Code Along 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(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 bigger diamonds 
    filter(carat < 3) %>%
    
    #plot 
    ggplot(aes(carat)) +
    geom_histogram(binwidth = 0.01)

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

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

Unusual Values

diamonds %>%
    ggplot(aes(x = y)) +
    geom_histogram()

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

diamonds %>%
    ggplot(aes(x = 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 cetegorical and continuois 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 Continuois varibales

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)))

Patterns and models

library(modelr)
mod <- lm(log(price) ~ log(carat), data = diamonds) 

diamonds2 <- diamonds %>% 
    modelr::add_residuals(mod) %>% 
    mutate(resid = exp(resid))
diamonds2 %>%
    ggplot(aes(carat,resid)) +
    geom_point()

diamonds2 %>%
    ggplot(aes(cut, resid)) +
    geom_boxplot()