I have a dataframe that contains an ID and Type column. I want a counter that if the Type is "T" then the counter in the next row would be counter + 1 for every ID. Basically, the counter is the Output_column in this example.
ID <- c(1,1,1,1,1,1,3,3,4,4,4,4)
Type <- c("A","A","T","A","A","A","A","A","T","A","T","A")
Output_Column <- c(1,1,1,2,2,2,1,1,1,2,2,3)
ID Type Output_Column
1 1 A 1
2 1 A 1
3 1 T 1
4 1 A 2
5 1 A 2
6 1 A 2
7 3 A 1
8 3 A 1
9 4 T 1
10 4 A 2
11 4 T 2
12 4 A 3
d <- data.frame(ID,Type, Output_Column)
baseR solution
output_col <- as.numeric(ave(Type, ID, FUN = function(x) cumsum(c('T', x[-length(x)]) == 'T')))
output_col
[1] 1 1 1 2 2 2 1 1 1 2 2 3
Here's data.table version :
library(data.table)
setDT(d)[, res := shift(cumsum(Type == 'T') + 1, fill = 1), ID]
d
# ID Type Output_Column res
# 1: 1 A 1 1
# 2: 1 A 1 1
# 3: 1 T 1 1
# 4: 1 A 2 2
# 5: 1 A 2 2
# 6: 1 A 2 2
# 7: 3 A 1 1
# 8: 3 A 1 1
# 9: 4 T 1 1
#10: 4 A 2 2
#11: 4 T 2 2
#12: 4 A 3 3
Here is a way to achieve it using group_by, lag, and cumsum
library(dplyr)
d %>%
# group by ID so calculation is within each ID
group_by(ID) %>%
mutate(
# create a counter variable check if previous Type is "T"
# Here default is "T" which result the first row of ID will start at 1
counter = if_else(lag(Type, default = "T") == "T", 1, 0),
# cumsum the counter which result same as the expected output column
output_column_calculated = cumsum(counter)) %>%
ungroup() %>%
# Remove the counter column if not needed
select(-counter)
#> # A tibble: 12 x 4
#> ID Type Output_Column output_column_calculated
#> <dbl> <chr> <dbl> <dbl>
#> 1 1 A 1 1
#> 2 1 A 1 1
#> 3 1 T 1 1
#> 4 1 A 2 2
#> 5 1 A 2 2
#> 6 1 A 2 2
#> 7 3 A 1 1
#> 8 3 A 1 1
#> 9 4 T 1 1
#> 10 4 A 2 2
#> 11 4 T 2 2
#> 12 4 A 3 3
Created on 2021-04-26 by the reprex package (v2.0.0)
Related
I have a data frame with multiple columns, the user provides a vector with the column names, and I want to count maximum amount of times an element appears
set.seed(42)
df <- tibble(
var1 = sample(c(1:3),10,replace=T),
var2 = sample(c(1:3),10,replace=T),
var3 = sample(c(1:3),10,replace=T)
)
select_vars <- c("var1", "var3")
df %>%
rowwise() %>%
mutate(consensus=max(table(unlist(c(var1,var3)))))
# A tibble: 10 x 4
# Rowwise:
var1 var2 var3 consensus
<int> <int> <int> <int>
1 1 1 1 2
2 1 1 3 1
3 1 2 1 2
4 1 2 1 2
5 2 2 2 2
6 2 3 3 1
7 2 3 2 2
8 1 1 1 2
9 3 1 2 1
10 3 3 2 1
This does exactly what I want, but when I try to use a vector of variables i cant get it to work
df %>%
rowwise() %>%
mutate(consensus=max(unlist(table(select_vars)) )))
You can wrap it in c(!!! syms()) to get it working, and you don't need the unlist apparently. But honestly, I'm not sure what you are trying to do, and why table is needed here. Do you just want to check if var2 and var3 are the same value and if then 2 and if not then 1?
library(dplyr)
df <- tibble(
var1 = sample(c(1:3),10,replace=T),
var2 = sample(c(1:3),10,replace=T),
var3 = sample(c(1:3),10,replace=T)
)
select_vars <- c("var2", "var3")
df %>%
rowwise() %>%
mutate(consensus=max(table(c(!!!syms(select_vars)))))
#> # A tibble: 10 x 4
#> # Rowwise:
#> var1 var2 var3 consensus
#> <int> <int> <int> <int>
#> 1 2 3 2 1
#> 2 3 1 3 1
#> 3 3 1 1 2
#> 4 3 3 3 2
#> 5 1 1 2 1
#> 6 2 1 3 1
#> 7 3 2 3 1
#> 8 1 2 3 1
#> 9 2 1 2 1
#> 10 2 1 1 2
Created on 2021-07-22 by the reprex package (v0.3.0)
In the OP's code, we need select
library(dplyr)
df %>%
rowwise() %>%
mutate(consensus=max(table(unlist(select(cur_data(), select_vars))) ))
-output
# A tibble: 10 x 4
# Rowwise:
var1 var2 var3 consensus
<int> <int> <int> <int>
1 1 1 1 2
2 1 1 3 1
3 1 2 1 2
4 1 2 1 2
5 2 2 2 2
6 2 3 3 1
7 2 3 2 2
8 1 1 1 2
9 3 1 2 1
10 3 3 2 1
Or just subset from cur_data() which would only return the data keeping the group attributes
df %>%
rowwise %>%
mutate(consensus = max(table(unlist(cur_data()[select_vars]))))
# A tibble: 10 x 4
# Rowwise:
var1 var2 var3 consensus
<int> <int> <int> <int>
1 1 1 1 2
2 1 1 3 1
3 1 2 1 2
4 1 2 1 2
5 2 2 2 2
6 2 3 3 1
7 2 3 2 2
8 1 1 1 2
9 3 1 2 1
10 3 3 2 1
Or using pmap
library(purrr)
df %>%
mutate(consensus = pmap_dbl(cur_data()[select_vars], ~ max(table(c(...)))))
# A tibble: 10 x 4
var1 var2 var3 consensus
<int> <int> <int> <dbl>
1 1 1 1 2
2 1 1 3 1
3 1 2 1 2
4 1 2 1 2
5 2 2 2 2
6 2 3 3 1
7 2 3 2 2
8 1 1 1 2
9 3 1 2 1
10 3 3 2 1
As these are rowwise operations, can get some efficiency if we use collapse functions
library(collapse)
tfm(df, consensus = dapply(slt(df, select_vars), MARGIN = 1,
FUN = function(x) fmax(tabulate(x))))
# A tibble: 10 x 4
var1 var2 var3 consensus
* <int> <int> <int> <int>
1 1 1 1 2
2 1 1 3 1
3 1 2 1 2
4 1 2 1 2
5 2 2 2 2
6 2 3 3 1
7 2 3 2 2
8 1 1 1 2
9 3 1 2 1
10 3 3 2 1
Benchmarks
As noted above, collapse is faster (run on a slightly bigger dataset)
df1 <- df[rep(seq_len(nrow(df)), 1e5), ]
system.time({
tfm(df1, consensus = dapply(slt(df1, select_vars), MARGIN = 1,
FUN = function(x) fmax(tabulate(x))))
})
#user system elapsed
# 5.257 0.123 5.323
system.time({
df1 %>%
mutate(consensus = pmap_dbl(cur_data()[select_vars], ~ max(table(c(...)))))
})
#user system elapsed
# 54.813 0.517 55.246
The rowwise operation is taking too much time, so stopped the execution
df1 %>%
rowwise() %>%
mutate(consensus=max(table(unlist(select(cur_data(), select_vars))) ))
})
Timing stopped at: 575.5 3.342 581.3
What you need is to use the verb all_of
df %>%
rowwise() %>%
mutate(consensus=max(table(unlist(all_of(select_vars)))))
# A tibble: 10 x 4
# Rowwise:
var1 var2 var3 consensus
<int> <int> <int> <int>
1 2 3 3 1
2 2 2 2 1
3 1 2 2 1
4 2 3 3 1
5 1 2 1 1
6 2 1 2 1
7 2 2 2 1
8 3 1 2 1
9 2 1 3 1
10 3 2 1 1
I would like conditionally mutate variables (var1, var2) within groups (id) at different timepoints (timepoint) using previously updated/muated values according to this function:
change_function <- function(value,pastvalue,timepoint){
if(timepoint==1){valuenew=value} else
if(value==0){valuenew=pastvalue-1}
if(value==1){valuenew=pastvalue}
if(value==2){valuenew=pastvalue+1}
return(valuenew)
}
pastvalue is the MUTATED/UPDATED value at timepoint -1 for timepoint 2:4
Here is an example and output file:
``` r
#example data
df <- data.frame(id=c(1,1,1,1,2,2,2,2),timepoint=c(1,2,3,4,1,2,3,4),var1=c(1,0,1,2,2,2,1,0),var2=c(2,0,1,2,3,2,1,0))
df
#> id timepoint var1 var2
#> 1 1 1 1 2
#> 2 1 2 0 0
#> 3 1 3 1 1
#> 4 1 4 2 2
#> 5 2 1 2 3
#> 6 2 2 2 2
#> 7 2 3 1 1
#> 8 2 4 0 0
#desired output
output <- data.frame(id=c(1,1,1,1,2,2,2,2),timepoint=c(1,2,3,4,1,2,3,4),var1=c(1,0,0,1,2,3,3,2),var2=c(2,1,1,2,3,4,4,3))
output
#> id timepoint var1 var2
#> 1 1 1 1 2
#> 2 1 2 0 1
#> 3 1 3 0 1
#> 4 1 4 1 2
#> 5 2 1 2 3
#> 6 2 2 3 4
#> 7 2 3 3 4
#> 8 2 4 2 3
```
<sup>Created on 2020-11-23 by the [reprex package](https://reprex.tidyverse.org) (v0.3.0)</sup>
My Approach: use my function using dplyr::mutate_at
library(dplyr)
df %>%
group_by(id) %>%
mutate_at(.vars=vars(var1,var2),
.funs=funs(.=change_function(.,dplyr::lag(.),timepoint)))
However, this does not work because if/else is not vectorized
Update 1:
Using a nested ifelse function does not give the desired output, because it does not use updated pastvalue's:
change_function <- function(value,pastvalue,timepoint){
ifelse((timepoint==1),value,
ifelse((value==0),pastvalue-1,
ifelse((value==1),pastvalue,
ifelse((value==2),pastvalue+1,NA))))
}
library(dplyr)
df %>%
group_by(id) %>%
mutate_at(.vars=vars(var1,var2),
.funs=funs(.=change_function(.,dplyr::lag(.),timepoint)))
id TimePoint var1 var2 var1_. var2_.
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 1 1 2 1 2
2 1 2 0 0 0 1
3 1 3 1 1 0 0
4 1 4 2 2 2 2
5 2 1 2 3 2 3
6 2 2 2 2 3 4
7 2 3 1 1 2 2
8 2 4 0 0 0 0
Update 2:
According to the comments, purrr:accumulate could be used
Thanks to akrun I could get the correct function:
# write a vectorized function
change_function <- function(prev, new) {
change=if_else(new==0,-1,
if_else(new==1,0,1))
if_else(is.na(new), new, prev + change)
}
# use purrr:accumulate
df %>%
group_by(id) %>%
mutate_at(.vars=vars(var1,var2),
.funs=funs(accumulate(.,change_function)))
# A tibble: 8 x 4
# Groups: id [2]
id timepoint var1 var2
<dbl> <dbl> <dbl> <dbl>
1 1 1 1 2
2 1 2 0 1
3 1 3 0 1
4 1 4 1 2
5 2 1 2 3
6 2 2 3 4
7 2 3 3 4
8 2 4 2 3
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
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
can anyone help me out in computing a new variable that will number a distinct combination from some factors?
Assuming there are 4 within subject factors (A, B, C, D) with 8 repetitions of each combination for any of 10 subjects, this is how my data could look like to represent it's actual structure:
library(AlgDesign) #for generating a factorial design)
df <-gen.factorial(c(2,2,2,2,8,10), factors = "all",
varNames = c("A", "B", "C", "D", "replication", "Subject"))
> head(df)
A B C D replication Subject
1 1 1 1 1 1 1
2 2 1 1 1 1 1
3 1 2 1 1 1 1
4 2 2 1 1 1 1
5 1 1 2 1 1 1
6 2 1 2 1 1 1
> tail(df)
A B C D replication Subject
1275 1 2 1 2 8 10
1276 2 2 1 2 8 10
1277 1 1 2 2 8 10
1278 2 1 2 2 8 10
1279 1 2 2 2 8 10
1280 2 2 2 2 8 10
In this example replication was simply generated in order to force 8 reps but it doesnt "code" the combintation itself.
My original data has only variables A, B, C, D and Subject and I'd like to compute replication in a way that it has distinct values
but for each combination of A, B, C, D
library(AlgDesign)
library(dplyr)
df <-gen.factorial(c(2,2,2,2,8,10), factors = "all",
varNames = c("A", "B", "C", "D", "replication", "Subject"))
df %>%
rowwise() %>% # for each row
mutate(factors = paste0(c(A,B,C,D), collapse = "_")) %>% # create a combination of your factors
ungroup() %>% # forget the row grouping
mutate(replication_upd = as.numeric(factor(factors))) # create a number based on the combination you have
# # A tibble: 1,280 x 8
# A B C D replication Subject factors replication_upd
# <fct> <fct> <fct> <fct> <fct> <fct> <chr> <dbl>
# 1 1 1 1 1 1 1 1_1_1_1 1
# 2 2 1 1 1 1 1 2_1_1_1 9
# 3 1 2 1 1 1 1 1_2_1_1 5
# 4 2 2 1 1 1 1 2_2_1_1 13
# 5 1 1 2 1 1 1 1_1_2_1 3
# 6 2 1 2 1 1 1 2_1_2_1 11
# 7 1 2 2 1 1 1 1_2_2_1 7
# 8 2 2 2 1 1 1 2_2_2_1 15
# 9 1 1 1 2 1 1 1_1_1_2 2
#10 2 1 1 2 1 1 2_1_1_2 10
# # ... with 1,270 more rows
You can remove any unnecessary variables. I left them there so you can see how the process works.
Another option is this
# create a look up table based on unique combinations and assign them a number
df %>% distinct(A,B,C,D) %>% mutate(replication_upd = row_number()) -> look_up
# join back to original dataset
df %>% inner_join(look_up, by=c("A","B","C","D")) %>% tbl_df()
# # A tibble: 1,280 x 7
# A B C D replication Subject replication_upd
# <fct> <fct> <fct> <fct> <fct> <fct> <int>
# 1 1 1 1 1 1 1 1
# 2 2 1 1 1 1 1 2
# 3 1 2 1 1 1 1 3
# 4 2 2 1 1 1 1 4
# 5 1 1 2 1 1 1 5
# 6 2 1 2 1 1 1 6
# 7 1 2 2 1 1 1 7
# 8 2 2 2 1 1 1 8
# 9 1 1 1 2 1 1 9
# 10 2 1 1 2 1 1 10
# # ... with 1,270 more rows
Note that the first approach picks the numbers based on the new variable we create (i.e. orders A,B,C,D), and the second approach uses the initial order of you dataset to pick the number for each unique combination.