3

私は dplyr を使用しており、グループ化引数に基づいて p.values を計算する関数を作成しようとしています。グループ化する任意の長さの変数のリストになる引数を持つことができるようにしたいと思います。データセットの例を次に示します。

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"))

そして、これが私が作成した機能であり、...を使用して機能します

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))

... を引数 (例: group_vars) に置き換えて、次のように呼び出したいと思います。

View(grouped.t.test(dataset = dataset, subset.plot = NULL, comparison = 'Genotype', group_vars = c(variable, Day)))

これは quos() では機能しないようですが、理由がわかりません。引用されて独立して使用される複数のリスト引数を使用できると便利です (たとえば、関数の最後に配置するために渡す変数のリストである引数「arrange.by」を作成します。

これが機能しない理由と、代わりに何ができるかを理解していただければ幸いです。

4

1 に答える 1

3
于 2018-04-14T17:56:49.907 に答える