问题
maybe I am missing something, but I can't seem to make dplyr's unquoting operator to work with the filter function. It does with with select, but not with filter...
Example
set.seed(1234)
A = matrix(rnorm(100),nrow = 10, ncol = 10)
colnames(A) <- paste("var", seq(1:10), sep = "")
varname_test <- "var2"
A <- as_tibble(A)
select(A, !!varname_test) #this works as expected
# this does NOT give me only the rows where var2
# is positive
(result1 <- filter(A, !!varname_test > 0))
# This is how the result 1 should look like
(result2 <- filter(A, var2 > 0))
# result1 is not equal to result2
I would appreciate any help!
回答1:
I would suggest the following:
library(dplyr)
filter_at(A, vars(starts_with(varname_test)), any_vars(. > 0))
A tibble: 3 x 10
var1 var2 var3 var4 var5 var6 var7 var8 var9 var10
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 -2.35 0.0645 0.460 -0.501 -0.281 -1.01 -0.670 0.648 -0.174 1.00
2 0.429 0.959 -0.694 -1.63 -0.994 -0.162 -0.00760 2.07 0.850 -0.496
3 -0.890 2.42 -0.936 -0.466 -0.497 -1.16 0.336 -0.317 -1.19 2.12
回答2:
Here, my solution (1g) uses filter_ and conditions built up with paste. Of course, 1a is a perfectly fine solution (as was provided by joran and aosmith in the comments).
I thought this might be a good place to use curly curly but I couldn't get it to work (maybe not applicable?)
I also thought: what if we wanted to filter by multiple variables? This is where you see 2g working below (while 2a does not work anymore).
Other issues: filter_ is now deprecated, and I'm not sure what the correct syntax would be here. Will be asking this in a question.
library(tidyverse)
set.seed(1234)
A <- matrix(rnorm(30),nrow = 10, ncol = 3) %>% as_tibble() %>% set_names(paste("var", seq(1:3), sep = ""))
varnames_1 <- c("var2")
(expected_result_1 <- filter(A, var2 > 0))
#> # A tibble: 3 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -2.35 0.0645 0.460
#> 2 0.429 0.959 -0.694
#> 3 -0.890 2.42 -0.936
(answer_1a <- filter(A,!!ensym(varnames_1) > 0)) # works (thanks joran and aosmith)
#> # A tibble: 3 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -2.35 0.0645 0.460
#> 2 0.429 0.959 -0.694
#> 3 -0.890 2.42 -0.936
(answer_1b <- filter_(A, varnames_1 > 0)) # filter_ not doing what I thought it might
#> Warning: filter_() is deprecated.
#> Please use filter() instead
#>
#> The 'programming' vignette or the tidyeval book can help you
#> to program with filter() : https://tidyeval.tidyverse.org
#> This warning is displayed once per session.
#> # A tibble: 10 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -1.21 -0.477 0.134
#> 2 0.277 -0.998 -0.491
#> 3 1.08 -0.776 -0.441
#> 4 -2.35 0.0645 0.460
#> 5 0.429 0.959 -0.694
#> 6 0.506 -0.110 -1.45
#> 7 -0.575 -0.511 0.575
#> 8 -0.547 -0.911 -1.02
#> 9 -0.564 -0.837 -0.0151
#> 10 -0.890 2.42 -0.936
(answer_1c <- filter(A, {{varnames_1}} > 0)) # curly curly not doing what I thought it might
#> # A tibble: 10 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -1.21 -0.477 0.134
#> 2 0.277 -0.998 -0.491
#> 3 1.08 -0.776 -0.441
#> 4 -2.35 0.0645 0.460
#> 5 0.429 0.959 -0.694
#> 6 0.506 -0.110 -1.45
#> 7 -0.575 -0.511 0.575
#> 8 -0.547 -0.911 -1.02
#> 9 -0.564 -0.837 -0.0151
#> 10 -0.890 2.42 -0.936
(answer_1d <- filter(A, {{varnames_1 > 0}})) # curly curly not doing what I thought it might
#> `arg` must be a symbol
conditions_1 <- paste(varnames_1, "> 0")
(answer_1e <- filter(A, conditions_1)) # does not work
#> Error: Argument 2 filter condition does not evaluate to a logical vector
(answer_1f <- filter(A, {{conditions_1}})) # curly curly not doing what I thought it might
#> Error: Argument 2 filter condition does not evaluate to a logical vector
(answer_1g <- filter_(A, conditions_1)) # works
#> # A tibble: 3 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -2.35 0.0645 0.460
#> 2 0.429 0.959 -0.694
#> 3 -0.890 2.42 -0.936
# what if we wanted to filter multiple variables?
varnames_2 <- c("var2", "var3")
(expected_result_2 <- filter(A, var2 > 0 & var3 > 0))
#> # A tibble: 1 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -2.35 0.0645 0.460
(answer_2a <- filter(A,!!ensym(varnames_2) > 0)) # does not work
#> Only strings can be converted to symbols
conditions_2 <- paste(paste(varnames_2, "> 0"), collapse = " & ")
(answer_2f <- filter(A, {{conditions_2}})) # curly curly not doing what I thought it might
#> Error: Argument 2 filter condition does not evaluate to a logical vector
(answer_2g <- filter_(A, conditions_2)) # works
#> # A tibble: 1 x 3
#> var1 var2 var3
#> <dbl> <dbl> <dbl>
#> 1 -2.35 0.0645 0.460
Created on 2019-08-28 by the reprex package (v0.3.0)
来源:https://stackoverflow.com/questions/54350264/dplyr-unquoting-does-not-work-with-filter-function