Week 7: Code Along 6

R for Data Science: Chapter 6/7

Introduction

Question2

Variation

Visualizing distributions

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

diamonds %>%
    ggplot(mapping = aes(x = carat)) +
    geom_histogram(binwidth = 0.5, fill = "red")

diamonds %>%
    
    filter(carat < 3) %>%
    
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = 0.7, fill = "Turquoise")

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
    
    filter(carat < 3) %>%
    
    #Plot
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = 0.01, fill = "pink")

faithful %>%
    ggplot(aes(eruptions)) +
  geom_histogram(binwidth = 0.25, fill = "green")

Unusual Values

diamonds %>%
    ggplot(aes(y)) + 
  geom_histogram(fill= "maroon")  +
  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 or values outside the scale range
## (`geom_point()`).

Covariation

A categorical and continuous variable

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

Two categorical and continuous variables

diamonds %>%

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

Two continous Variables

library(hexbin)

## Warning: package 'hexbin' was built under R version 4.4.3

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)))

## Paterns and Models

library(modelr)

## Warning: package 'modelr' was built under R version 4.4.3

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(fill= "navy")