OREdplyr functions for grouping columns and rows.
Table 3-4 Grouping Columns and Rows
| Function | Description |
|---|---|
|
|
Groups an |
|
|
Lists the number of rows in each group. |
|
|
Shows the names of the grouping columns. |
|
|
Returns the number of groups. |
|
|
Drops the grouping from the input |
Example 3-73 Using Grouping Functions
The following examples use the ore.frame object MTCARS that is created by using the ore.push function on the mtcars data.frame object. They exemplify the use of the grouping functions group_by, group_size, groups, n_group, and ungroup. They also use the OREdplyr functions arrange, rename, and summarize.
MTCARS <- ore.push(mtcars) by_cyl <- group_by(MTCARS, cyl) # Apply the summarise function to each group arrange(summarise(by_cyl, mean(disp), mean(hp)), cyl) # Summarise drops one layer of grouping by_vs_am <- group_by(MTCARS, vs, am) by_vs <- summarise(by_vs_am, n = n()) arrange(by_vs, vs, am) arrange(summarise(by_vs, n = sum(n)), vs) # Remove grouping summarise(ungroup(by_vs), n = sum(n)) # Group by expressions with mutate arrange(group_size(group_by(mutate(MTCARS, vsam = vs + am), vsam)), vsam) # Rename the grouping column groups(rename(group_by(MTCARS, vs), vs2 = vs)) # Add more grouping columns groups(group_by(by_cyl, vs, am)) groups(group_by(by_cyl, vs, am, add = TRUE)) # Drop duplicate groups groups(group_by(by_cyl, cyl, cyl)) # Load the magrittr library to use the forward-pipe operator %>% library(magrittr) by_cyl_gear_carb <- MTCARS %>% group_by(cyl, gear, carb) n_groups(by_cyl_gear_carb) arrange(group_size(by_cyl_gear_carb), cyl, gear, carb) by_cyl <- MTCARS %>% group_by(cyl) # Number of groups n_groups(by_cyl) # Size of each group arrange(group_size(by_cyl), cyl)
Listing for This Example
R> MTCARS <- ore.push(mtcars) R> by_cyl <- group_by(MTCARS, cyl) R> R> # Apply the summarise function to each group R> arrange(summarise(by_cyl, mean(disp), mean(hp)), cyl) cyl mean.disp. mean.hp. 1 4 105.1364 82.63636 2 6 183.3143 122.28571 3 8 353.1000 209.21429 R> R> # Summarise drops one layer of grouping R> by_vs_am <- group_by(MTCARS, vs, am) R> by_vs <- summarise(by_vs_am, n = n()) R> arrange(by_vs, vs, am) vs am n 1 0 0 12 2 0 1 6 3 1 0 7 4 1 1 7 R> arrange(summarise(by_vs, n = sum(n)), vs) vs n 1 0 18 2 1 14 R> R> # Remove grouping R> summarise(ungroup(by_vs), n = sum(n)) n 32 R> R> # Group by expressions with mutate R> arrange(group_size(group_by(mutate(MTCARS, vsam = vs + am), vsam)), vsam) vsam n 1 0 12 2 1 13 3 2 7 R> R> # Rename the grouping column R> groups(rename(group_by(MTCARS, vs), vs2 = vs)) [1] "vs2" R> R> # Add more grouping columns R> groups(group_by(by_cyl, vs, am)) [[1]] [1] "vs" [[2]] [1] "am" R> groups(group_by(by_cyl, vs, am, add = TRUE)) [[1]] [1] "cyl" [[2]] [1] "vs" [[3]] [1] "am" R> R> # Drop duplicate groups R> groups(group_by(by_cyl, cyl, cyl)) [1] "cyl R> R> # Load the magrittr library to use the forward-pipe operator %>% R> library(magrittr) R> by_cyl_gear_carb <- MTCARS %>% group_by(cyl, gear, carb) R> n_groups(by_cyl_gear_carb) [1] 12 R> arrange(group_size(by_cyl_gear_carb), cyl, gear, carb) cyl gear carb n 1 4 3 1 1 2 4 4 1 4 3 4 4 2 4 4 4 5 2 2 5 6 3 1 2 6 6 4 4 4 7 6 5 6 1 8 8 3 2 4 9 8 3 3 3 10 8 3 4 5 11 8 5 4 1 12 8 5 8 1 R> R> by_cyl <- MTCARS %>% group_by(cyl) R> # Number of groups R> n_groups(by_cyl) [1] 3 R> # Number of groups R> n_groups(by_cyl) [1] 3 R> R> # Size of each group R> arrange(group_size(by_cyl), cyl) cyl n 1 4 11 2 6 7 3 8 14