r - Randomly pick a value from a set of rows and add value to new row below

Question

my R skills are not sufficient to tackle this issue so I'm hoping someone can help.

My data look like this:

head(human.players,25)

Season	Episode	Round	Player	Player_type	Crowd_size	q1_a	q2_a	q3_a	q4_a	q5_a
2020	1	1	1	1	3	0	1	0	0	NA
2020	1	1	2	1	3	0	1	1	1	NA
2020	1	1	3	1	3	0	0	0	1	NA
2020	1	2	1	1	3	1	1	0	1	NA
2020	1	2	2	1	3	1	0	1	0	NA
2020	1	2	3	1	3	1	1	1	0	NA
2020	1	3	1	1	3	0	1	0	0	NA
2020	1	3	2	1	3	0	1	1	1	NA
2020	1	3	3	1	3	0	0	1	1	NA
2020	1	4	1	1	3	0	0	1	1	NA
2020	1	4	2	1	3	0	0	1	1	NA
2020	1	4	3	1	3	0	0	1	1	NA
2020	1	5	1	1	2	1	1	0	0	NA
2020	1	5	2	1	2	1	1	1	0	NA
2020	1	5	3	1	2	NA	NA	NA	NA	NA
2020	1	6	1	1	2	0	0	0	0	NA
2020	1	6	2	1	2	0	0	0	0	NA
2020	1	6	3	1	2	NA	NA	NA	NA	NA
2020	1	7	1	1	2	0	1	1	1	NA
2020	1	7	2	1	2	1	0	0	1	NA
2020	1	7	3	1	2	NA	NA	NA	NA	NA
2020	2	1	1	1	3	1	1	0	0	NA
2020	2	1	2	1	3	0	0	0	1	NA
2020	2	1	3	1	3	0	1	1	0	NA

question from:https://stackoverflow.com/questions/66046804/randomly-pick-a-value-from-a-set-of-rows-and-add-value-to-new-row-below

Answer 1

Here's one pipe that samples the new players and their scores into a separate frame, which you can then bind_rows back into the original data.

set.seed(2021)
newplayers <- dat %>%
  filter(!is.na(q1_a)) %>%
  group_by(Season, Episode, Round) %>%
  summarize(across(everything(), ~ sample(., size=1)), .groups = "drop") %>%
  mutate(Player = NA_integer_, Player_type = NA_integer_)
newplayers
# # A tibble: 8 x 11
#   Season Episode Round Player Player_type Crowd_size  q1_a  q2_a  q3_a  q4_a q5_a 
#    <int>   <int> <int>  <int>       <int>      <int> <int> <int> <int> <int> <lgl>
# 1   2020       1     1     NA          NA          3     0     0     1     1 NA   
# 2   2020       1     2     NA          NA          3     1     1     0     0 NA   
# 3   2020       1     3     NA          NA          3     0     1     1     0 NA   
# 4   2020       1     4     NA          NA          3     0     0     1     1 NA   
# 5   2020       1     5     NA          NA          2     1     1     1     0 NA   
# 6   2020       1     6     NA          NA          2     0     0     0     0 NA   
# 7   2020       1     7     NA          NA          2     0     0     1     1 NA   
# 8   2020       2     1     NA          NA          3     0     1     0     0 NA   

bind_rows(dat, newplayers) %>%
  arrange(Season, Episode, Round, is.na(Player), Player) %>%
  head(.)
#   Season Episode Round Player Player_type Crowd_size q1_a q2_a q3_a q4_a q5_a
# 1   2020       1     1      1           1          3    0    1    0    0   NA
# 2   2020       1     1      2           1          3    0    1    1    1   NA
# 3   2020       1     1      3           1          3    0    0    0    1   NA
# 4   2020       1     1     NA          NA          3    0    0    1    1   NA
# 5   2020       1     2      1           1          3    1    1    0    1   NA
# 6   2020       1     2      2           1          3    1    0    1    0   NA

I didn't know what values to put into Player*, so I chose NA.

---

Data

# dput(dat)
dat <- structure(list(Season = c(2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L, 2020L), Episode = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), Round = c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 1L, 1L, 1L), Player = c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), Player_type = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), Crowd_size = c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L), q1_a = c(0L, 0L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, NA, 0L, 0L, NA, 0L, 1L, NA, 1L, 0L, 0L), q2_a = c(1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L, 1L, NA, 0L, 0L, NA, 1L, 0L, NA, 1L, 0L, 1L), q3_a = c(0L, 1L, 0L, 0L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, NA, 0L, 0L, NA, 1L, 0L, NA, 0L, 0L, 1L), q4_a = c(0L, 1L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, NA, 0L, 0L, NA, 1L, 1L, NA, 0L, 1L, 0L), q5_a = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), class = "data.frame", row.names = c(NA, -24L))