Week 7: Code Along 6

R for Data Science: Chapter 6

Introduction

Questions

Variation

Vosualizing 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 `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()

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

diamonds %>%
    ggplot(aes(y)) + 
    geom_histogram() + 
    coord_cartesian(ylim = c(0, 50))

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

## Warning: Removed 9 rows containing missing values or values outside the scale range
## (`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 variables

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)

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

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

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