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
Related
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
Suppose I have the following df
data <- data.frame(ID = c(1,1,1,1,1,1,1,2,2,2,2,3,3,3),
Value = c(1,1,0,1,0,1,1,1,0,0,1,0,0,0),
Result = c(1,1,2,3,4,5,5,1,2,2,3,1,1,1))
How can I obtain column Result from the first two columns?
I have tried different approaches using rle, seq, cumsum and cur_group_id but can't get the Result column easily
library(data.table)
library(dplyr)
data %>%
group_by(ID) %>%
mutate(Result2 = rleid(Value))
This gives us:
ID Value Result Result2
<dbl> <dbl> <dbl> <int>
1 1 1 1 1
2 1 1 1 1
3 1 0 2 2
4 1 1 3 3
5 1 0 4 4
6 1 1 5 5
7 1 1 5 5
8 2 1 1 1
9 2 0 2 2
10 2 0 2 2
11 2 1 3 3
12 3 0 1 1
13 3 0 1 1
14 3 0 1 1
Does this work:
library(dplyr)
data %>% group_by(ID) %>% mutate(r = rep(seq_along(rle(ID*Value)$values), rle(ID*Value)$lengths))
# A tibble: 14 x 4
# Groups: ID [3]
ID Value Result r
<dbl> <dbl> <dbl> <int>
1 1 1 1 1
2 1 1 1 1
3 1 0 2 2
4 1 1 3 3
5 1 0 4 4
6 1 1 5 5
7 1 1 5 5
8 2 1 1 1
9 2 0 2 2
10 2 0 2 2
11 2 1 3 3
12 3 0 1 1
13 3 0 1 1
14 3 0 1 1
We could use rle with ave in base R
data$Result2 <- with(data, ave(Value, ID, FUN =
function(x) inverse.rle(within.list(rle(x), values <- seq_along(values)))))
data$Result2
#[1] 1 1 2 3 4 5 5 1 2 2 3 1 1 1
I have data with 33 attribute. 30 of them is variable. And other 3 column is cluster number ,degree and sum of degree. I want to remove duplicate row which have same value from variable 1 until 30. Within duplicate row I want to choose the row which have highest values of sum degree to remain in the data. This coding is run in R. My question is how do I simplify zz.
df_order=dfOrder(rule2,c(33),ascending=FALSE)
df_order2=as_tibble(df_order)
zz=df_order2 %>% distinct(X1,X2,X3,X4,X5,X6,X7,X8,X9,X10,X11,X12,X13,X14,X15,X16,X17,X18,X19,X20,X21,X22,X23,X24,X25,X26,X27,X28,X29,X30,.keep_all = TRUE)
Sample data:
set.seed(42)
dat <- tibble(a=rep(1:2, each=10), b=rep(1:4, each=5), x1=sample(3,size=20,replace=TRUE), x2=sample(3,size=20,replace=TRUE), x3=sample(3,size=20,replace=TRUE))
dat
# # A tibble: 20 x 5
# a b x1 x2 x3
# <int> <int> <int> <int> <int>
# 1 1 1 1 1 3
# 2 1 1 1 3 3
# 3 1 1 1 1 1
# 4 1 1 1 1 1
# 5 1 1 2 2 2
# 6 1 2 2 3 2
# ...truncated...
Brute-force to show what distinct gives you:
distinct(dat, x1, x2, x3, .keep_all = TRUE)
# # A tibble: 14 x 5
# a b x1 x2 x3
# <int> <int> <int> <int> <int>
# 1 1 1 1 1 3
# 2 1 1 1 3 3
# 3 1 1 1 1 1
# 4 1 1 2 2 2
# 5 1 2 2 3 2
# 6 1 2 1 1 2
# 7 1 2 3 2 2
# 8 1 2 3 2 3
# 9 2 3 1 3 2
# 10 2 3 1 3 1
# 11 2 3 2 2 3
# 12 2 4 3 1 2
# 13 2 4 1 2 1
# 14 2 4 3 2 1
Programmatic way, without specifying each of x1 through x3, both work (depending on your preference towards "just use these" or "don't use those"). The first two work in base R and tidyverse equally well, the third is using dplyr::select.
dat[!duplicated(subset(dat, select = -(a:b))),]
dat[!duplicated(subset(dat, select = x1:x3)),]
dat[!duplicated(select(dat, x1:x3)),] # or -(a:b), same
Or perhaps a pipe-looking method:
select(dat, x1:x3) %>%
Negate(duplicated)(.) %>%
which(.) %>%
slice(dat, .)
Using the data from #r2evans post an option is to use splice after converting the column names to symbols
library(dplyr)
dat %>%
distinct(!!! rlang::syms(names(select(., starts_with('x')))), .keep_all = TRUE)
# A tibble: 14 x 5
# a b x1 x2 x3
# <int> <int> <int> <int> <int>
# 1 1 1 1 1 3
# 2 1 1 1 3 3
# 3 1 1 1 1 1
# 4 1 1 2 2 2
# 5 1 2 2 3 2
# 6 1 2 1 1 2
# 7 1 2 3 2 2
# 8 1 2 3 2 3
# 9 2 3 1 3 2
#10 2 3 1 3 1
#11 2 3 2 2 3
#12 2 4 3 1 2
#13 2 4 1 2 1
#14 2 4 3 2 1
From dplyr version >= 1.0.0, we can also use distinct with across
dat %>%
distinct(across(starts_with('x')), .keep_all = TRUE)
# A tibble: 14 x 5
# a b x1 x2 x3
# <int> <int> <int> <int> <int>
# 1 1 1 1 1 3
# 2 1 1 1 3 3
# 3 1 1 1 1 1
# 4 1 1 2 2 2
# 5 1 2 2 3 2
# 6 1 2 1 1 2
# 7 1 2 3 2 2
# 8 1 2 3 2 3
# 9 2 3 1 3 2
#10 2 3 1 3 1
#11 2 3 2 2 3
#12 2 4 3 1 2
#13 2 4 1 2 1
#14 2 4 3 2 1
A) Here is my data frame arranged by plate:
df <- read.table(header=TRUE, stringsAsFactors=FALSE, text="
plate phase score
A 1 1
A 1 1
A 1 1
A 2 1
A 2 1
A 2 1
A 3 2
A 3 2
A 3 2
B 1 1
B 1 1
B 1 2
B 2 1
B 2 1
B 2 3")
B) Goal: I want to order it by both plate first and then phase but sequentially (see below how the rows are ordered alphabetically by plate but sequentially by phase
plate phase score
<chr> <int> <int>
1 A 1 1
2 A 2 1
3 A 3 2
4 A 1 1
5 A 2 1
6 A 3 2
7 A 1 1
8 A 2 1
9 A 3 2
10 B 1 1
11 B 2 1
12 B 1 1
13 B 2 1
14 B 1 2
15 B 2 3
One option is to create a sequence variable grouped by 'plate', 'phase' and arrange on it along with 'plate' and 'score'
library(dplyr)
df %>%
group_by(plate, phase) %>%
mutate(rn = row_number()) %>%
ungroup %>%
arrange(plate, rn, score) %>%
select(-rn)
# A tibble: 15 x 3
# plate phase score
# <chr> <int> <int>
# 1 A 1 1
# 2 A 2 1
# 3 A 3 2
# 4 A 1 1
# 5 A 2 1
# 6 A 3 2
# 7 A 1 1
# 8 A 2 1
# 9 A 3 2
#10 B 1 1
#11 B 2 1
#12 B 1 1
#13 B 2 1
#14 B 1 2
#15 B 2 3
Or using data.table
library(data.table)
setDT(df)[order(plate, rowid(phase), score)]
df[with(df, order(plate, ave(phase, phase, FUN = seq_along), phase)),]
#> plate phase score
#> 1 A 1 1
#> 4 A 2 1
#> 7 A 3 2
#> 2 A 1 1
#> 5 A 2 1
#> 8 A 3 2
#> 3 A 1 1
#> 6 A 2 1
#> 9 A 3 2
#> 10 B 1 1
#> 13 B 2 1
#> 11 B 1 1
#> 14 B 2 1
#> 12 B 1 2
#> 15 B 2 3
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)))