 
    geom_hex()

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat, y = price)) +
    geom_boxplot(mapping = aes(group = cut_width(carat, .1)))

Patterns and Models

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

diamonds3 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

diamonds3 %>%
    ggplot(aes(carat, resid)) +
    geom_point()

diamonds3 %>%
    ggplot(aes(cut, resid)) +
    geom_boxplot()

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

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.