Actually, consider base R's by (object-oriented wrapper to tapply) using identity if objective is as title reads and OP's specific needs below:
Print method that shows groups
...one can easily see the groups by which a dataset is grouped
In fact, you can run any operation like summary and by outputs still have group headers with section breaks!
# ONE GROUP
by(df, random_df$group, identity)
# TWO GROUPS
with(df, by(random_df, list(group1, group2), identity))
# THREE GROUPS
with(df, by(random_df, list(group1, group2, group3), identity))
Below is demonstration with random, seeded data:
Random Data
set.seed(3222018)
data_tools <- c("sas", "stata", "spss", "python", "r", "julia")
random_df <- data.frame(
group = sample(data_tools, 50, replace=TRUE),
int = sample(1:5, 50, replace=TRUE),
num = rnorm(50),
char = rep(letters[1:3], 20)[1:50],
bool = sample(c(TRUE, FALSE), 50, replace=TRUE),
data = as.Date(sample(1:as.integer(Sys.Date()), 50, replace=TRUE), origin="1970-01-01")
)
Rextester demo
One Group
by(random_df, random_df$group, identity)
# random_df$group: julia
# group int num char bool data
# 9 julia 1 0.55209060 c TRUE 2003-01-08
# 12 julia 5 0.25581573 c FALSE 1973-01-20
# 20 julia 2 -0.44872825 b FALSE 1981-12-20
# 30 julia 1 0.09790121 c TRUE 1981-07-11
# 31 julia 1 1.75711081 a FALSE 1984-05-23
# 35 julia 3 -1.78797757 b TRUE 1992-10-23
# 39 julia 5 -1.83548253 c TRUE 1982-04-18
# 44 julia 3 0.52640304 b FALSE 2016-07-28
# 50 julia 2 0.05759068 b FALSE 1987-07-09
# ------------------------------------------------------------
# random_df$group: python
# group int num char bool data
# 8 python 3 -0.75471461 b TRUE 2018-04-08
# 15 python 4 0.03756282 c FALSE 2006-03-29
# 19 python 1 0.43025626 a FALSE 2005-03-30
# 22 python 4 -0.28019319 a FALSE 1997-02-19
# 24 python 2 -0.05318753 c FALSE 1977-08-02
# 45 python 2 -0.11575270 c TRUE 2006-06-23
# 48 python 2 -0.29651827 c TRUE 2015-07-13
# 49 python 3 -0.45816745 a FALSE 1991-09-09
# ------------------------------------------------------------
# random_df$group: r
# group int num char bool data
# 5 r 4 -0.1748250 b FALSE 2005-04-20
# 14 r 2 -0.5868782 b TRUE 2005-12-30
# 25 r 5 -0.5108906 a TRUE 1985-08-26
# 33 r 1 0.3580581 c FALSE 1983-08-16
# 34 r 3 -2.9556022 a TRUE 1998-07-24
# 36 r 5 -2.5008645 c TRUE 1990-12-30
# 43 r 5 -2.1710319 a TRUE 1987-09-29
# ------------------------------------------------------------
# ...
Two Groups
with(random_df, by(random_df, list(group, char), identity))
# : julia
# : a
# group int num char bool data
# 31 julia 1 1.757111 a FALSE 1984-05-23
# ------------------------------------------------------------
# : python
# : a
# group int num char bool data
# 19 python 1 0.4302563 a FALSE 2005-03-30
# 22 python 4 -0.2801932 a FALSE 1997-02-19
# 49 python 3 -0.4581675 a FALSE 1991-09-09
# ------------------------------------------------------------
# : r
# : a
# group int num char bool data
# 25 r 5 -0.5108906 a TRUE 1985-08-26
# 34 r 3 -2.9556022 a TRUE 1998-07-24
# 43 r 5 -2.1710319 a TRUE 1987-09-29
# ------------------------------------------------------------
# : sas
# : a
# group int num char bool data
# 28 sas 2 -0.6086176 a FALSE 2019-01-26
# 40 sas 4 0.5408948 a FALSE 2004-10-24
# 46 sas 1 0.7266734 a TRUE 1996-09-05
# ------------------------------------------------------------
# : spss
# : a
# group int num char bool data
# 1 spss 1 -0.06494476 a TRUE 1999-07-10
# 7 spss 5 1.93460991 a TRUE 1974-04-17
# 16 spss 1 -0.55380012 a FALSE 2010-04-06
# 37 spss 1 0.17309091 a TRUE 1999-01-22
# ------------------------------------------------------------
# : stata
# : a
# group int num char bool data
# 4 stata 1 -1.0498222 a TRUE 1981-05-01
# 10 stata 1 1.9223104 a TRUE 1996-07-23
# 13 stata 1 -0.8381546 a TRUE 1989-01-12
# ------------------------------------------------------------
# ...
Three Groups
with(random_df, by(random_df, list(group, char, int), identity))
# : julia
# : a
# : 1
# group int num char bool data
# 31 julia 1 1.757111 a FALSE 1984-05-23
# ------------------------------------------------------------
# : python
# : a
# : 1
# group int num char bool data
# 19 python 1 0.4302563 a FALSE 2005-03-30
# ------------------------------------------------------------
# : r
# : a
# : 1
# NULL
# ------------------------------------------------------------
# : sas
# : a
# : 1
# group int num char bool data
# 46 sas 1 0.7266734 a TRUE 1996-09-05
# ------------------------------------------------------------
# : spss
# : a
# : 1
# group int num char bool data
# 1 spss 1 -0.06494476 a TRUE 1999-07-10
# 16 spss 1 -0.55380012 a FALSE 2010-04-06
# 37 spss 1 0.17309091 a TRUE 1999-01-22
# ------------------------------------------------------------
# : stata
# : a
# : 1
# group int num char bool data
# 4 stata 1 -1.0498222 a TRUE 1981-05-01
# 10 stata 1 1.9223104 a TRUE 1996-07-23
# 13 stata 1 -0.8381546 a TRUE 1989-01-12
# ------------------------------------------------------------
# ...
data.table example
To illustrate, you can also run any operation inside by including data.table aggregation to still return grouped headers and section breaks print output:
library(data.table)
...
by(random_df, random_df$group, function(sub)
data.table(sub)[, list(mean_num = mean(num),
median_num = median(num),
min_num = min(num),
max_num = max(num),
total_num = sum(num)), by = char]
)
# random_df$group: julia
# char mean_num median_num min_num max_num total_num
# 1: c -0.2324187 0.1768585 -1.835483 0.5520906 -0.929675
# 2: b -0.4131780 -0.1955688 -1.787978 0.5264030 -1.652712
# 3: a 1.7571108 1.7571108 1.757111 1.7571108 1.757111
# ------------------------------------------------------------------------------
# random_df$group: python
# char mean_num median_num min_num max_num total_num
# 1: b -0.7547146 -0.75471461 -0.7547146 -0.75471461 -0.7547146
# 2: c -0.1069739 -0.08447011 -0.2965183 0.03756282 -0.4278957
# 3: a -0.1027015 -0.28019319 -0.4581675 0.43025626 -0.3081044
# ------------------------------------------------------------------------------
# random_df$group: r
# char mean_num median_num min_num max_num total_num
# 1: b -0.3808516 -0.3808516 -0.5868782 -0.1748250 -0.7617031
# 2: a -1.8791749 -2.1710319 -2.9556022 -0.5108906 -5.6375247
# 3: c -1.0714032 -1.0714032 -2.5008645 0.3580581 -2.1428064
# ------------------------------------------------------------------------------
# random_df$group: sas
# char mean_num median_num min_num max_num total_num
# 1: c 0.08215953 0.163064560 -1.3670420 1.3695510 0.3286381
# 2: b -0.16423225 0.005903355 -1.3995380 0.7308023 -0.6569290
# 3: a 0.21965022 0.540894826 -0.6086176 0.7266734 0.6589507
# ------------------------------------------------------------------------------
# random_df$group: spss
# char mean_num median_num min_num max_num total_num
# 1: a 0.3722390 0.05407307 -0.5538001 1.9346099 1.488956
# 2: b 0.5085635 0.73430008 -0.3003130 0.8659667 2.034254
# 3: c -1.2909541 -1.29095413 -1.2909541 -1.2909541 -1.290954
# ------------------------------------------------------------------------------
# random_df$group: stata
# char mean_num median_num min_num max_num total_num
# 1: a 0.01144453 -0.8381546 -1.0498222 1.9223104 0.0343336
# 2: b -0.65927260 -0.6592726 -1.1870952 -0.1314500 -1.3185452
# 3: c 0.94910811 0.9491081 0.9491081 0.9491081 0.9491081
