Week 7: Code Along 6

R for Data Science: Chapter 6

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(mapping = 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()`).

nycflights13::flights %>% 
  mutate(
    cancelled = is.na(dep_time),
    sched_hour = sched_dep_time %/% 100,
    sched_min = sched_dep_time %% 100,
    sched_dep_time = sched_hour + sched_min / 60
  ) %>% 
  ggplot(mapping = aes(sched_dep_time)) + 
    geom_freqpoly(mapping = aes(colour = cancelled), binwidth = 1/4)

Covariation

A Categorical and Continuous variable

diamonds %>%
    ggplot(aes(x = cut, y = price)) +
    geom_boxplot()

Two Categorical Variables

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

Two Continuous Variables

diamonds %>%
    ggplot(aes(data = diamonds)) +
    geom_point(mapping = aes(x = carat, y = price), alpha = 1 / 100)

## Don't know how to automatically pick scale for object of type
## <tbl_df/tbl/data.frame>. Defaulting to continuous.

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)))

## Warning: Orientation is not uniquely specified when both the x and y aesthetics are
## continuous. Picking default orientation 'x'.

diamonds %>%
    ggplot(aes(x = carat, y = price)) + 
  geom_boxplot(aes(group = cut_number(carat, 20)))

## Warning: Orientation is not uniquely specified when both the x and y aesthetics are
## continuous. Picking default orientation 'x'.

Patterns and models

faithful %>%
    ggplot(aes(data = faithful)) + 
  geom_point(aes(x = eruptions, y = waiting))

## Don't know how to automatically pick scale for object of type <data.frame>.
## Defaulting to continuous.

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))