Week 7 Code Along 6

R for Data Science: Chapter 6

Introduction

Questions

Variation

Visulizing distributions

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

diamonds %>%
    ggplot(mapping = aes(x = carat))+
    geom_histogram(binwidth = .5)

diamonds %>%
    
    filter(carat < 3) %>%
    
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = .5)

diamonds %>%
    ggplot(aes(x = carat, color = cut)) +
    geom_freqpoly()

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

Typical values

diamonds %>%
    
    filter(carat < 3) %>%
    
    ggplot(mapping = aes(x = carat))+
    geom_histogram(binwidth = .01)

faithful %>%
    
    ggplot(aes(x = eruptions)) +
    geom_histogram(binwidth = .25)

Unusuals 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)) %>%
    
    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 cateogrical 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 continous variables

library(hexbin)
diamonds %>%
    ggplot(aes(x = carat, y = price))+
    geom_hex()

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat, y = price))+
    geom_boxplot(mapping = 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)
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()