问题
I am using dplyr and trying to create a function to calculate p.values based on grouping arguments. I would like to be able to have an argument that would be list of any length of variables to group by. Here is the example dataset:
dataset <- structure(list(Experiment = c(170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170222, 170222, 170222, 170222,
170222, 170222, 170222, 170222, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824, 170824, 170824, 170824, 170824,
170824, 170824, 170824, 170824), Sample = c("1: FL_496", "1: FL_496",
"1: FL_496", "1: FL_496", "1: FL_496", "1: FL_496", "1: FL_496",
"1: FL_496", "2: FL_505", "2: FL_505", "2: FL_505", "2: FL_505",
"2: FL_505", "2: FL_505", "2: FL_505", "2: FL_505", "3: FL_509",
"3: FL_509", "3: FL_509", "3: FL_509", "3: FL_509", "3: FL_509",
"3: FL_509", "3: FL_509", "4: FL_514", "4: FL_514", "4: FL_514",
"4: FL_514", "4: FL_514", "4: FL_514", "4: FL_514", "4: FL_514",
"5: cKO_497", "5: cKO_497", "5: cKO_497", "5: cKO_497", "5: cKO_497",
"5: cKO_497", "5: cKO_497", "5: cKO_497", "6: cKO_504", "6: cKO_504",
"6: cKO_504", "6: cKO_504", "6: cKO_504", "6: cKO_504", "6: cKO_504",
"6: cKO_504", "7: cKO_510", "7: cKO_510", "7: cKO_510", "7: cKO_510",
"7: cKO_510", "7: cKO_510", "7: cKO_510", "7: cKO_510", "8: cKO_515",
"8: cKO_515", "8: cKO_515", "8: cKO_515", "8: cKO_515", "8: cKO_515",
"8: cKO_515", "8: cKO_515", "9: cKO_517", "9: cKO_517", "9: cKO_517",
"9: cKO_517", "9: cKO_517", "9: cKO_517", "9: cKO_517", "9: cKO_517",
NA, NA, NA, NA, NA, NA, NA, NA, "1: FL_627", "1: FL_627", "1: FL_627",
"1: FL_627", "1: FL_627", "1: FL_627", "2: FL_628", "2: FL_628",
"2: FL_628", "2: FL_628", "2: FL_628", "2: FL_628", "3: FL_633",
"3: FL_633", "3: FL_633", "3: FL_633", "3: FL_633", "3: FL_633",
"4: FL_636", "4: FL_636", "4: FL_636", "4: FL_636", "4: FL_636",
"4: FL_636", "5: cKO_620", "5: cKO_620", "5: cKO_620", "5: cKO_620",
"5: cKO_620", "5: cKO_620", "6: cKO_625", "6: cKO_625", "6: cKO_625",
"6: cKO_625", "6: cKO_625", "6: cKO_625", "7: cKO_626", "7: cKO_626",
"7: cKO_626", "7: cKO_626", "7: cKO_626", "7: cKO_626", "8: cKO_634",
"8: cKO_634", "8: cKO_634", "8: cKO_634", "8: cKO_634", "8: cKO_634",
"cKO_620", "cKO_620", "cKO_625", "cKO_625", "cKO_626", "cKO_626",
"cKO_634", "cKO_634", "FL_627", "FL_627", "FL_628", "FL_628",
"FL_633", "FL_633", "FL_636", "FL_636"), Genotype = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("miR-15/16 FL",
"miR-15/16 cKO"), class = "factor"), variable = c("% CD127+",
"% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+",
"% KLRG1+", "% KLRG1+", "% KLRG1+", "% CD127+", "% CD127+", "% CD127+",
"% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+", "% KLRG1+", "% CD127+",
"% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+",
"% KLRG1+", "% KLRG1+", "% KLRG1+", "% CD127+", "% CD127+", "% CD127+",
"% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+", "% KLRG1+", "% CD127+",
"% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+",
"% KLRG1+", "% KLRG1+", "% KLRG1+", "% CD127+", "% CD127+", "% CD127+",
"% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+", "% KLRG1+", "% CD127+",
"% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% CD127+", "% CD127+", "% KLRG1+", "% KLRG1+",
"% KLRG1+", "% CD127+", "% KLRG1+", "% CD127+", "% KLRG1+", "% CD127+",
"% KLRG1+", "% CD127+", "% KLRG1+", "% CD127+", "% KLRG1+", "% CD127+",
"% KLRG1+", "% CD127+", "% KLRG1+", "% CD127+", "% KLRG1+"),
value = c(1, 28.7, 40.1, 47.4, 64.1, 69.9, 73.1, 79.42, 0.99,
21.72, 33, 56.6, 55.5, 82.9, 84.96, 86.7, 3.94, 43.4, 49.5,
60.8, 57.1, 69.8, 71.4, 77.72, 1, 20.56, 28.77, 35.1, 71.07,
71.2, 78.16, 84.04, 3.77, 56.9, 60.5, 66.5, 43.7, 50.36,
50.8, 51.8, 3.24, 58.2, 59.8, 70.8, 47.9, 58.5, 59.5, 61.3,
4.21, 62, 65.7, 73.8, 40, 51.5, 53.1, 55.69, 9.48, 41.7,
44, 63, 53.7, 57.31, 60.4, 60.8, 3.84, 34.1, 41.1, 53.2,
55.07, 55.3, 62.2, 76.6, NA, NA, NA, NA, NA, NA, NA, NA,
12.01, 18.5, 20.99, 66.39, 77.2, 85.6, 12.8, 31.3, 35.11,
59.8, 85.5, 89.7, 32.1, 33.3, 34.7, 63.2, 71.6, 80.5, 15.3,
17.02, 33.5, 65.54, 82.7, 85.8, 41.61, 51.3, 69.3, 39.81,
59, 62, 46.6, 52.1, 67.8, 39.5, 58.8, 66, 52.2, 52.9, 68.7,
46, 55.9, 61.6, 45.17, 59.9, 74.3, 31.87, 48.4, 51.2, 6.2,
56.34, 4.17, 70.85, 3.54, 59.89, 5.61, 49.71, 1.87, 77.09,
0.51, 86.05, 1.8, 80.69, 2.15, 79.43), Day = structure(c(1L,
2L, 3L, 4L, 4L, 3L, 2L, 1L, 1L, 3L, 4L, 2L, 2L, 4L, 1L, 3L,
1L, 3L, 2L, 4L, 4L, 2L, 3L, 1L, 1L, 3L, 4L, 2L, 4L, 2L, 3L,
1L, 1L, 3L, 2L, 4L, 4L, 1L, 2L, 3L, 1L, 3L, 2L, 4L, 4L, 2L,
3L, 1L, 1L, 3L, 2L, 4L, 4L, 3L, 2L, 1L, 1L, 3L, 4L, 2L, 2L,
1L, 4L, 3L, 1L, 2L, 3L, 4L, 1L, 4L, 3L, 2L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 3L, 2L, 4L, 3L, 2L, 4L, 2L, 3L, 4L, 3L, 2L,
4L, 2L, 3L, 4L, 3L, 2L, 4L, 2L, 3L, 4L, 3L, 4L, 2L, 3L, 2L,
4L, 3L, 2L, 4L, 3L, 2L, 4L, 3L, 2L, 4L, 3L, 2L, 4L, 3L, 2L,
4L, 3L, 2L, 4L, 3L, 2L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("8", "15", "22",
"30+"), class = "factor")), class = "data.frame", row.names = c(NA,
-144L), .Names = c("Experiment", "Sample", "Genotype", "variable",
"value", "Day"))
and here is the function I have made that works using ...
grouped.t.test <- function(dataset, subset.plot, comparison, ...)
{
group.by <- quos(...)
if (is.null(subset.plot)){
subset.plot <- dataset[['variable']]
}
filter(dataset, variable %in% subset.plot) %>%
group_by(!!!group.by) %>%
do(tidy(t.test(x = .$value[.[comparison] == levels(.[[comparison]])[1]],
y = .$value[.[comparison] == levels(.[[comparison]])[2]]))) %>%
mutate(p.value.format = symnum(p.value, corr = FALSE, na = FALSE, cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, 1), symbols = c("****", "***", "**", "*", NA))) %>%
arrange(!!!group.by)
}
View(grouped.t.test(dataset = dataset, subset.plot = NULL, comparison = 'Genotype', variable, Day))
I would like to be able to replace ... with an argument (e.g., group_vars) and call it like this:
View(grouped.t.test(dataset = dataset, subset.plot = NULL, comparison = 'Genotype', group_vars = c(variable, Day)))
This does not seem to work with quos() but I don't understand why. It would be nice to be able to use multiple list arguments that get quosed and used independently (e.g., creating an argument "arrange.by" that would be a list of variables to pass to arrange at the end of the function.
I'd greatly appreciate any help understanding why this doesn't work and what I could do instead!
回答1:
As mentioned by @lionel - one of the lead developers of dplyr in this comment
You want the quoting to be external and explicitly done by the user rather than implicitly by your function. To this end you can ask your users to quote with base::alist(), rlang::exprs(), or dplyr::vars()
You can do something like this for your question
grouped.t.test2 <- function(dataset, subset.plot, comparison, group_vars) {
if (is.null(subset.plot)) {
subset.plot <- dataset[['variable']]
}
filter(dataset, variable %in% subset.plot) %>%
group_by(!!! group_vars) %>%
do(tidy(t.test(x = .$value[.[comparison] == levels(.[[comparison]])[1]],
y = .$value[.[comparison] == levels(.[[comparison]])[2]]))) %>%
mutate(p.value.format = symnum(p.value, corr = FALSE, na = FALSE,
cutpoints = c(0, 0.0001, 0.001, 0.01, 0.05, 1),
symbols = c("****", "***", "**", "*", NA))) %>%
arrange(!!! group_vars)
}
grouped.t.test2(dataset = dataset, subset.plot = NULL, comparison = 'Genotype',
alist(variable, Day))
# or
grouped.t.test2(dataset = dataset, subset.plot = NULL, comparison = 'Genotype',
dplyr::vars(variable, Day))
# A tibble: 8 x 13
# Groups: variable, Day [8]
variable Day estimate estimate1 estimate2 statistic p.value parameter
<fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 % CD127+ 8 -3.24 1.66 4.90 -4.26 9.93e-4 12.6
2 % CD127+ 15 -24.4 31.1 55.5 -3.80 2.88e-3 11.2
3 % CD127+ 22 -22.1 27.4 49.5 -4.60 5.54e-4 12.5
4 % CD127+ 30+ -28.6 36.8 65.4 -5.23 1.36e-4 13.7
5 % KLRG1+ 8 23.8 81.2 57.4 9.79 3.11e-7 12.5
6 % KLRG1+ 15 16.5 73.7 57.2 3.78 2.08e-3 13.8
7 % KLRG1+ 22 20.9 70.1 49.2 4.44 4.82e-4 14.9
8 % KLRG1+ 30+ 22.5 76.7 54.2 4.46 6.01e-4 13.4
# ... with 5 more variables: conf.low <dbl>, conf.high <dbl>,
# method <fct>, alternative <fct>, p.value.format <chr>
来源：https://stackoverflow.com/questions/49826595/using-dplyrquos-with-a-list-argument-rather-than-the-ellipsis-argument