tidyfst (version 0.7.7)

group_dt: Data manipulation within groups

Description

Analogous function for group_by in dplyr, but in another efficient way.

Usage

group_dt(data, by = NULL, ...)

Arguments

data

A data.frame

by

Variables to group by,unquoted name of grouping variable of list of unquoted names of grouping variables.

...

Any data manipulation arguments that could be implemented on a data.frame.

Value

data.table

Examples

# NOT RUN {
iris %>% group_dt(by = Species,slice_dt(1:2))
iris %>% group_dt(Species,filter_dt(Sepal.Length == max(Sepal.Length)))
iris %>% group_dt(Species,summarise_dt(new = max(Sepal.Length)))

# you can pipe in the `group_dt`
iris %>% group_dt(Species,
                  mutate_dt(max= max(Sepal.Length)) %>%
                    summarise_dt(sum=sum(Sepal.Length)))

# for users familiar with data.table, you can work on .SD directly
# following codes get the first and last row from each group
iris %>%
  group_dt(
    by = Species,
    rbind(.SD[1],.SD[.N])
  )

#' # for summarise_dt, you can use "by" to calculate within the group
mtcars %>%
  summarise_dt(
   disp = mean(disp),
   hp = mean(hp),
   by = cyl
)

  # but you could also, of course, use group_dt
 mtcars %>%
   group_dt(by =.(vs,am),
     summarise_dt(avg = mean(mpg)))

  # and list of variables could also be used
 mtcars %>%
   group_dt(by =list(vs,am),
            summarise_dt(avg = mean(mpg)))
# }