How to apply a function to each data.frame element?

Question

I want to convert a numerical value to a coefficient, if the value is below -2, then "down" should be a factor, if it is above 2, then "up" and between "no_change":

So far I have been thinking about creating a function:

classifier <- function(x){
    if (x >= 2){
      return(as.factor("up"))
    }else if (x <= -2){
      return(as.factor("down"))
    }else {
      return(as.factor("no_change"))
    }
}

I could make it iterate (with a for loop) over the entry and return of the list, so I could use it with application.

I want to apply this function to all cells of a data.frame file, how can I do this?

mock data ( runif(15, min=-5, max=5)):

c(1.11004611710086, -1.86842617811635, 1.72159335808828, -2.68788822228089, 
2.72551498375833, 3.67290901951492, -4.00984475389123, -2.39582793787122, 
4.22395745059475, -0.360892189200968, 1.35027756914496, 2.89919016882777, 
-0.158692332915962, -0.950306688901037, 3.39141107397154)

Answer 1

Using DF <- iris[-5]as sample data, you can use cut, as I suggested in the comments.

Try:

DF[] <- lapply(DF, cut, c(-Inf, -2, 2, Inf), c("down", "no_change", "up"))

head(DF)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1           up          up    no_change   no_change
## 2           up          up    no_change   no_change
## 3           up          up    no_change   no_change
## 4           up          up    no_change   no_change
## 5           up          up    no_change   no_change
## 6           up          up    no_change   no_change

tail(DF)
##     Sepal.Length Sepal.Width Petal.Length Petal.Width
## 145           up          up           up          up
## 146           up          up           up          up
## 147           up          up           up   no_change
## 148           up          up           up   no_change
## 149           up          up           up          up
## 150           up          up           up   no_change

, RHertel "mock_data":

cut(mock_data, c(-Inf, -2, 2, Inf), c("down", "no_change", "up"))
##  [1] no_change no_change no_change down      up        up        down     
##  [8] down      up        no_change no_change up        no_change no_change
## [15] up       
## Levels: down no_change up

---

, RHertel, , . ( ) factor ( ).

, , :

set.seed(1)
nrow = 20000
ncol = 1000
x <- as.data.frame(matrix(runif(nrow * ncol, min=-5, max=5), ncol = ncol))

factorize <- function(invec) {
  factorized <- rep("no_change", length(invec))
  factorized[invec > 2]  <- "up"
  factorized[invec < -2]  <- "down"
  factor(factorized, c("down", "no_change", "up"))
}

RHfun <- function(indf = x) {
  indf[] <- lapply(indf, factorize)
  indf
}

AMfun <- function(DF = x) {
  DF[] <- lapply(DF, cut, c(-Inf, -2, 2, Inf), c("down", "no_change", "up"))
  DF
}

library(microbenchmark)
microbenchmark(AMfun(), RHfun(), times = 10)
# Unit: seconds
#     expr      min       lq     mean   median       uq       max neval
#  AMfun() 7.501814 8.015532 8.852863 8.731638 9.660191 10.198983    10
#  RHfun() 1.437696 1.485791 1.723402 1.574507 1.637139  2.528574    10

Answer 2

ifelse(), , , -.

factorized <- rep("no_change", length(mock_data))
factorized[mock_data > 2]  <- "up"
factorized[mock_data < -2]  <- "down"
factorized <- as.factor(factorized)
#> factorized
#[1] no_change no_change no_change down      up        up        down      down      up        no_change no_change up        no_change no_change up       
#Levels: down no_change up

OP:

mock_data <- c(1.11004611710086, -1.86842617811635, 1.72159335808828, -2.68788822228089, 
           2.72551498375833, 3.67290901951492, -4.00984475389123, -2.39582793787122, 
           4.22395745059475, -0.360892189200968, 1.35027756914496, 2.89919016882777, 
           -0.158692332915962, -0.950306688901037, 3.39141107397154)

@docendo discimus .

Answer 3

apply .

apply(yourDF, c(1, 2), classifier)

This is done to apply a function to each cell data.frame. It will probably not work on vectors.