I want to count the number of fluctuation of responses under the column response per id. However, responses No~ no ~ DK. I need to consider as the same response just only for count to the number of fluctuate in response. I don't change responses permanently.
df <- data.frame(
id=c(1,1,1,1,1,2,2,2,2,2,2,3,3,3,3,3,3,4,4,4,4,4,4),
response=c("Yes","Yes","No","DK","no","No","No","no","No","Yes","Yes","DK","No","Yes","Yes","No","No","No","died","TO","Yes","No","Yes")
)
I am trying it using the following code:
library(tidyverse)
df <- df %>%
group_by(id) %>% fill(response) %>%
mutate(new = rleid(response), rn = row_number()) %>%
mutate(flactuation = case_when(rn >2 & duplicated(new) ~ 'No', rn > 2 ~ 'Yes')) %>%
mutate(numberofchange = sum(flactuation=="Yes", na.rm = T)) %>% select(-rn, -flactuation)
Expected
id response new numberofchange
<dbl> <chr> <int> <int>
1 1 Yes 1 1
2 1 Yes 1 1
3 1 No 2 1
4 1 DK 2 1
5 1 no 2 1
6 2 No 1 1
7 2 No 1 1
8 2 no 1 1
9 2 No 1 1
10 2 Yes 2 1
11 2 Yes 2 1
12 3 DK 1 2
13 3 No 1 2
14 3 Yes 2 2
15 3 Yes 2 2
16 3 No 3 2
17 3 No 3 2
18 4 No 1 5
19 4 died 2 5
20 4 TO 3 5
21 4 Yes 4 5
22 4 No 5 5
23 4 Yes 6 5
You could use data.table::rleid() to get the run-length indices.
library(dplyr)
df %>%
group_by(id) %>%
mutate(new = data.table::rleid(replace(response, response %in% c('no', 'DK'), "No")),
numberofchange = max(new) - 1) %>%
ungroup()
# A tibble: 23 × 4
id response new numberofchange
<dbl> <chr> <int> <dbl>
1 1 Yes 1 1
2 1 Yes 1 1
3 1 No 2 1
4 1 DK 2 1
5 1 no 2 1
6 2 No 1 1
7 2 No 1 1
8 2 no 1 1
9 2 No 1 1
10 2 Yes 2 1
11 2 Yes 2 1
12 3 DK 1 2
13 3 No 1 2
14 3 Yes 2 2
15 3 Yes 2 2
16 3 No 3 2
17 3 No 3 2
18 4 No 1 5
19 4 died 2 5
20 4 TO 3 5
21 4 Yes 4 5
22 4 No 5 5
23 4 Yes 6 5
Related
A sample of my data is :
dat <- read.table(text = " ID BC1 DC1 DE1 MN2 DC2 PO2 SA3 BC3 KL3 AA4 AP4 BC4 PO4
1 2 1 2 3 1 3 1 1 3 2 2 2 2
2 3 1 1 2 3 1 1 2 3 1 1 3 2
3 2 3 2 3 2 3 2 1 1 3 1 1 1
4 3 3 1 1 1 1 1 2 2 1 2 1 2", header = TRUE)
I want to get the following table and missing data are blank
ID Group1 Group2 Group3 Group4
1 2 1 2
2 3 1 1
3 2 3 2
4 3 3 1
1 3 1 3
2 2 3 1
3 3 2 3
4 1 1 1
1 1 1 3
2 1 2 3
3 2 1 1
4 1 2 2
1 2 2 2 2
2 1 1 3 2
3 3 1 1 1
4 1 2 1 2
The number in front of each column is where the columns are separated from each other. For example BC1, DC1 and DE1. They form the first four rows with their Ids and MN2, DC2 and PO2 form the second rows with their IDs and so on.
What about using the row numbers with some pivoting?
library(dplyr)
library(tidyr)
dat |>
pivot_longer(-ID, names_sep = "(?=\\d)", names_to = c(NA, "id")) |>
group_by(ID, id) |>
mutate(name = row_number()) |>
pivot_wider(c(ID, id), names_prefix = "Group") |>
arrange(id) |>
ungroup() |>
select(-id)
Or using a map:
library(purrr)
library(dplyr)
paste(1:4) |> # unique(readr::parse_number(names(dat |> select(-ID))))
map(\(x) select(dat, ID, ends_with(x)) |> rename_with(\(x) names(x) <- paste0("Group", 1:length(x)), -ID)) |>
bind_rows()
Output:
# A tibble: 16 × 5
ID Group1 Group2 Group3 Group4
<int> <int> <int> <int> <int>
1 1 2 1 2 NA
2 2 3 1 1 NA
3 3 2 3 2 NA
4 4 3 3 1 NA
5 1 3 1 3 NA
6 2 2 3 1 NA
7 3 3 2 3 NA
8 4 1 1 1 NA
9 1 1 1 3 NA
10 2 1 2 3 NA
11 3 2 1 1 NA
12 4 1 2 2 NA
13 1 2 2 2 2
14 2 1 1 3 2
15 3 3 1 1 1
16 4 1 2 1 2
Update 13-01: Now the first solution returns the correct ID (not id) + another approach added.
Would be interesting to see if there is an easier approach:
library(tidyverse)
dat |>
pivot_longer(-ID) |>
mutate(id = str_extract(name, "\\d$")) |>
group_by(ID, id) |>
mutate(name = paste0("Group", row_number())) |>
ungroup() |>
pivot_wider(names_from = name, values_from = value) |>
arrange(id, ID) |>
select(-id)
#> # A tibble: 16 × 5
#> ID Group1 Group2 Group3 Group4
#> <int> <int> <int> <int> <int>
#> 1 1 2 1 2 NA
#> 2 2 3 1 1 NA
#> 3 3 2 3 2 NA
#> 4 4 3 3 1 NA
#> 5 1 3 1 3 NA
#> 6 2 2 3 1 NA
#> 7 3 3 2 3 NA
#> 8 4 1 1 1 NA
#> 9 1 1 1 3 NA
#> 10 2 1 2 3 NA
#> 11 3 2 1 1 NA
#> 12 4 1 2 2 NA
#> 13 1 2 2 2 2
#> 14 2 1 1 3 2
#> 15 3 3 1 1 1
#> 16 4 1 2 1 2
You can rename the data with a specified pattern ("index1_index2"), i.e.
# ID 1_1 1_2 1_3 2_1 2_2 2_3 3_1 3_2 3_3 4_1 4_2 4_3 4_4
# 1 1 2 1 2 3 1 3 1 1 3 2 2 2 2
# 2 2 3 1 1 2 3 1 1 2 3 1 1 3 2
# 3 3 2 3 2 3 2 3 2 1 1 3 1 1 1
# 4 4 3 3 1 1 1 1 1 2 2 1 2 1 2
so that you can add the special element ".value" to names_to when using pivot_longer() to stack multiple columns that are grouped by that pattern.
Code
library(dplyr)
library(tidyr)
dat %>%
rename_with(~ sub('\\D+', '', .x) %>%
paste(., ave(., ., FUN = seq), sep = '_'), -ID) %>%
pivot_longer(-ID, names_to = c("set", ".value"), names_sep = '_') %>%
arrange(set) %>%
select(-set)
Output
# A tibble: 16 × 5
ID `1` `2` `3` `4`
<int> <int> <int> <int> <int>
1 1 2 1 2 NA
2 2 3 1 1 NA
3 3 2 3 2 NA
4 4 3 3 1 NA
5 1 3 1 3 NA
6 2 2 3 1 NA
7 3 3 2 3 NA
8 4 1 1 1 NA
9 1 1 1 3 NA
10 2 1 2 3 NA
11 3 2 1 1 NA
12 4 1 2 2 NA
13 1 2 2 2 2
14 2 1 1 3 2
15 3 3 1 1 1
16 4 1 2 1 2
HAVE = data.frame("TRIMESTER" = c(1,1,1,1,1,2,2,2,2,2,3,3,3,3,4,4,4,4,4,4),
"STUDENT" = c(1,2,3,3,4,2,5,6,7,1,2,2,2,2,2,1,2,3,4,5))
HAVE$WANT1 = c(4,4,4,4,4,5,5,5,5,5,1,1,1,1,5,5,5,5,5,5)
HAVE$WANT2 = c(0,0,0,0,0,1,1,1,1,1,0,0,0,0,1,1,1,1,1,1)
I have HAVE and wish to APPEND a column to count the UNIQUE value of STUDENT for every TRIMESTER shown WANT1 and I wish to create WANT2 which is the SUM of times for every TRIMESTER that STUDENT==5 appears so STUDENT==5 appear ZERO times in TRIMESTER == 1, so the value for all TRIMESTER == 1 is ZERO but student 5 appear ONCE in TRIMESTER==4 so the value is 1
After grouping by 'TRIMESTER', get the count of distinct elements of 'STUDENT' with n_distinct and the count of STUDENT 5 with sum on a logical expression
library(dplyr)
HAVE %>%
group_by(TRIMESTER) %>%
mutate(WANT1new = n_distinct(STUDENT),
WANT2NEW = sum(STUDENT == 5)) %>%
ungroup
-output
# A tibble: 20 × 6
TRIMESTER STUDENT WANT1 WANT2 WANT1new WANT2NEW
<dbl> <dbl> <dbl> <dbl> <int> <int>
1 1 1 4 0 4 0
2 1 2 4 0 4 0
3 1 3 4 0 4 0
4 1 3 4 0 4 0
5 1 4 4 0 4 0
6 2 2 5 1 5 1
7 2 5 5 1 5 1
8 2 6 5 1 5 1
9 2 7 5 1 5 1
10 2 1 5 1 5 1
11 3 2 1 0 1 0
12 3 2 1 0 1 0
13 3 2 1 0 1 0
14 3 2 1 0 1 0
15 4 2 5 1 5 1
16 4 1 5 1 5 1
17 4 2 5 1 5 1
18 4 3 5 1 5 1
19 4 4 5 1 5 1
20 4 5 5 1 5 1
The code below should produce the desired result.
library(dplyr)
HAVE %>%
group_by(TRIMESTER) %>%
mutate(WANT1 = length(unique(STUDENT)),
WANT2 = as.numeric(any(5 == STUDENT)))
I have a series of rows in a single dataframe. I'm trying to aggregate the first two rows for each ID- i.e. - I want to combine events 1 and 2 for ID 1 into a single row, events 1 and 2 for ID 2 into a singlw row etc, but leave event 3 completely untouched.
id <- c(1,1,1,2,2,2,3,3,3,4,4,4,5,5,5)
event <- c(1,2,3,1,2,3,1,2,3,1,2,3,1,2,3)
score <- c(3,NA,1,3,NA,2,6,NA,1,8,NA,2,4,NA,1)
score2 <- c(NA,4,1,NA,5,2,NA,0,3,NA,5,6,NA,8,7)
df <- tibble(id, event, score, score2)
# A tibble: 15 x 4
id event score score2
<dbl> <dbl> <dbl> <dbl>
1 1 1 3 NA
2 1 2 NA 4
3 1 3 1 1
4 2 1 3 NA
5 2 2 NA 5
6 2 3 2 2
7 3 1 6 NA
8 3 2 NA 0
9 3 3 1 3
10 4 1 8 NA
11 4 2 NA 5
12 4 3 2 6
13 5 1 4 NA
14 5 2 NA 8
15 5 3 1 7
I've tried :
df_merged<- df %>% group_by (id) %>% summarise_all(funs(min(as.character(.),na.rm=TRUE))),
which aggregates these nicely, but then I struggle to merge these back into the orignal dataframe/tibble (there are really about 300 different "score" columns in the full dataset, so a right_join is a headache with score.x, score.y, score2.x, score2.y all over the place...)
Ideally, the situation would need to be dplyr as the rest of my code runs on this!
EDIT:
Ideally, my expected output would be:
# A tibble: 10 x 4
id event score score2
<dbl> <dbl> <dbl> <dbl>
1 1 1 3 4
3 1 3 1 1
4 2 1 3 5
6 2 3 2 2
7 3 1 6 0
9 3 3 1 3
10 4 1 8 5
12 4 3 2 6
13 5 1 4 8
15 5 3 1 7
We may change the order of NA elements with replace
library(dplyr)
df %>%
group_by(id) %>%
mutate(across(starts_with('score'),
~replace(., 1:2, .[1:2][order(is.na(.[1:2]))]))) %>%
ungroup %>%
filter(if_all(starts_with('score'), Negate(is.na)))
-output
# A tibble: 10 x 4
id event score score2
<dbl> <dbl> <dbl> <dbl>
1 1 1 3 4
2 1 3 1 1
3 2 1 3 5
4 2 3 2 2
5 3 1 6 0
6 3 3 1 3
7 4 1 8 5
8 4 3 2 6
9 5 1 4 8
10 5 3 1 7
Here is an alternative way to achieve your task with fill from tidyr package:
library(dplyr)
library(tidyr)
df %>%
group_by(id) %>%
fill(everything(), .direction = "down") %>%
fill(everything(), .direction = "up") %>%
slice(1,3)
id event score score2
<dbl> <dbl> <dbl> <dbl>
1 1 1 3 4
2 1 3 1 1
3 2 1 3 5
4 2 3 2 2
5 3 1 6 0
6 3 3 1 3
7 4 1 8 5
8 4 3 2 6
9 5 1 4 8
10 5 3 1 7
How about this?
library(dplyr)
df_e12 <- df %>%
filter(event %in% c(1, 2)) %>%
group_by(id) %>%
mutate(across(starts_with("score"), ~min(.x, na.rm = TRUE))) %>%
ungroup() %>%
distinct(id, .keep_all = TRUE)
df_e3 <- df %>%
filter(event == 3)
df <- bind_rows(df_e12, df_e3) %>%
arrange(id, event)
df
> df
# A tibble: 10 x 4
id event score score2
<dbl> <dbl> <dbl> <dbl>
1 1 1 3 4
2 1 3 1 1
3 2 1 3 5
4 2 3 2 2
5 3 1 6 0
6 3 3 1 3
7 4 1 8 5
8 4 3 2 6
9 5 1 4 8
10 5 3 1 7
data
data=data.frame("person"=c(1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2),
"score"=c(1,2,1,2,3,1,3,NA,4,2,1,NA,2,NA,3,1,2,4),
"want"=c(1,2,1,2,3,3,3,3,4,2,1,1,2,2,3,3,3,4))
attempt
library(dplyr)
data = data %>%
group_by(person) %>%
mutate(wantTEST = ifelse(score >= 3 | (row_number() >= which.max(score == 3)),
cummax(score), score),
wantTEST = replace(wantTEST, duplicated(wantTEST == 4) & wantTEST == 4, NA))
i am basically working to use the cummax function but only under specific circumstances. i want to keep any values (1-2-1-1) except if there is a 3 or 4 (1-2-1-3-2-1-4) should be (1-2-1-3-3-4). if there is NA value i want to carry forward previous value. thank you.
Here's one way with tidyverse. You may want to use fill() after group_by() but that's somewhat unclear.
data %>%
fill(score) %>%
group_by(person) %>%
mutate(
w = ifelse(cummax(score) > 2, cummax(score), score)
) %>%
ungroup()
# A tibble: 18 x 4
person score want w
<dbl> <dbl> <dbl> <dbl>
1 1 1 1 1
2 1 2 2 2
3 1 1 1 1
4 1 2 2 2
5 1 3 3 3
6 1 1 3 3
7 1 3 3 3
8 1 3 3 3
9 1 4 4 4
10 2 2 2 2
11 2 1 1 1
12 2 1 1 1
13 2 2 2 2
14 2 2 2 2
15 2 3 3 3
16 2 1 3 3
17 2 2 3 3
18 2 4 4 4
One way to do this is to first fill NA values and then for each row check if anytime the score of 3 or more is passed in the group. If the score of 3 is reached till that point we take the max score until that point or else return the same score.
library(tidyverse)
data %>%
fill(score) %>%
group_by(person) %>%
mutate(want1 = map_dbl(seq_len(n()), ~if(. >= which.max(score == 3))
max(score[seq_len(.)]) else score[.]))
# person score want want1
# <dbl> <dbl> <dbl> <dbl>
# 1 1 1 1 1
# 2 1 2 2 2
# 3 1 1 1 1
# 4 1 2 2 2
# 5 1 3 3 3
# 6 1 1 3 3
# 7 1 3 3 3
# 8 1 3 3 3
# 9 1 4 4 4
#10 2 2 2 2
#11 2 1 1 1
#12 2 1 1 1
#13 2 2 2 2
#14 2 2 2 2
#15 2 3 3 3
#16 2 1 3 3
#17 2 2 3 3
#18 2 4 4 4
Another way is to use accumulate from purrr. I use if_else_ from hablar for type stability:
library(tidyverse)
library(hablar)
data %>%
fill(score) %>%
group_by(person) %>%
mutate(wt = accumulate(score, ~if_else_(.x > 2, max(.x, .y), .y)))
I want to create two variables giving me the total number of positive and negative values by id, hopefully using dplyr.
Example data:
library(dplyr)
set.seed(42)
df <- data.frame (id=rep(1:10,each=10),
ff=rnorm(100, 0,14 ))
> head(df,20)
id ff
1 1 19.1934183
2 1 -7.9057744
3 1 5.0837978
4 1 8.8600765
5 1 5.6597565
6 1 -1.4857432
7 1 21.1613080
8 1 -1.3252265
9 1 28.2579320
10 1 -0.8779974
11 2 18.2681752
12 2 32.0130355
13 2 -19.4440498
14 2 -3.9030427
15 2 -1.8664987
16 2 8.9033056
17 2 -3.9795409
18 2 -37.1903759
19 2 -34.1665370
20 2 18.4815868
the resulting dataset should look like:
> head(df,20)
id ff pos neg
1 1 19.1934183 6 4
2 1 -7.9057744 6 4
3 1 5.0837978 6 4
4 1 8.8600765 6 4
5 1 5.6597565 6 4
6 1 -1.4857432 6 4
7 1 21.1613080 6 4
8 1 -1.3252265 6 4
9 1 28.2579320 6 4
10 1 -0.8779974 6 4
11 2 18.2681752 4 6
12 2 32.0130355 4 6
13 2 -19.4440498 4 6
14 2 -3.9030427 4 6
15 2 -1.8664987 4 6
16 2 8.9033056 4 6
17 2 -3.9795409 4 6
18 2 -37.1903759 4 6
19 2 -34.1665370 4 6
20 2 18.4815868 4 6
I have thought something similar to this will work:
df<-df%>% group_by(id) %>% mutate(pos= nrow(ff>0)) %>% ungroup()
Any help would be great, thanks.
You need sum():
df %>% group_by(id) %>%
mutate(pos = sum(ff>0),
neg = sum(ff<0))
For a fun (and a fast) solution data.table can also be used:
library(data.table)
setDT(df)
df[, ":="(pos = sum(ff > 0), neg = sum(ff < 0)), by = id]
Here's an answer that add the ifelse part of your question:
df <- df %>% group_by(id) %>%
mutate(pos = sum(ff>0), neg = sum(ff<0)) %>%
group_by(id) %>%
mutate(any_neg=ifelse(any(ff < 0), 1, 0))
Output:
> head(df, 20)
Source: local data frame [20 x 5]
Groups: id [2]
id ff pos neg any_neg
<int> <dbl> <int> <int> <dbl>
1 1 19.1934183 6 4 1
2 1 -7.9057744 6 4 1
3 1 5.0837978 6 4 1
4 1 8.8600765 6 4 1
5 1 5.6597565 6 4 1
6 1 -1.4857432 6 4 1
7 1 21.1613080 6 4 1
8 1 -1.3252265 6 4 1
9 1 28.2579320 6 4 1
10 1 -0.8779974 6 4 1
11 2 18.2681752 4 6 1
12 2 32.0130355 4 6 1
13 2 -19.4440498 4 6 1
14 2 -3.9030427 4 6 1
15 2 -1.8664987 4 6 1
16 2 8.9033056 4 6 1
17 2 -3.9795409 4 6 1
18 2 -37.1903759 4 6 1
19 2 -34.1665370 4 6 1
20 2 18.4815868 4 6 1