Code Along 6

R for Data Science Chapter 7

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 = .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_rev = ifelse(y < 3 | y> 20, NA, y)) %>%
    
    # Plot
    ggplot(aes(x = x, y = y)) + 
    geom_point()

Covariation

A Categorical Variables

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 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()