I am working with the R programming language.
Suppose I have the following data frame:
var_1 = var_2 = var_3 = var_4 = var_5 = c("1,2,3,4,5,6,7,8,9,10")
my_data = data.frame(var_1,var_2,var_3,var_4,var_5)
my_data = rbind(my_data, my_data[rep(1, 100), ])
rownames(my_data) = 1:nrow(my_data)
The data looks like this:
head(my_data)
var_1 var_2 var_3 var_4 var_5
1 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
2 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
3 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
4 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
5 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
6 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
My Question: I would like to randomly replace elements in this data frame with 0 - for instance, the final result should look something like this (for brevity, I am only showing the first row):
# desired result
var_1 var_2 var_3 var_4 var_5
1 1,0,3,0,5,6,0,0,9,10 1,2,0,4,5,0,0,8,9,0 1,0,3,0,0,0,0,8,9,0 1,2,3,4,0,6,7,0,0,10 1,2,0,4,5,0,7,8,0,10
I tried to do this with the following line of code (Replace random values in a column in a dataframe) :
my_data$var_1[sample(nrow(my_data),as.integer(0.5*nrow(my_data)) , replace = TRUE)] <- 0
my_data$var_2[sample(nrow(my_data),as.integer(0.5*nrow(my_data)), replace = TRUE)] <- 0
my_data$var_3[sample(nrow(my_data),as.integer(0.5*nrow(my_data)), replace = TRUE)] <- 0
my_data$var_4[sample(nrow(my_data),as.integer(0.5*nrow(my_data)), replace = TRUE)] <- 0
my_data$var_5[sample(nrow(my_data),as.integer(0.5*nrow(my_data)), replace = TRUE)] <- 0
But this is replacing ALL the elements of a row with 0 (instead of just replacing some of the elements within a row):
head(my_data)
var_1 var_2 var_3 var_4 var_5
1 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 0 0 0
2 0 0 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 0
3 0 1,2,3,4,5,6,7,8,9,10 0 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
4 0 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 0 1,2,3,4,5,6,7,8,9,10
5 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10
6 1,2,3,4,5,6,7,8,9,10 0 1,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,10 0
Can someone please show me what I am doing wrong and how to get the desired result?
Thanks!
CodePudding user response：
This could be one way to get to your aim:
library(dplyr)
library(tidyr)
my_data %>%
separate_rows(starts_with("var")) %>%
group_by(id_Group =cumsum(var_1==1)) %>%
mutate(across(starts_with("var"), ~replace(., sample(row_number(),
size = ceiling(0.4 * n()), replace = TRUE), 0))) %>%
mutate(across(starts_with("var"), ~toString(.))) %>%
slice(1) %>%
ungroup() %>%
select(-id_Group)
var_1 var_2 var_3 var_4 var_5
<chr> <chr> <chr> <chr> <chr>
1 1, 2, 0, 4, 0, 6, 7, 0, 9, 10 1, 2, 3, 0, 5, 0, 0, 8, 9, 0 0, 0, 3,~ 1, 2~ 0, 0~
2 1, 2, 3, 4, 0, 6, 0, 8, 9, 0 1, 2, 3, 0, 0, 6, 7, 8, 9, 0 1, 2, 3,~ 1, 0~ 1, 0~
3 1, 0, 3, 4, 5, 0, 7, 8, 9, 0 1, 2, 3, 0, 5, 0, 0, 0, 9, 10 1, 2, 0,~ 1, 2~ 1, 2~
4 1, 0, 0, 4, 5, 0, 7, 8, 9, 0 1, 2, 3, 4, 5, 0, 7, 0, 0, 10 0, 0, 0,~ 0, 0~ 0, 0~
5 0, 0, 3, 4, 0, 6, 7, 8, 9, 10 0, 0, 3, 4, 5, 6, 0, 8, 9, 10 1, 0, 3,~ 1, 2~ 1, 2~
6 1, 0, 0, 4, 5, 6, 0, 8, 9, 10 1, 2, 3, 0, 0, 6, 7, 8, 9, 0 1, 0, 3,~ 1, 2~ 1, 2~
7 1, 0, 3, 4, 5, 0, 0, 8, 0, 10 0, 2, 3, 0, 5, 6, 7, 8, 0, 0 1, 2, 3,~ 1, 2~ 1, 0~
8 1, 2, 0, 4, 0, 0, 7, 8, 9, 10 1, 2, 3, 0, 5, 0, 7, 8, 0, 0 1, 0, 3,~ 1, 0~ 0, 2~
9 1, 2, 3, 0, 5, 0, 0, 0, 9, 10 1, 2, 3, 4, 0, 0, 0, 8, 9, 0 1, 2, 0,~ 0, 0~ 0, 0~
10 1, 2, 3, 0, 5, 6, 7, 8, 9, 0 1, 2, 0, 4, 5, 6, 7, 8, 0, 10 1, 0, 3,~ 1, 2~ 1, 2~
# ... with 91 more rows
CodePudding user response：
Here is a way.
Create a function to sample n elements from each vector element, defaulting to 1, and lapply the function to the vectors to be changed. In the posted example all column vectors will be changed.
options(width=205)
var_1 = var_2 = var_3 = var_4 = var_5 = c("1,2,3,4,5,6,7,8,9,10")
my_data = data.frame(var_1,var_2,var_3,var_4,var_5)
my_data = rbind(my_data, my_data[rep(1, 100), ])
rownames(my_data) = 1:nrow(my_data)
my_data1 <- my_data
randReplace <- function(x, n = 1L, split = ",") {
y <- strsplit(x, split = split)
z <- lapply(y, function(.y) {
i <- seq_along(.y)
m <- min(n, length(.y))
.y[sample(i, m)] <- 0
.y
})
z <- lapply(z, paste, collapse = split)
unlist(z)
}
my_data[] <- lapply(my_data, randReplace)
head(my_data)
#> var_1 var_2 var_3 var_4 var_5
#> 1 1,2,3,4,5,0,7,8,9,10 0,2,3,4,5,6,7,8,9,10 1,2,3,4,5,0,7,8,9,10 1,2,3,4,0,6,7,8,9,10 1,2,3,0,5,6,7,8,9,10
#> 2 1,0,3,4,5,6,7,8,9,10 1,2,0,4,5,6,7,8,9,10 1,2,3,0,5,6,7,8,9,10 1,2,3,4,5,0,7,8,9,10 0,2,3,4,5,6,7,8,9,10
#> 3 1,2,3,4,0,6,7,8,9,10 1,2,3,4,5,6,7,0,9,10 0,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,0,8,9,10 1,2,3,4,0,6,7,8,9,10
#> 4 1,2,0,4,5,6,7,8,9,10 1,2,3,4,0,6,7,8,9,10 1,2,3,4,5,6,7,0,9,10 1,2,3,4,5,6,0,8,9,10 1,0,3,4,5,6,7,8,9,10
#> 5 1,2,3,0,5,6,7,8,9,10 1,2,3,4,5,6,7,8,0,10 1,2,3,0,5,6,7,8,9,10 0,2,3,4,5,6,7,8,9,10 1,2,3,4,5,6,7,0,9,10
#> 6 1,2,3,4,5,6,0,8,9,10 1,2,3,4,5,6,7,8,9,0 1,2,3,0,5,6,7,8,9,10 1,2,3,4,5,6,7,8,9,0 1,0,3,4,5,6,7,8,9,10
my_data1[] <- lapply(my_data1, randReplace, n = 4)
head(my_data1)
#> var_1 var_2 var_3 var_4 var_5
#> 1 1,2,3,4,0,0,0,8,9,0 0,2,0,0,5,6,7,8,9,0 1,0,0,4,0,6,0,8,9,10 0,0,3,4,0,0,7,8,9,10 1,0,3,4,5,6,0,8,0,0
#> 2 1,0,3,4,5,6,0,8,0,0 1,0,3,0,0,6,7,8,9,0 0,2,3,4,5,0,0,8,0,10 1,0,0,4,5,0,7,8,0,10 0,0,3,4,0,6,7,8,9,0
#> 3 0,2,3,4,5,6,7,0,0,0 0,2,0,0,5,6,7,8,0,10 1,2,0,4,5,6,0,0,9,0 0,2,0,0,5,0,7,8,9,10 0,2,0,4,5,0,7,8,9,0
#> 4 1,2,3,0,0,6,0,8,0,10 1,0,3,4,5,0,7,8,0,0 1,2,0,0,5,0,7,0,9,10 1,0,3,0,5,6,0,8,9,0 0,2,0,4,0,6,0,8,9,10
#> 5 1,2,3,4,0,0,7,0,9,0 0,0,0,0,5,6,7,8,9,10 0,0,3,4,5,6,0,0,9,10 0,2,3,4,0,0,7,0,9,10 1,0,0,0,5,6,7,8,0,10
#> 6 1,2,0,4,0,0,0,8,9,10 0,2,3,0,0,0,7,8,9,10 0,2,0,4,0,6,7,8,0,10 1,2,3,4,5,0,0,0,0,10 0,2,0,4,0,6,7,8,9,0
Created on 2022-04-10 by the reprex package (v2.0.1)