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)))
Related
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
I have some results cluster labels from kmeans done on different ids (reprex example below). the problem is the kmeans clusters codes are not ordered consistently across ids although all ids have 3 clusters.
reprex = data.frame(id = rep(1:2, each = 41,
v1 = rep(seq(1:4), 2),
cluster = c(2,2,1,3,3,1,2,2))
reprex
id v1 cluster
1 1 1 2
2 1 2 2
3 1 3 1
4 1 4 3
5 2 1 3
6 2 2 1
7 2 3 2
8 2 4 2
what I want is that the variable cluster should always start with 1 within each ID. Note I don't want to reorder that dataframe by cluster, the order needs to remain the same. so the desired result would be:
reprex_desired<- data.frame(id = rep(1:2, each = 4),
v1 = rep(seq(1:4), 2),
cluster = c(2,2,1,3,3,1,2,2),
what_iWant = c(1,1,2,3,1,2,3,3))
reprex_desired
id v1 cluster what_iWant
1 1 1 2 1
2 1 2 2 1
3 1 3 1 2
4 1 4 3 3
5 2 1 3 1
6 2 2 1 2
7 2 3 2 3
8 2 4 2 3
We can use match after grouping by 'id'
library(dplyr)
reprex <- reprex %>%
group_by(id) %>%
mutate(what_IWant = match(cluster, unique(cluster))) %>%
ungroup
-output
reprex
# A tibble: 8 × 4
id v1 cluster what_IWant
<int> <int> <dbl> <int>
1 1 1 2 1
2 1 2 2 1
3 1 3 1 2
4 1 4 3 3
5 2 1 3 1
6 2 2 1 2
7 2 3 2 3
8 2 4 2 3
Here is a version with cumsum combined with lag:
library(dplyr)
df %>%
group_by(id) %>%
mutate(what_i_want = cumsum(cluster != lag(cluster, def = first(cluster)))+1)
id v1 cluster what_i_want
<int> <int> <dbl> <dbl>
1 1 1 2 1
2 1 2 2 1
3 1 3 1 2
4 1 4 3 3
5 2 1 3 1
6 2 2 1 2
7 2 3 2 3
8 2 4 2 3
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
Say I have something like:
df<-data.frame(group=c(1, 1,1, 2,2,2,3,3,3,4,4, 1, 1,1),
group2=c(1,2,3,1,2,3,1,2,3,1,3, 1,2,3))
group group2
1 1 1
2 1 2
3 1 3
4 2 1
5 2 2
6 2 3
7 3 1
8 3 2
9 3 3
10 4 1
11 4 3
12 1 1
13 1 2
14 1 3
My goal is to count the number of unique instances for group= something and group2= something. Like so:
df1<-df%>%group_by(group, group2)%>% mutate(want=n())%>%distinct(group, group2, .keep_all=TRUE)
group group2 want
<dbl> <dbl> <int>
1 1 1 2
2 1 2 2
3 1 3 2
4 2 1 1
5 2 2 1
6 2 3 1
7 3 1 1
8 3 2 1
9 3 3 1
10 4 1 1
11 4 3 1
however, notice that group=4, group2=2 was not in my dataset to begin with. Is there some sort of autofill function where I can fill these non-observations with a zero to get below easily?:
group group2 want
<dbl> <dbl> <int>
1 1 1 2
2 1 2 2
3 1 3 2
4 2 1 1
5 2 2 1
6 2 3 1
7 3 1 1
8 3 2 1
9 3 3 1
10 4 1 1
11 4 2 0
12 4 3 1
After getting the count, we can expand with complete to fill the missing combinations with 0
library(dplyr)
library(tidyr)
df %>%
count(group, group2) %>%
complete(group, group2, fill = list(n = 0))
# A tibble: 12 x 3
# group group2 n
# <dbl> <dbl> <dbl>
# 1 1 1 2
# 2 1 2 2
# 3 1 3 2
# 4 2 1 1
# 5 2 2 1
# 6 2 3 1
# 7 3 1 1
# 8 3 2 1
# 9 3 3 1
#10 4 1 1
#11 4 2 0
#12 4 3 1
Or if we do the group_by, instead of mutate and then do the distinct, directly use the summarise
df %>%
group_by(group, group2) %>%
summarise(n = n()) %>%
ungroup %>%
complete(group, group2, fill = list(n = 0))
Here is a data.table approach solution to this problem:
library(data.table)
setDT(df)[CJ(group, group2, unique = TRUE),
c(.SD, .(want = .N)), .EACHI,
on = c("group", "group2")]
# group group2 want
# 1 1 2
# 1 2 2
# 1 3 2
# 2 1 1
# 2 2 1
# 2 3 1
# 3 1 1
# 3 2 1
# 3 3 1
# 4 1 1
# 4 2 0
# 4 3 1
I am trying to figure out the dplyr way to do grouped differences.
Here is some fake data:
>crossing(year=seq(1,4),week=seq(1,3)) %>%
mutate(value = c(rep(4,3),rep(3,3),rep(2,3),rep(1,3)))
year week value
<int> <int> <dbl>
1 1 1 4
2 1 2 4
3 1 3 4
4 2 1 3
5 2 2 3
6 2 3 3
7 3 1 2
8 3 2 2
9 3 3 2
10 4 1 1
11 4 2 1
12 4 3 1
What I would like is year 1- year2, year2-year3, and year3-year4. The result would like like the following.
year week diffs
<int> <int> <dbl>
1 1 1 1
2 1 2 1
3 1 3 1
4 2 1 1
5 2 2 1
6 2 3 1
7 3 1 1
8 3 2 1
9 3 3 1
Edit:
I apologize. I was trying to make a simple reprex, but I messed up a lot.
Please let me know what the proper etiquette is. I don't want to ruffle any feathers.
I did not know that -diff() was a function. What I am actually looking for is percent difference ((new-old)/old)*100 and I am not able to find a straight forward way to use diff to get that value.
I am starting from the largest year. Adding a arrange(desc(year)) to the above code is what I have. I would be trimming the smallest year not the largest.
If this edit with worth a separate question let me know.
If you don't have missing years for each week:
df %>%
arrange(year) %>%
group_by(week) %>%
mutate(diffs = value - lead(value)) %>%
na.omit() %>% select(-value)
# A tibble: 9 x 3
# Groups: week [3]
# year week diffs
# <int> <int> <dbl>
#1 1 1 1
#2 1 2 1
#3 1 3 1
#4 2 1 1
#5 2 2 1
#6 2 3 1
#7 3 1 1
#8 3 2 1
#9 3 3 1
You can use diff, but it needs adjusting, as it subtracts the other way and returns a vector that's one shorter than what it's passed:
library(tidyverse)
diffed <- crossing(year = seq(1,4),
week = seq(1,3)) %>%
mutate(value = rep(4:1, each = 3)) %>%
group_by(week) %>%
mutate(value = c(-diff(value), NA)) %>%
drop_na(value)
diffed
#> # A tibble: 9 x 3
#> # Groups: week [3]
#> year week value
#> <int> <int> <int>
#> 1 1 1 1
#> 2 1 2 1
#> 3 1 3 1
#> 4 2 1 1
#> 5 2 2 1
#> 6 2 3 1
#> 7 3 1 1
#> 8 3 2 1
#> 9 3 3 1
using dplyr and do:
library(dplyr)
df %>% group_by(week) %>% do(cbind(.[-nrow(.),1:2],diffs=-diff(.$value)))
# # A tibble: 9 x 3
# # Groups: week [3]
# year week diffs
# <int> <int> <dbl>
# 1 1 1 1
# 2 2 1 1
# 3 3 1 1
# 4 1 2 1
# 5 2 2 1
# 6 3 2 1
# 7 1 3 1
# 8 2 3 1
# 9 3 3 1