Week 7: Code along 6

R for data

Introduction

Question

Variation

Visualizing Distribution

ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut))

ggplot(data = diamonds) +
  geom_histogram(mapping = aes(x = carat), binwidth = 0.5)

smaller <- diamonds %>% 
  filter(carat < 3)
  
ggplot(data = smaller, mapping = aes(x = carat)) +
  geom_histogram(binwidth = 0.1)

ggplot(data = smaller, mapping = aes(x = carat, colour = cut)) +
  geom_freqpoly(binwidth = 0.1)

Typical values

ggplot(data = smaller, mapping = aes(x = carat)) +
  geom_histogram(binwidth = 0.01)

faithful %>%
    ggplot(aes(eruptions))+
    geom_histogram(binwidth = 0.25)

Unusual values

ggplot(diamonds) + 
  geom_histogram(mapping = aes(x = y), binwidth = 0.5) +
  coord_cartesian(ylim = c(0, 50))

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()

two categorical variables

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

two continuous variables

ggplot(data = smaller) +
  geom_bin2d(mapping = aes(x = carat, y = price))

## `stat_bin2d()` using `bins = 30`. Pick better value `binwidth`.

ggplot(data = smaller) +
  geom_hex(mapping = aes(x = carat, y = price))

ggplot(data = smaller, mapping = 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)

diamonds2 <- diamonds %>% 
  add_residuals(mod) %>% 
  mutate(resid = exp(resid))

ggplot(data = diamonds2) + 
  geom_point(mapping = aes(x = carat, y = resid))

ggplot(data = diamonds2) + 
  geom_boxplot(mapping = aes(x = cut, y = resid))