Home > Net >  R: Randomly Sampling Mixed Variables
R: Randomly Sampling Mixed Variables

Time:12-29

I am working with the R programming language.

Suppose I have the following 10 variables (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):

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

Problem: I want to do the following (In real life, I only have the "my_data" dataset):

  1. Choose a random number of variables from "my_data"
  2. For "factor variables" from Step 1), randomly select some of the "levels" from each variable
  3. For the "numeric variables" from Step 1), randomly select a number within the range of each variable
  4. Repeat Steps 1 - Step 3 many times

For example, this might look like this:

  • Iteration 1: num_var_3 (9.1), num_var_5 (2.1), factor_var_2 (AA, CC)
  • Iteration 2: num_var_1 (5.01), factor_var_3(AAA, CCC, DDD), factor_var_4(CCCC, DDDD), factor_var_5 (EEEEE)

etc.

What I tried so far: I tried to do this manually:

#Iteration 1

# 4 variables are selected
n = sample.int(10, 1)
[1] 4

# which 4 variables are selected (each number corresponds to their position):
sample.int(10, length(n))
[1] 6 2 1 4

num_var_1
num_var_2
num_var_4
factor_var_1

#select random points for the continuous variables

p1 <- runif(1, min(num_var_1), max(num_var_1))
p2 <- runif(1, min(num_var_2), max(num_var_2))
p4 <- runif(1, min(num_var_4), max(num_var_4))


> p1
[1] 10.6902
> p2
[1] 18.11022
> p4
[1] -4.778462

#select random factor levels for the factor variable

nlevel = nlevels(factor_var_1)
nlevels = sample.int(nlevel, 1)
[1] 2

sample(factor_1, nlevels, replace=TRUE, prob=c(0.3, 0.5, 0.2))
[1] "A" "B"

 # Desired Output

 Iteration 1: num_var_1 = 10.6902 ,  num_var_2 =  18.11022 , num_var_4 =  -4.778462, factor_var_1 = "A, B"

But this is taking a long time to do.

Question: Can someone please show me how to do this (i.e. perform 10 such iterations and record the results)?

Thanks!

Note: Summary of Data

> summary(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
 Min.   :   1.0   Min.   : 6.658   Min.   :-6.007   Min.   :-23.775   Min.   :-20.301   Min.   :-20.59   A:294        AA:513       AAA:514      AAAA:495     AAAA:327    
 1st Qu.: 250.8   1st Qu.: 9.401   1st Qu.: 6.374   1st Qu.:  2.759   1st Qu.:  2.794   1st Qu.:  3.89   B:507        BB:291       BBB:202      BBBB:190     BBBB:271    
 Median : 500.5   Median :10.066   Median : 9.978   Median : 10.068   Median : 10.134   Median : 10.25   C:199        CC:196       CCC:199      CCCC: 94     CCCC:125    
 Mean   : 500.5   Mean   :10.061   Mean   : 9.766   Mean   :  9.938   Mean   :  9.979   Mean   : 10.33                             DDD: 85      DDDD:103     DDDD:138    
 3rd Qu.: 750.2   3rd Qu.:10.716   3rd Qu.:13.188   3rd Qu.: 16.399   3rd Qu.: 17.404   3rd Qu.: 17.14                                          EEEE:118     EEEE:139    
 Max.   :1000.0   Max.   :13.270   Max.   :24.805   Max.   : 41.441   Max.   : 42.262   Max.   : 38.80        

                                                       
> str(my_data)
'data.frame':   1000 obs. of  11 variables:
 $ id          : int  1 2 3 4 5 6 7 8 9 10 ...
 $ num_var_1   : num  9.13 9.96 8.2 10.49 9.19 ...
 $ num_var_2   : num  19.03 3.31 16.73 20.52 10.35 ...
 $ num_var_3   : num  25.45 6.26 24.99 8.11 26.45 ...
 $ num_var_4   : num  21.284 2.313 3.203 -0.347 11.847 ...
 $ num_var_5   : num  9.26 7.39 -1.4 13.94 10.71 ...
 $ factor_var_1: Factor w/ 3 levels "A","B","C": 1 2 1 3 2 1 1 3 3 3 ...
 $ factor_var_2: Factor w/ 3 levels "AA","BB","CC": 2 1 3 1 2 1 1 2 2 2 ...
 $ factor_var_3: Factor w/ 4 levels "AAA","BBB","CCC",..: 3 1 1 1 4 1 4 4 1 3 ...
 $ factor_var_4: Factor w/ 5 levels "AAAA","BBBB",..: 3 1 2 1 1 1 5 1 1 1 ...
 $ factor_var_5: Factor w/ 5 levels "AAAA","BBBB",..: 1 2 4 2 1 4 4 3 1 2 ...

CodePudding user response:

it is important that the ratio of choosing variable is constant.
you can get it by sum(1:var_num ) / (var_num^2).
And next point is vectorize (Vector operation). (but as far as I see, it is difficult to vectorize your factor process, so I didn't do it). sample and runif returns vector when n, size > 1. And they are very fast, so I calc ALL runif vals of num_vals and ALL nlevels of fact_vals regardless of whether or not it is selected.

NOTE:
I used sample(factor_var_1, nlevels, replace=TRUE) instead of sample(factor_1, nlevels, replace=TRUE, prob=c(0.3, 0.5, 0.2)) in your example.
NOTE2:
map and map2 are close relatives of 'sapply' and 'mapply'.

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)
}

set.seed(1)
res <- my_data %>% 
  select(-id) %>% 
  map(~ integ_func(.x, iter_num = 10)) %>%  # use the func with each cols
  as_tibble()                               # just appearance

# output
> res
# A tibble: 10 × 10
   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
       <dbl>     <dbl>     <dbl>     <dbl>     <dbl> <list>       <list>       <list>       <list>       <list>      
 1      8.80     25.9      27.2      35.2       1.14 <fct [1]>    <NULL>       <fct [1]>    <fct [1]>    <fct [1]>   
 2      9.53     NA        NA        NA        18.9  <fct [1]>    <fct [2]>    <NULL>       <NULL>       <fct [1]>   
 3     NA        16.2      24.7       6.71     NA    <fct [1]>    <fct [1]>    <fct [3]>    <NULL>       <fct [5]>


# 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

> res2
# A tibble: 10 × 10
   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                
       <dbl>     <dbl>     <dbl>     <dbl>     <dbl> <chr>        <chr>        <chr>           <chr>                    <chr>                       
 1      8.80     25.9      27.2      35.2       1.14 B            NA           BBB             AAAA                     DDDDD                       
 2      9.53     NA        NA        NA        18.9  B            AA BB        NA              NA                       BBBBB                       
 3     NA        16.2      24.7       6.71     NA    B            BB           AAA AAA DDD     NA                       AAAAA AAAAA BBBBB BBBBB FFF…

# the data I used
# (a litte modified, e.g., `factor_var_5` using not `factor_4` but `factor_5`)
set.seed(1)
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_5, 1000, replace=TRUE, prob=c(0.3, 0.2, 0.1, 0.1, 0.1, 0.2)))

my_data = data.frame(id = 1:length(num_var_1), 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)
  • Related