data <- penguins
data %>% count(island)
## island n
## 1 Biscoe 168
## 2 Dream 124
## 3 Torgersen 52
island_levels <- c("Biscoe", "Dream", "Torgersen")
data_rev <- data %>%
mutate(island = island %>% factor(levels = island_levels))
Make two bar charts here - one before ordering another after
data_summary <- data %>%
group_by(island) %>%
summarise(
bill_len = mean(bill_len, na.rm = TRUE)
)
data_summary
## # A tibble: 3 × 2
## island bill_len
## <fct> <dbl>
## 1 Biscoe 45.3
## 2 Dream 44.2
## 3 Torgersen 39.0
ggplot (data_summary, aes (bill_len, island)) + geom_point ()
ggplot (data_summary, aes (bill_len, fct_reorder (island, bill_len))) + geom_point()
Show examples of three functions:
data %>%
mutate(island = fct_recode(island,
"BiscoeIsland" = "Biscoe",
"DreamIsland" = "Dream",
"TorgersenIsland" = "Torgersen")) %>%
count(island)
## island n
## 1 BiscoeIsland 168
## 2 DreamIsland 124
## 3 TorgersenIsland 52
data %>%
mutate(island = fct_collapse(island,
BiscoeIsland = "Biscoe",
Other = c("Dream", "Torgersen"))) %>%
count(island)
## island n
## 1 BiscoeIsland 168
## 2 Other 176
data %>%
mutate(island = fct_lump(island)) %>%
count(island)
## island n
## 1 Biscoe 168
## 2 Dream 124
## 3 Other 52
No need to do anything here.