Introduction
Questions
Variation
Visualizing distribution
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
## # ℹ 53,930 more rows
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut))
diamonds %>%
count(cut)
## # A tibble: 5 × 2
## cut n
## <ord> <int>
## 1 Fair 1610
## 2 Good 4906
## 3 Very Good 12082
## 4 Premium 13791
## 5 Ideal 21551
#> # A tibble: 5 × 2
#> cut n
#> <ord> <int>
#> 1 Fair 1610
#> 2 Good 4906
#> 3 Very Good 12082
#> 4 Premium 13791
#> 5 Ideal 21551
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)
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))
unusual <- diamonds %>%
filter(y < 3 | y > 20) %>%
select(price, x, y, z) %>%
arrange(y)
unusual
## # A tibble: 9 × 4
## price x y z
## <int> <dbl> <dbl> <dbl>
## 1 5139 0 0 0
## 2 6381 0 0 0
## 3 12800 0 0 0
## 4 15686 0 0 0
## 5 18034 0 0 0
## 6 2130 0 0 0
## 7 2130 0 0 0
## 8 2075 5.15 31.8 5.12
## 9 12210 8.09 58.9 8.06
#> # A tibble: 9 × 4
#> price x y z
#> <int> <dbl> <dbl> <dbl>
#> 1 5139 0 0 0
#> 2 6381 0 0 0
#> 3 12800 0 0 0
#> 4 15686 0 0 0
#> 5 18034 0 0 0
#> 6 2130 0 0 0
#> 7 2130 0 0 0
#> 8 2075 5.15 31.8 5.12
#> 9 12210 8.09 58.9 8.06
Missing Values
diamonds2 <- diamonds %>%
mutate(y = ifelse(y < 3 | y > 20, NA, y))
ggplot(data = diamonds2, mapping = aes(x = x, y = y)) +
geom_point(na.rm = TRUE)
nycflights13::flights %>%
mutate(
cancelled = is.na(dep_time),
sched_hour = sched_dep_time %/% 100,
sched_min = sched_dep_time %% 100,
sched_dep_time = sched_hour + sched_min / 60
) %>%
ggplot(mapping = aes(sched_dep_time)) +
geom_freqpoly(mapping = aes(colour = cancelled), binwidth = 1/4)
Covariation
ggplot(data = diamonds, mapping = aes(x = price)) +
geom_freqpoly(mapping = aes(colour = cut), binwidth = 500)
ggplot(diamonds) +
geom_bar(mapping = aes(x = cut))
ggplot(data = diamonds, mapping = aes(x = price, y = ..density..)) +
geom_freqpoly(mapping = aes(colour = cut), binwidth = 500)
## Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
#> Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
#> ℹ Please use `after_stat(density)` instead.
#> This warning is displayed once every 8 hours.
#> Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
#> generated.
ggplot(data = diamonds, mapping = aes(x = cut, y = price)) +
geom_boxplot()
ggplot(data = mpg, mapping = aes(x = class, y = hwy)) +
geom_boxplot()
ggplot(data = mpg) +
geom_boxplot(mapping = aes(x = reorder(class, hwy, FUN = median), y = hwy))
Two categorical variables
ggplot(data = diamonds) +
geom_count(mapping = aes(x = cut, y = color))
diamonds %>%
count(color, cut) %>%
ggplot(mapping = aes(x = color, y = cut)) +
geom_tile(mapping = aes(fill = n))
Two Continuous Variables
ggplot(data = diamonds) +
geom_point(mapping = aes(x = carat, y = price))
ggplot(data = diamonds) +
geom_point(mapping = aes(x = carat, y = price), alpha = 1 / 100)
ggplot(data = smaller, mapping = aes(x = carat, y = price)) +
geom_boxplot(mapping = aes(group = cut_width(carat, 0.1)))
Patterns and Models
ggplot(data = faithful) +
geom_point(mapping = aes(x = eruptions, y = waiting))
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))
