R中的rank函数仅返回1的rank

Question

我有一个数据集，我想对平均准确率(meanacc)和平均RT (meanrt)进行排名，以找到每个参与者(id)的最佳和最差素数。

数据：

    data <- dput(sum_dat_id2)
    structure(list(id = structure(c(1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 
    4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 8L, 8L, 8L, 9L, 
    9L, 9L), .Label = c("8c2ybacs", "a5y79isc", "amya7xh9", "e9jjib8j", 
    "gy2iobr9", "i9la2x3h", "lotedm1d", "uhxghpam", "wmke4pwa"), class = "factor"), 
        Grade = 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), .Label = "7th", class = "factor"), GradeNum = 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), .Label = "7", class = "factor"), 
        Prime = structure(c(2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
        3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
        3L), .Label = c("s100w100", "s135w150", "s50w100"), class = "factor"), 
        Sex = c("Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female"), Number_Languages = 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, 2L, 2L, 2L), .Label = c("monolingual", 
        "trilingual"), class = "factor"), meanacc = c(0.5, 0.333333333333333, 
        0.5, 0.447368421052632, 0.323529411764706, 0.488372093023256, 
        0.545454545454545, 0.545454545454545, 0.6, 0.5, 0.416666666666667, 
        0.568181818181818, 0.454545454545455, 0.558139534883721, 
        0.564102564102564, 0.432432432432432, 0.457142857142857, 
        0.529411764705882, 0.318181818181818, 0.318181818181818, 
        0.422222222222222, 0.51219512195122, 0.425, 0.837209302325581, 
        0.780487804878049, 0.871794871794872), meanrt = c(235.635, 
        221.1, 218.365416666667, 128.225789473684, 133.196764706176, 
        914.898255813953, 890.709886363636, 712.409090909091, 282.70525, 
        444.358088235294, 316.470138888889, 880.698295454545, 720.212954545455, 
        902.265930232558, 538.900256410256, 444.451081081081, 437.215285714286, 
        285.566617647059, 105.416363636364, 202.969545454545, 1005.48833333333, 
        642.993902439024, 760.722, 637.837906976512, 722.863170732439, 
        656.063461538462), n = c(2L, 3L, 36L, 38L, 34L, 43L, 44L, 
        44L, 40L, 34L, 36L, 44L, 44L, 43L, 39L, 37L, 35L, 34L, 22L, 
        22L, 45L, 41L, 40L, 43L, 41L, 39L)), row.names = c(NA, -26L
    ), groups = structure(list(id = structure(c(1L, 1L, 2L, 2L, 2L, 
    3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 8L, 
    8L, 8L, 9L, 9L, 9L), .Label = c("8c2ybacs", "a5y79isc", "amya7xh9", 
    "e9jjib8j", "gy2iobr9", "i9la2x3h", "lotedm1d", "uhxghpam", "wmke4pwa"
    ), class = "factor"), Grade = 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), .Label = "7th", class = "factor"), GradeNum = 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), .Label = "7", class = "factor"), 
        Prime = structure(c(2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
        3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
        3L), .Label = c("s100w100", "s135w150", "s50w100"), class = "factor"), 
        Sex = c("Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female", "Female", "Female", "Female", 
        "Female", "Female", "Female"), .rows = structure(list(1L, 
            2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 
            15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 
            26L), ptype = integer(0), class = c("vctrs_list_of", 
        "vctrs_vctr", "list"))), row.names = c(NA, -26L), class = c("tbl_df", 
    "tbl", "data.frame"), .drop = TRUE), class = c("grouped_df", 
    "tbl_df", "tbl", "data.frame"))

当我使用这段代码时，我只得到两列(acc_rank和rt_rank)，其中所有内容的排名都是1：

best <-sum_dat_id2 %>%  mutate(acc_rank  = rank(meanacc, ties.method = "average")) %>%
      mutate(rt_rank  = rank(meanrt, ties.method = "average")) 

结果数据示例：

head(best)

# A tibble: 6 x 11
# Groups:   id, Grade, GradeNum, Prime, Sex [6]
  id       Grade GradeNum Prime    Sex    Number_Languages meanacc meanrt     n acc_rank rt_rank
  <fct>    <fct> <fct>    <fct>    <chr>  <fct>              <dbl>  <dbl> <int>    <dbl>   <dbl>
1 8c2ybacs 7th   7        s135w150 Female monolingual        0.5     236.     2        1       1
2 8c2ybacs 7th   7        s50w100  Female monolingual        0.333   221.     3        1       1
3 a5y79isc 7th   7        s100w100 Female monolingual        0.5     218.    36        1       1
4 a5y79isc 7th   7        s135w150 Female monolingual        0.447   128.    38        1       1
5 a5y79isc 7th   7        s50w100  Female monolingual        0.324   133.    34        1       1
6 amya7xh9 7th   7        s100w100 Female monolingual        0.488   915.    43        1       1

有没有人知道为什么会发生这样的事情？

Answer 1

您可以在dplyr中使用dense_rank：

library(dplyr)

sum_dat_id2 %>% 
  group_by (id) %>% 
  mutate(acc_rank = dense_rank(meanacc),
         rt_rank = dense_rank(meanrt)) 

Answer 2

在data.table中使用frank

library(data.table)
setDT(sum_dat_id2)[, c('acc_rank', 'rt_rank') := 
       lapply(.SD, frank, method = 'dense'), id, .SDcols = c('meanacc', 'meanrt')]