#There are solution to replace mutate () ?code below:
df <- data.frame(A = c(12,71,53,34,21),
B = c(23, 41, 32, 58, 26),
C=c(12,1,3,5,6),
D=c(12,4,7,8,11),
E=c(11,33,45,67,89)
)
df
library(dplyr)
df_new<-mutate(df,Y=A-B,Z=A-C,U=A-D,W=A-E)
df_new
It depends on how esoteric you want to be but there is an interesting solution in {data.table}. You will probably have to install the {data.table} package.
install.packages("data.table")
Note that I am reading in the data as a data.table rather than as a data.frame.
library(data.table)
DT <- data.table(A = c(12,71,53,34,21),
B = c(23, 41, 32, 58, 26),
C=c(12,1,3,5,6),
D=c(12,4,7,8,11),
E=c(11,33,45,67,89))
NewDT <- DT
NewDT[, c("Y", "Z", "U", "W") := .(A - B, A - C, A - D, A - E )]
NewDT
# Or if you only want to keep the new variables
DX <- DT[, .(Y = A - B, Z = A - C, U = A - D, W = A - E)]
DX
1 Like
#>Can we use; for loop,,,?
It probably could be done but compared to the {dplyr} "mutate()" or the {data.table} approach I think it would be much clumsier.
The general advice in R is to only use a "for loop" if there is nothing else.
Also, Danut, what you can do depends on the version of dplyr you have access to — does your version contain the across() function?
Yes contain across()function
The across() function is a poweful loop substitute in this context. I'm not sure if there's a difference between what my and your versions can do, but here is what can be done with mine:
df <-
data.frame(
A = c(12,71,53,34,21),
B = c(23, 41, 32, 58, 26),
C = c(12,1,3,5,6),
D = c(12,4,7,8,11),
E = c(11,33,45,67,89)
)
df
#> A B C D E
#> 1 12 23 12 12 11
#> 2 71 41 1 4 33
#> 3 53 32 3 7 45
#> 4 34 58 5 8 67
#> 5 21 26 6 11 89
library(tidyverse)
# applying to each column, without changing column names
df |>
# using anonymous function of the form \(input) {...; ...; output}
mutate(
across(
B:E,
\(column) A - column
)
)
#> A B C D E
#> 1 12 -11 0 0 1
#> 2 71 30 70 67 38
#> 3 53 21 50 46 8
#> 4 34 -24 29 26 -33
#> 5 21 -5 15 10 -68
# applying to each column, but changing column names
df |>
mutate(
across(
B:E,
\(column) A - column,
# construct name using internal .col variable
.names = 'A - {.col}')
)
#> A B C D E A - B A - C A - D A - E
#> 1 12 23 12 12 11 -11 0 0 1
#> 2 71 41 1 4 33 30 70 67 38
#> 3 53 32 3 7 45 21 50 46 8
#> 4 34 58 5 8 67 -24 29 26 -33
#> 5 21 26 6 11 89 -5 15 10 -68
# alternative to using anonynmous function
df |>
mutate(
across(
B:E,
# using named function
list(A = \(column) A - column),
# construct name using internal .fn and .col variables
.names = '{.fn} - {.col}')
) |> as_tibble()
#> # A tibble: 5 × 9
#> A B C D E `A - B` `A - C` `A - D` `A - E`
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 12 23 12 12 11 -11 0 0 1
#> 2 71 41 1 4 33 30 70 67 38
#> 3 53 32 3 7 45 21 50 46 8
#> 4 34 58 5 8 67 -24 29 26 -33
#> 5 21 26 6 11 89 -5 15 10 -68
# applying multiple functions to each column
df |>
mutate(
across(
B:E,
# using named functions, but with backticks since names are nonsyntactic
list(
`A - ` = \(column) A - column,
`A + ` = \(column) A + column
),
.names = '{.fn}{.col}')
)
#> A B C D E A - B A + B A - C A + C A - D A + D A - E A + E
#> 1 12 23 12 12 11 -11 35 0 24 0 24 1 23
#> 2 71 41 1 4 33 30 112 70 72 67 75 38 104
#> 3 53 32 3 7 45 21 85 50 56 46 60 8 98
#> 4 34 58 5 8 67 -24 92 29 39 26 42 -33 101
#> 5 21 26 6 11 89 -5 47 15 27 10 32 -68 110
Created on 2024-04-03 with reprex v2.0.2
full reprex (click to open)
df <-
data.frame(
A = c(12,71,53,34,21),
B = c(23, 41, 32, 58, 26),
C = c(12,1,3,5,6),
D = c(12,4,7,8,11),
E = c(11,33,45,67,89)
)
df
#> A B C D E
#> 1 12 23 12 12 11
#> 2 71 41 1 4 33
#> 3 53 32 3 7 45
#> 4 34 58 5 8 67
#> 5 21 26 6 11 89
library(tidyverse)
# applying to each column, without changing column names
df |>
# using anonymous function of the form \(input) {...; ...; output}
mutate(
across(
B:E,
\(column) A - column
)
)
#> A B C D E
#> 1 12 -11 0 0 1
#> 2 71 30 70 67 38
#> 3 53 21 50 46 8
#> 4 34 -24 29 26 -33
#> 5 21 -5 15 10 -68
# applying to each column, but changing column names
df |>
mutate(
across(
B:E,
\(column) A - column,
# construct name using internal .col variable
.names = 'A - {.col}')
)
#> A B C D E A - B A - C A - D A - E
#> 1 12 23 12 12 11 -11 0 0 1
#> 2 71 41 1 4 33 30 70 67 38
#> 3 53 32 3 7 45 21 50 46 8
#> 4 34 58 5 8 67 -24 29 26 -33
#> 5 21 26 6 11 89 -5 15 10 -68
# alternative to using anonynmous function
df |>
mutate(
across(
B:E,
# using name function
list(A = \(column) A - column),
# construct name using internal .fn and .col variables
.names = '{.fn} - {.col}')
) |> as_tibble()
#> # A tibble: 5 × 9
#> A B C D E `A - B` `A - C` `A - D` `A - E`
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 12 23 12 12 11 -11 0 0 1
#> 2 71 41 1 4 33 30 70 67 38
#> 3 53 32 3 7 45 21 50 46 8
#> 4 34 58 5 8 67 -24 29 26 -33
#> 5 21 26 6 11 89 -5 15 10 -68
# applying multiple functions to each column
df |>
mutate(
across(
B:E,
# using named functions, but with backticks since names are nonsyntactic
list(
`A - ` = \(column) A - column,
`A + ` = \(column) A + column
),
.names = '{.fn}{.col}')
)
#> A B C D E A - B A + B A - C A + C A - D A + D A - E A + E
#> 1 12 23 12 12 11 -11 35 0 24 0 24 1 23
#> 2 71 41 1 4 33 30 112 70 72 67 75 38 104
#> 3 53 32 3 7 45 21 85 50 56 46 60 8 98
#> 4 34 58 5 8 67 -24 92 29 39 26 42 -33 101
#> 5 21 26 6 11 89 -5 47 15 27 10 32 -68 110
Created on 2024-04-03 with reprex v2.0.2
library(tidyverse)
# applying to each column, without changing column names
df %>%
# using anonymous function of the form \(input) {...; ...; output}
mutate(
across(
B:E,
\(column)A-column
)
)
reprex()
Error in parse(text = x, keep.source = TRUE) :
<text>:5:7: unexpected 'in'
4:
5: Error in
^
Could you post a complete reprex that shows the error generated? It's very difficult to sort out what's going on without one. You can follow the instructions I posted here.
No user-supplied code found … so we’ve made some up. You’re welcome!
sprintf("Happy %s!", weekdays(Sys.Date()))
#> [1] "Happy Friday!"
Created on 2024-04-05 with reprex v2.1.0
Happy Friday to you too.
1 Like
Looks like you didn't select the code as shown, when you ran the reprex add-in.
Error in parse(text = x, keep.source = TRUE) :
<text>:7:4: unexpected symbol
6:
7: No user
^
As I said, it's hard to know how to help without a reprex to show what's going on. If you follow the instruction in the post I linked carefully, you'll be able to post one.
you should only attempt to reprex code; if you reprex things that are not code; like a conversation; or a mix of R code and error message text ; , you can expect reprex to fail.
``` r
#Loop over columns and rows in a data frame
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
library(formattable)
library(reshape2)
library(data.table)
#>
#> Attaching package: 'data.table'
#> The following objects are masked from 'package:reshape2':
#>
#> dcast, melt
#> The following objects are masked from 'package:dplyr':
#>
#> between, first, last
mac <- read.csv("D:/TEMP/sto1.csv", dec=",")
mac1<- mac %>% mutate(Lung=sample(x = c(216,213,184),
size = 129, replace = TRUE))
head(mac1)
#> Buc MT Kg Lung
#> 1 302 1884.48 2619 184
#> 2 296 1847.4 2568 216
#> 3 304 1869.96 2599 216
#> 4 240 1497.6 2082 184
#> 5 385 2194.5 3050 216
#> 6 302 1887.5 2624 184
mac1 <- mac1 %>%
mutate(Buc = as.numeric(Buc),MT=as.numeric(MT))
mac1<-mac1%>%mutate(medie=round(MT/Buc,2))
mac1<-mac1%>%mutate(Pcs=floor((medie*1000-200)/Lung))
#str(mac)
mac1<-mac1%>%mutate(CTT=MT/(Buc*Lung*Pcs/1000))
mac1<-mac1%>%mutate(util=(Buc*Lung*Pcs/1000))
head(mac1)
#> Buc MT Kg Lung medie Pcs CTT util
#> 1 302 1884.48 2619 184 6.24 32 1.059783 1778.176
#> 2 296 1847.40 2568 216 6.24 27 1.070167 1726.272
#> 3 304 1869.96 2599 216 6.15 27 1.054730 1772.928
#> 4 240 1497.60 2082 184 6.24 32 1.059783 1413.120
#> 5 385 2194.50 3050 216 5.70 25 1.055556 2079.000
#> 6 302 1887.50 2624 184 6.25 32 1.061481 1778.176
#################
#########################
y=rep(sample(c(216,213,184),
size = 129,
replace=TRUE))
y
#> [1] 184 213 213 184 184 184 213 213 213 216 213 213 213 184 184 213 216 213
#> [19] 213 184 184 184 184 184 213 213 213 213 216 184 184 216 216 216 184 213
#> [37] 216 216 213 216 213 184 213 184 216 216 216 216 184 216 184 213 184 184
#> [55] 184 184 213 213 213 216 184 216 213 216 184 184 213 216 213 216 216 184
#> [73] 184 184 213 213 216 213 216 216 213 213 213 213 216 184 213 216 216 213
#> [91] 213 216 184 213 213 213 213 216 184 216 216 213 213 184 216 216 184 216
#> [109] 216 216 213 213 213 184 213 216 216 184 216 184 216 213 184 213 216 216
#> [127] 213 184 216
z= matrix(ncol = 10,nrow = 129)
for(year in 1:10) {
# for each year sample the return 10000 times
for(i in 1:129){
z[i,year] = sample(y,1)
}
}
colnames(z) <- paste0("V", 1:ncol(z))
head(z)
#> V1 V2 V3 V4 V5 V6 V7 V8 V9 V10
#> [1,] 216 213 216 213 216 216 184 184 184 216
#> [2,] 216 184 213 184 184 184 216 213 216 213
#> [3,] 216 184 213 184 216 184 213 213 184 184
#> [4,] 216 213 184 216 216 184 216 216 213 216
#> [5,] 213 213 216 216 213 216 213 216 216 216
#> [6,] 213 213 213 184 213 216 213 213 184 213
data_new2 <- cbind(mac1, z)
head(data_new2)
#> Buc MT Kg Lung medie Pcs CTT util V1 V2 V3 V4 V5 V6 V7
#> 1 302 1884.48 2619 184 6.24 32 1.059783 1778.176 216 213 216 213 216 216 184
#> 2 296 1847.40 2568 216 6.24 27 1.070167 1726.272 216 184 213 184 184 184 216
#> 3 304 1869.96 2599 216 6.15 27 1.054730 1772.928 216 184 213 184 216 184 213
#> 4 240 1497.60 2082 184 6.24 32 1.059783 1413.120 216 213 184 216 216 184 216
#> 5 385 2194.50 3050 216 5.70 25 1.055556 2079.000 213 213 216 216 213 216 213
#> 6 302 1887.50 2624 184 6.25 32 1.061481 1778.176 213 213 213 184 213 216 213
#> V8 V9 V10
#> 1 184 184 216
#> 2 213 216 213
#> 3 213 184 184
#> 4 216 213 216
#> 5 216 216 216
#> 6 213 184 213
#ADAUGAT
head(data_new2)
#> Buc MT Kg Lung medie Pcs CTT util V1 V2 V3 V4 V5 V6 V7
#> 1 302 1884.48 2619 184 6.24 32 1.059783 1778.176 216 213 216 213 216 216 184
#> 2 296 1847.40 2568 216 6.24 27 1.070167 1726.272 216 184 213 184 184 184 216
#> 3 304 1869.96 2599 216 6.15 27 1.054730 1772.928 216 184 213 184 216 184 213
#> 4 240 1497.60 2082 184 6.24 32 1.059783 1413.120 216 213 184 216 216 184 216
#> 5 385 2194.50 3050 216 5.70 25 1.055556 2079.000 213 213 216 216 213 216 213
#> 6 302 1887.50 2624 184 6.25 32 1.061481 1778.176 213 213 213 184 213 216 213
#> V8 V9 V10
#> 1 184 184 216
#> 2 213 216 213
#> 3 213 184 184
#> 4 216 213 216
#> 5 216 216 216
#> 6 213 184 213
library(tidyverse)
#> Warning: package 'readr' was built under R version 4.3.2
library(conflicted)
library(dplyr)
(colnames <- colnames(data_new2))
#> [1] "Buc" "MT" "Kg" "Lung" "medie" "Pcs" "CTT" "util" "V1"
#> [10] "V2" "V3" "V4" "V5" "V6" "V7" "V8" "V9" "V10"
(cols_to_process <- colnames[startsWith(colnames, "V")])
#> [1] "V1" "V2" "V3" "V4" "V5" "V6" "V7" "V8" "V9" "V10"
(new_names <- sub("^V", "W", cols_to_process))
#> [1] "W1" "W2" "W3" "W4" "W5" "W6" "W7" "W8" "W9" "W10"
for(i in seq_along(cols_to_process)){
medie_i <- data_new2$medie[[i]]
MT_i <- data_new2$MT[[i]]
Buc_i<-data_new2$Buc[[i]]
data_new2[[ new_names[[ i ]] ]] <-floor((medie_i*1000-200)/ data_new2[[ cols_to_process[[ i ]] ]])
}
head(data_new2)
#> Buc MT Kg Lung medie Pcs CTT util V1 V2 V3 V4 V5 V6 V7
#> 1 302 1884.48 2619 184 6.24 32 1.059783 1778.176 216 213 216 213 216 216 184
#> 2 296 1847.40 2568 216 6.24 27 1.070167 1726.272 216 184 213 184 184 184 216
#> 3 304 1869.96 2599 216 6.15 27 1.054730 1772.928 216 184 213 184 216 184 213
#> 4 240 1497.60 2082 184 6.24 32 1.059783 1413.120 216 213 184 216 216 184 216
#> 5 385 2194.50 3050 216 5.70 25 1.055556 2079.000 213 213 216 216 213 216 213
#> 6 302 1887.50 2624 184 6.25 32 1.061481 1778.176 213 213 213 184 213 216 213
#> V8 V9 V10 W1 W2 W3 W4 W5 W6 W7 W8 W9 W10
#> 1 184 184 216 27 28 27 28 25 28 32 32 32 28
#> 2 213 216 213 27 32 27 32 29 32 28 28 27 28
#> 3 213 184 184 27 32 27 32 25 32 28 28 32 33
#> 4 216 213 216 27 28 32 27 25 32 28 28 27 28
#> 5 216 216 216 28 28 27 27 25 28 28 28 27 28
#> 6 213 184 213 28 28 27 32 25 28 28 28 32 28
(colnames <- colnames(data_new2))
#> [1] "Buc" "MT" "Kg" "Lung" "medie" "Pcs" "CTT" "util" "V1"
#> [10] "V2" "V3" "V4" "V5" "V6" "V7" "V8" "V9" "V10"
#> [19] "W1" "W2" "W3" "W4" "W5" "W6" "W7" "W8" "W9"
#> [28] "W10"
(cols_to_process <-colnames( data_new2 %>% select(V1:W10)))
#> [1] "V1" "V2" "V3" "V4" "V5" "V6" "V7" "V8" "V9" "V10" "W1" "W2"
#> [13] "W3" "W4" "W5" "W6" "W7" "W8" "W9" "W10"
(new_names <- sub("^W", "x", cols_to_process))
#> [1] "V1" "V2" "V3" "V4" "V5" "V6" "V7" "V8" "V9" "V10" "x1" "x2"
#> [13] "x3" "x4" "x5" "x6" "x7" "x8" "x9" "x10"
for(i in seq_along(cols_to_process)){
V_i<-data_new2$V[[i]]
W_i<-data_new2$W[[i]]
Buc_i<-data_new2$Buc[[i]]
data_new2[[ new_names[[ i ]] ]] <-Buc_i *data_new2[[ cols_to_process[[ i ]] ]]
}
head(data_new2)
#> Buc MT Kg Lung medie Pcs CTT util V1 V2 V3 V4
#> 1 302 1884.48 2619 184 6.24 32 1.059783 1778.176 65232 63048 65664 51120
#> 2 296 1847.40 2568 216 6.24 27 1.070167 1726.272 65232 54464 64752 44160
#> 3 304 1869.96 2599 216 6.15 27 1.054730 1772.928 65232 54464 64752 44160
#> 4 240 1497.60 2082 184 6.24 32 1.059783 1413.120 65232 63048 55936 51840
#> 5 385 2194.50 3050 216 5.70 25 1.055556 2079.000 64326 63048 65664 51840
#> 6 302 1887.50 2624 184 6.25 32 1.061481 1778.176 64326 63048 64752 44160
#> V5 V6 V7 V8 V9 V10 W1 W2 W3 W4 W5 W6 W7 W8 W9 W10 x1 x2
#> 1 83160 65232 59248 56304 65688 63720 27 28 27 28 25 28 32 32 32 28 8640 8820
#> 2 70840 55568 69552 65178 77112 62835 27 32 27 32 29 32 28 28 27 28 8640 10080
#> 3 83160 55568 68586 65178 65688 54280 27 32 27 32 25 32 28 28 32 33 8640 10080
#> 4 83160 55568 69552 66096 76041 63720 27 28 32 27 25 32 28 28 27 28 8640 8820
#> 5 82005 65232 68586 66096 77112 63720 28 28 27 27 25 28 28 28 27 28 8960 8820
#> 6 82005 65232 68586 65178 65688 62835 28 28 27 32 25 28 28 28 32 28 8960 8820
#> x3 x4 x5 x6 x7 x8 x9 x10
#> 1 5886 7560 7000 10080 9216 9408 9856 7924
#> 2 5886 8640 8120 11520 8064 8232 8316 7924
#> 3 5886 8640 7000 11520 8064 8232 9856 9339
#> 4 6976 7290 7000 11520 8064 8232 8316 7924
#> 5 5886 7290 7000 10080 8064 8232 8316 7924
#> 6 5886 8640 7000 10080 8064 8232 9856 7924
#############
Created on 2024-04-06 with reprex v2.0.2
This is unrelated to your original topic — is there a reason you posted it here?
From the sessionInfo() output you posted here, I don't think you can use the base R pipe (|>) or the \(input) output version of anonymous functions, so you would want to try this instead:
df <-
data.frame(
A = c(12,71,53,34,21),
B = c(23, 41, 32, 58, 26),
C = c(12,1,3,5,6),
D = c(12,4,7,8,11),
E = c(11,33,45,67,89)
)
df
#> A B C D E
#> 1 12 23 12 12 11
#> 2 71 41 1 4 33
#> 3 53 32 3 7 45
#> 4 34 58 5 8 67
#> 5 21 26 6 11 89
library(tidyverse)
# applying to each column, without changing column names
df %>%
# using anonymous function of the form '~ output', where 'output' is
# the result of transforming the input, which is represented by '.'
mutate(
across(
B:E,
~ A - .
)
)
#> A B C D E
#> 1 12 -11 0 0 1
#> 2 71 30 70 67 38
#> 3 53 21 50 46 8
#> 4 34 -24 29 26 -33
#> 5 21 -5 15 10 -68
This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.
If you have a query related to it or one of the replies, start a new topic and refer back with a link.