Week7: Code along 6

Introduction

Questions

Variation

Visualizing Distributions

diamonds

## # A tibble: 53,940 × 10
##    carat cut       color clarity depth table price     x     y     z
##    <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
##  1  0.23 Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
##  2  0.21 Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
##  3  0.23 Good      E     VS1      56.9    65   327  4.05  4.07  2.31
##  4  0.29 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
##  5  0.31 Good      J     SI2      63.3    58   335  4.34  4.35  2.75
##  6  0.24 Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48
##  7  0.24 Very Good I     VVS1     62.3    57   336  3.95  3.98  2.47
##  8  0.26 Very Good H     SI1      61.9    55   337  4.07  4.11  2.53
##  9  0.22 Fair      E     VS2      65.1    61   337  3.87  3.78  2.49
## 10  0.23 Very Good H     VS1      59.4    61   338  4     4.05  2.39
## # … with 53,930 more rows

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)

Typicaal Values

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

ggplot(data = faithful, mapping = aes(x = eruptions)) + 
  geom_histogram(binwidth = 0.25)

Unusual values

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

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

Missing Values

diamonds2 <- diamonds %>% 
  filter(between(y, 3, 20))

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

Covariation

A categorical and continuous variable

ggplot(data = diamonds, mapping = 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

library(hexbin)
ggplot(data = diamonds) +
  geom_bin2d(mapping = aes(x = carat, y = price))

# install.packages("hexbin")
ggplot(data = smaller) +
  geom_hex(mapping = aes(x = carat, y = price))

ggplot(data = diamonds, mapping = aes(x = carat, y = price)) + 
  geom_boxplot(mapping = aes(group = cut_width(carat, 0.1)))

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))