I have the dataframe below and I would like to sum the values of all my columns which actually are much more than 4, per Category. So I would like a loop or something to run something like:
library(dplyr)
Ind<-Abstract_50 %>% group_by(Category) %>%
summarize(Abstract_50$`2018-03` = sum(Abstract_50$`2018-03`))
Abstract_50<-structure(list(Category = c("Gaming", "Comedy", "Education",
"Entertainment", "People & Blogs", "Howto & Style", "Gaming",
"Entertainment", "Comedy", "Education", "Science & Technology",
"People & Blogs", "Gaming", "Howto & Style", "Entertainment",
"Entertainment", "Entertainment", "Gaming", "Entertainment",
"Gaming", "Entertainment", "Entertainment", "Film & Animation",
"Entertainment", "Education", "Gaming", "Gaming", "People & Blogs",
"Entertainment", "Comedy", "Gaming", "People & Blogs", "Entertainment",
"Comedy", "Entertainment", "Sports", "Gaming", "Gaming", "Film & Animation",
"Entertainment", "Entertainment", "Entertainment", "Music", "Gaming",
"Film & Animation", "People & Blogs", "Entertainment", "Science & Technology",
"Entertainment", "Gaming"), `2018-03` = c(NA, NA, 101163664,
222435612, 2566, 539836128, 170830842, 43657714, NA, 589789888,
18453451, 22327, 275987966, 3398517, 115637850, NA, 3358627,
104063416, 904737659, NA, 138065088, NA, 178509153, 147605809,
252376836, 47241577, 145748966, NA, 112800, NA, 92281120, NA,
884076, NA, 147558050, 160818771, 209932596, 1269924, 66883227,
NA, NA, NA, 45831420, 10426490, NA, NA, 67836946, 8847841, 2614794,
51696616), `2018-04` = c(NA, NA, 138215454, 217690060, 2486,
634144976, 140351664, 40516483, NA, 755403217, 23270005, -178648,
326352497, 3315085, 77217671, NA, 2824360, 105855275, 708273455, NA, 209272453, NA, 165972373, 195448116, 262205166, 71156940,
64229826, NA, 789991, NA, 107928087, NA, 587108, NA, 135852933,
208830991, 198161237, 2462926, 77881362, NA, NA, NA, 38904148,
21032898, NA, NA, 59783457, 16303243, 7311107, 57273819), `2018-05` = c(NA,
NA, 151697886, 254479194, 2374, 712486430, 196327850, 75886076,
NA, 959619148, 29213361, 164395, 330922933, 3112488, 86213061,
NA, 3601193, 103629125, 708728068, NA, 250967293, NA, 151501861,
48698231, 249038679, 73774699, 164568363, NA, 943891, NA, 130376287,
NA, 5322697, NA, 164697288, 189706047, 213415764, 7806720, 78552229,
NA, NA, NA, 73012836, 45648322, NA, NA, 68432350, 18830495, 15834552,
88757967), `2018-06` = c(NA, NA, 142169001, 297190999, 2057,
850709260, 191765278, 70501496, NA, 1454871272, 28011897, 465378,
370654981, 3211888, 53592160, NA, 4667279, 193768594, 821707471,
NA, 599954205, NA, 189548519, 371602705, 229237800, 68325636,
193613716, NA, 1858138, NA, 94145274, NA, 8718655, NA, 255038043,
254772059, 265200729, 9386440, 51753755, NA, NA, NA, 84645886,
266089027, NA, NA, 167742900, 11844037, 33770300, 81240819)), row.names = c(NA,
-50L), class = c("tbl_df", "tbl", "data.frame"))
>Solution :
You can use across to calculate the sum across all columns, except for the grouping column.
library(tidyverse)
Abstract_50 %>%
group_by(Category) %>%
summarise(across(everything(), sum))
Output
Category `2018-03` `2018-04` `2018-05` `2018-06`
<chr> <dbl> <dbl> <dbl> <dbl>
1 Comedy NA NA NA NA
2 Education 943330388 1155823837 1360355713 1826278073
3 Entertainment NA NA NA NA
4 Film & Animation NA NA NA NA
5 Gaming NA NA NA NA
6 Howto & Style 543234645 637460061 715598918 853921148
7 Music 45831420 38904148 73012836 84645886
8 People & Blogs NA NA NA NA
9 Science & Technology 27301292 39573248 48043856 39855934
10 Sports 160818771 208830991 189706047 254772059