Week 7: Code Along 6

R for Data Science: Chapter 7

Introduction

Question

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 `binwidth`.

Typical values

diamonds %>%
    
    # Filter out diamonds greater than 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 chategorical and continous variable

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

Two categorical variables

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

Two continious variables

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

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)))

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

Patterns and models

library(modelr)
library(dplyr)

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()