I am working with the R programming language.
I have the following dataset:
num_var_1 <- rnorm(1000, 10, 1)
num_var_2 <- rnorm(1000, 10, 5)
num_var_3 <- rnorm(1000, 10, 10)
num_var_4 <- rnorm(1000, 10, 10)
num_var_5 <- rnorm(1000, 10, 10)
factor_1 <- c("A","B", "C")
factor_2 <- c("AA","BB", "CC")
factor_3 <- c("AAA","BBB", "CCC", "DDD")
factor_4 <- c("AAAA","BBBB", "CCCC", "DDDD", "EEEE")
factor_5 <- c("AAAAA","BBBBB", "CCCCC", "DDDDD", "EEEEE", "FFFFFF")
factor_var_1 <- as.factor(sample(factor_1, 1000, replace=TRUE, prob=c(0.3, 0.5, 0.2)))
factor_var_2 <- as.factor(sample(factor_2, 1000, replace=TRUE, prob=c(0.5, 0.3, 0.2)))
factor_var_3 <- as.factor(sample(factor_3, 1000, replace=TRUE, prob=c(0.5, 0.2, 0.2, 0.1)))
factor_var_4 <- as.factor(sample(factor_4, 1000, replace=TRUE, prob=c(0.5, 0.2, 0.1, 0.1, 0.1)))
factor_var_5 <- as.factor(sample(factor_4, 1000, replace=TRUE, prob=c(0.3, 0.2, 0.1, 0.1, 0.1)))
my_data = data.frame(id,num_var_1, num_var_2, num_var_3, num_var_4, num_var_5, factor_var_1, factor_var_2, factor_var_3, factor_var_4, factor_var_5)
> head(my_data)
id num_var_1 num_var_2 num_var_3 num_var_4 num_var_5 factor_var_1 factor_var_2 factor_var_3 factor_var_4 factor_var_5
1 1 9.439524 5.021006 4.883963 8.496925 11.965498 B AA AAA CCCC AAAA
2 2 9.769823 4.800225 12.369379 6.722429 16.501132 B AA AAA AAAA AAAA
3 3 11.558708 9.910099 4.584108 -4.481653 16.710042 C AA BBB AAAA CCCC
4 4 10.070508 9.339124 22.192276 3.027154 -2.841578 B CC DDD BBBB AAAA
5 5 10.129288 -2.746714 11.741359 35.984902 -10.261096 B AA AAA DDDD DDDD
6 6 11.715065 15.202867 3.847317 9.625850 32.053261 B AA CCC BBBB EEEE
Based on the answer provided from a previous question (R: Randomly Sampling Mixed Variables), I learned how to randomly take samples from this data:
library(dplyr)
library(purrr)
# calc the ratio of choosing variable
var_num <- ncol(my_data) - 1
var_select_ratio <- sum(1:var_num) / (var_num^2)
num_func <- function(vec, iter_num) {
random_val = runif(iter_num, min(vec), max(vec))
is_select <- sample(c(NA, 1), iter_num,
prob = c(1 - var_select_ratio, var_select_ratio), replace = TRUE)
return(random_val * is_select)
}
fac_func <- function(vec, iter_num) {
nlevels <- sample.int(length(levels(vec)), iter_num, replace = TRUE)
is_select <- sample(c(0, 1), iter_num,
prob = c(1 - var_select_ratio, var_select_ratio), replace = TRUE)
out <- map2(nlevels, is_select, # NOTE: this process isn't vectorized
function(nl, ic){
if(ic == 0) NULL else sample(vec, nl)
})
return(out)
}
integ_func <- function(vec, iter_num) {
if(is.factor(vec)) fac_func(vec, iter_num) else num_func(vec, iter_num)
}
# if you want to paste factor_var
res2 <- res %>%
mutate_if(is.list, function(col) map_chr(col, function(cell) paste(sort(cell), collapse = " "))) %>% # paste
mutate_if(is.character, function(col) na_if(col, "")) # replace "" to NA
This produces the following results:
> res2 = data.frame(res2)
> res2
num_var_1 num_var_2 num_var_3 num_var_4 num_var_5 factor_var_1 factor_var_2 factor_var_3 factor_var_4 factor_var_5
1 8.251683 27.791314 30.525573 33.95768 2.388074 B <NA> AAA AAAA DDDD
2 9.012602 NA NA NA 20.236515 A AA BB <NA> <NA> BBBB
3 NA 16.778085 28.097324 5.69020 NA B BB CCC DDD DDD <NA> AAAA BBBB CCCC CCCC CCCC
4 12.838667 -3.694075 13.411877 -2.20004 NA <NA> AA AA BB AAA BBB CCC <NA> AAAA AAAA BBBB CCCC DDDD
5 NA NA 11.922439 17.63757 NA A B AA AA BB <NA> AAAA AAAA BBBB
6 12.768595 NA 28.507646 NA NA C AA BBB DDD DDD AAAA AAAA CCCC DDDD AAAA AAAA BBBB EEEE EEEE
7 NA NA -20.424906 NA 20.147004 <NA> AA AA <NA> AAAA AAAA AAAA CCCC EEEE <NA>
8 NA 6.299722 8.569485 24.82825 -17.715862 <NA> BB AAA AAA BBB CCC <NA> BBBB EEEE
9 10.846757 NA NA NA NA A B C AA BB CC <NA> <NA> BBBB BBBB
10 NA 4.663916 22.335404 NA NA B B C AA BB AAA AAA AAA DDD AAAA AAAA CCCC EEEE EEEE <NA>
My Question: Is it possible to take conditions from different rows in "res2" and use them to perform operations on "my_data"? For example:
-
If you take the 6th row and 10th row from "res2" :
res2[c(6,10),] -
In Row 6: num_var_2 = NA, num_var_4 = NA and num_var_5 = NA
-
In Row 6: num_var_1 = 12.768595 , num_var_3 = 28.507646, factor_var_1 = C, factor_var_2 = AA, factor_var_3 = BBB DDD DDD, factor_var_4 = AAAA CCCC DDDD, factor_var_5 = AAAA BBBB EEEE EEEE
-
In Row 10: num_var_1 = NA, num_var_4 = NA num_var_5 = NA, factor_var_5 = NA
-
In Row 10: num_var_2 = 4.663916, num_var_3 = 22.335404 , factor_var_1 = B C, factor_var_2 = BB CC, factor_var_3 = AAA DDD, factor_var_4 = AAAA CCCC DDDD, factor_var_5 = AAAA CCCC EEEE
I want to perform the following operation:
Step 1: where my_data$num_var_1 = 12.768595 , my_data$num_var_3 = 28.507646, my_data$factor_var_1 = C, my_data$factor_var_2 = AA, my_data$factor_var_3 = BBB DDD DDD, my_data$factor_var_4 = AAAA CCCC DDDD, my_data$factor_var_5 = AAAA BBBB EEEE EEEE
Step 2 (using the data from Step 1): Take columns "my_data$num_var_2 , my_data$num_var_4 and my_data$num_var_5" and replace a random 30% of elements in these columns with 0
Step 3 (using the data from Step 2): where my_data$num_var_2 = 4.663916, my_data$num_var_3 = 22.335404 , my_data$factor_var_1 = B C, my_data$factor_var_2 = BB CC, my_data$factor_var_3 = AAA DDD, my_data$factor_var_4 = AAAA CCCC DDDD, my_data$factor_var_5 = AAAA CCCC EEEE
Step 4 (using the data from Step 3): Take columns "my_data$num_var_1 , my_data$num_var_4 and my_data$num_var_5, my_data$factor_var_5" and replace a random 35% of elements in these columns with 0
Is it possible to directly perform Step 1 - Step 4 using "my_data" and "res2"?
Currently, I can do this manually (R: Randomly Changing Values in a Dataframe).
Can someone please show me how to do this?
Thanks!
Aucun commentaire:
Enregistrer un commentaire