Week 7: Code along 6

R for Data science: Chapter 6

Introduction

Question2

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()

## `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
    ggplot(aes(x =x, y = y)) +
    geom_point()

## Warning: Removed 9 rows containing missing values (`geom_point()`).

Covariation

A categroical 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(mapping = aes(fill = n))

Two continuous variables

library(hexbin)

## Warning: package 'hexbin' was built under R version 4.3.3

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

diamonds %>% 
  count(cut, clarity) %>% 
  ggplot(aes(clarity, cut, fill = n)) + 
    geom_tile()