Can dplyr package be used for conditional mutating

问题:

Can the mutate be used when the mutation is conditional (depending on the values of certain column values)?

This example helps showing what I mean.

structure(list(a = c(1, 3, 4, 6, 3, 2, 5, 1), b = c(1, 3, 4, 
2, 6, 7, 2, 6), c = c(6, 3, 6, 5, 3, 6, 5, 3), d = c(6, 2, 4, 
5, 3, 7, 2, 6), e = c(1, 2, 4, 5, 6, 7, 6, 3), f = c(2, 3, 4, 
2, 2, 7, 5, 2)), .Names = c(\"a\", \"b\", \"c\", \"d\", \"e\", \"f\"), row.names = c(NA, 
8L), class = \"data.frame\")

  a b c d e f
1 1 1 6 6 1 2
2 3 3 3 2 2 3
3 4 4 6 4 4 4
4 6 2 5 5 5 2
5 3 6 3 3 6 2
6 2 7 6 7 7 7
7 5 2 5 2 6 5
8 1 6 3 6 3 2

I was hoping to find a solution to my problem using the dplyr package (and yes I know this not code that should work, but I guess it makes the purpose clear) for creating a new column g:

 library(dplyr)
 df <- mutate(df,
         if (a == 2 | a == 5 | a == 7 | (a == 1 & b == 4)){g = 2},
         if (a == 0 | a == 1 | a == 4 | a == 3 |  c == 4) {g = 3})

The result of the code I am looking for should have this result in this particular example:

  a b c d e f  g
1 1 1 6 6 1 2  3
2 3 3 3 2 2 3  3
3 4 4 6 4 4 4  3
4 6 2 5 5 5 2 NA
5 3 6 3 3 6 2 NA
6 2 7 6 7 7 7  2
7 5 2 5 2 6 5  2
8 1 6 3 6 3 2  3

Does anyone have an idea about how to do this in dplyr? This data frame is just an example, the data frames I am dealing with are much larger. Because of its speed I tried to use dplyr, but perhaps there are other, better ways to handle this problem?

回答1:

Use ifelse

df %>%
  mutate(g = ifelse(a == 2 | a == 5 | a == 7 | (a == 1 & b == 4), 2,
               ifelse(a == 0 | a == 1 | a == 4 | a == 3 |  c == 4, 3, NA)))

Added - if_else: Note that in dplyr 0.5 there is an if_else function defined so an alternative would be to replace ifelse with if_else; however, note that since if_else is stricter than ifelse (both legs of the condition must have the same type) so the NA in that case would have to be replaced with NA_real_ .

df %>%
  mutate(g = if_else(a == 2 | a == 5 | a == 7 | (a == 1 & b == 4), 2,
               if_else(a == 0 | a == 1 | a == 4 | a == 3 |  c == 4, 3, NA_real_)))

Added - case_when Since this question was posted dplyr has added case_when so another alternative would be:

df %>% mutate(g = case_when(a == 2 | a == 5 | a == 7 | (a == 1 & b == 4) ~ 2,
                            a == 0 | a == 1 | a == 4 | a == 3 |  c == 4 ~ 3,
                            TRUE ~ NA_real_))

回答2:

Since you ask for other better ways to handle the problem, here\'s another way using data.table:

require(data.table) ## 1.9.2+
setDT(df)
df[a %in% c(0,1,3,4) | c == 4, g := 3L]
df[a %in% c(2,5,7) | (a==1 & b==4), g := 2L]

Note the order of conditional statements is reversed to get g correctly. There\'s no copy of g made, even during the second assignment - it\'s replaced in-place.

On larger data this would have better performance than using nested if-else, as it can evaluate both \'yes\' and \'no\' cases, and nesting can get harder to read/maintain IMHO.

---

Here\'s a benchmark on relatively bigger data:

# R version 3.1.0
require(data.table) ## 1.9.2
require(dplyr)
DT <- setDT(lapply(1:6, function(x) sample(7, 1e7, TRUE)))
setnames(DT, letters[1:6])
# > dim(DT) 
# [1] 10000000        6
DF <- as.data.frame(DT)

DT_fun <- function(DT) {
    DT[(a %in% c(0,1,3,4) | c == 4), g := 3L]
    DT[a %in% c(2,5,7) | (a==1 & b==4), g := 2L]
}

DPLYR_fun <- function(DF) {
    mutate(DF, g = ifelse(a %in% c(2,5,7) | (a==1 & b==4), 2L, 
            ifelse(a %in% c(0,1,3,4) | c==4, 3L, NA_integer_)))
}

BASE_fun <- function(DF) { # R v3.1.0
    transform(DF, g = ifelse(a %in% c(2,5,7) | (a==1 & b==4), 2L, 
            ifelse(a %in% c(0,1,3,4) | c==4, 3L, NA_integer_)))
}

system.time(ans1 <- DT_fun(DT))
#   user  system elapsed 
#  2.659   0.420   3.107 

system.time(ans2 <- DPLYR_fun(DF))
#   user  system elapsed 
# 11.822   1.075  12.976 

system.time(ans3 <- BASE_fun(DF))
#   user  system elapsed 
# 11.676   1.530  13.319 

identical(as.data.frame(ans1), as.data.frame(ans2))
# [1] TRUE

identical(as.data.frame(ans1), as.data.frame(ans3))
# [1] TRUE

Not sure if this is an alternative you\'d asked for, but I hope it helps.

回答3:

dplyr now has a function case_when that offers a vectorised if. The syntax is a little strange compared to mosaic:::derivedFactor as you cannot access variables in the standard dplyr way, and need to declare the mode of NA, but it is considerably faster than mosaic:::derivedFactor.

df %>%
mutate(g = case_when(a %in% c(2,5,7) | (a==1 & b==4) ~ 2L, 
                     a %in% c(0,1,3,4) | c == 4 ~ 3L, 
                     TRUE~as.integer(NA)))

EDIT: If you\'re using dplyr::case_when() from before version 0.7.0 of the package, then you need to precede variable names with \'.$\' (e.g. write .$a == 1 inside case_when).

Benchmark: For the benchmark (reusing functions from Arun \'s post) and reducing sample size:

require(data.table) 
require(mosaic) 
require(dplyr)
require(microbenchmark)

DT <- setDT(lapply(1:6, function(x) sample(7, 10000, TRUE)))
setnames(DT, letters[1:6])
DF <- as.data.frame(DT)

DPLYR_case_when <- function(DF) {
  DF %>%
  mutate(g = case_when(a %in% c(2,5,7) | (a==1 & b==4) ~ 2L, 
                       a %in% c(0,1,3,4) | c==4 ~ 3L, 
                       TRUE~as.integer(NA)))
}

DT_fun <- function(DT) {
  DT[(a %in% c(0,1,3,4) | c == 4), g := 3L]
  DT[a %in% c(2,5,7) | (a==1 & b==4), g := 2L]
}

DPLYR_fun <- function(DF) {
  mutate(DF, g = ifelse(a %in% c(2,5,7) | (a==1 & b==4), 2L, 
                    ifelse(a %in% c(0,1,3,4) | c==4, 3L, NA_integer_)))
}

mosa_fun <- function(DF) {
  mutate(DF, g = derivedFactor(
    \"2\" = (a == 2 | a == 5 | a == 7 | (a == 1 & b == 4)),
    \"3\" = (a == 0 | a == 1 | a == 4 | a == 3 |  c == 4),
    .method = \"first\",
    .default = NA
  ))
}

microbenchmark(
  DT_fun(DT),
  DPLYR_fun(DF),
  DPLYR_case_when(DF),
  mosa_fun(DF),
  times=20
)

This gives:

            expr        min         lq       mean     median         uq        max neval
         DT_fun(DT)   1.503589   1.626971   2.054825   1.755860   2.292157   3.426192    20
      DPLYR_fun(DF)   2.420798   2.596476   3.617092   3.484567   4.184260   6.235367    20
DPLYR_case_when(DF)   2.153481   2.252134   6.124249   2.365763   3.119575  72.344114    20
       mosa_fun(DF) 396.344113 407.649356 413.743179 412.412634 416.515742 459.974969    20

回答4:

The derivedFactor function from mosaic package seems to be designed to handle this. Using this example, it would look like:

library(dplyr)
library(mosaic)
df <- mutate(df, g = derivedFactor(
     \"2\" = (a == 2 | a == 5 | a == 7 | (a == 1 & b == 4)),
     \"3\" = (a == 0 | a == 1 | a == 4 | a == 3 |  c == 4),
     .method = \"first\",
     .default = NA
     ))

(If you want the result to be numeric instead of a factor, you can wrap derivedFactor in an as.numeric call.)

derivedFactor can be used for an arbitrary number of conditionals, too.

回答5:

case_when is now a pretty clean implementation of the SQL-style case when:

structure(list(a = c(1, 3, 4, 6, 3, 2, 5, 1), b = c(1, 3, 4, 
2, 6, 7, 2, 6), c = c(6, 3, 6, 5, 3, 6, 5, 3), d = c(6, 2, 4, 
5, 3, 7, 2, 6), e = c(1, 2, 4, 5, 6, 7, 6, 3), f = c(2, 3, 4, 
2, 2, 7, 5, 2)), .Names = c(\"a\", \"b\", \"c\", \"d\", \"e\", \"f\"), row.names = c(NA, 
8L), class = \"data.frame\") -> df


df %>% 
    mutate( g = case_when(
                a == 2 | a == 5 | a == 7 | (a == 1 & b == 4 )     ~   2,
                a == 0 | a == 1 | a == 4 |  a == 3 | c == 4       ~   3
))

Using dplyr 0.7.4

The manual: http://dplyr.tidyverse.org/reference/case_when.html