基于 R 中的一组规则的模拟

Question

我想运行一个随机选择行并根据一组规则将行的总值相加的模拟程序。我是模拟新手，所以不知道从哪里开始。

规则：每个 sim 卡总共选择 9 行。每个 9 的 sim 卡必须包含以下数量的“位置”：

QB：1
RB：2
WR：3
TE: 1
克：1
夏令时：1

我希望每个 sim 将组的值（WAR 列）和输出相加，以显示每个玩家的百分比，例如 WAR 最高的组的前 10%。希望这有点道理。这里的最终目标是确定哪些玩家最有可能成功。

这里以每个位置的十名顶级球员为例。

dput

    structure(list(player = c("Justin Tucker", "Harrison Butker", 
    "Wil Lutz", "Greg Zuerlein", "Matt Gay", "Brandon McManus", "Jake Elliott", 
    "Robbie Gould", "Stephen Hauschka", "Dan Bailey", "Patrick Mahomes", 
    "Lamar Jackson", "Dak Prescott", "Russell Wilson", "Kyler Murray", 
    "Deshaun Watson", "Matt Ryan", "Josh Allen", "Tom Brady", "Carson Wentz", 
    "Christian McCaffrey", "Saquon Barkley", "Ezekiel Elliott", "Alvin Kamara", 
    "Dalvin Cook", "Clyde Edwards-Helaire", "Derrick Henry", "Miles Sanders", 
    "Joe Mixon", "Josh Jacobs", "Travis Kelce", "George Kittle", 
    "Mark Andrews", "Zach Ertz", "Darren Waller", "Evan Engram", 
    "Hayden Hurst", "Tyler Higbee", "Hunter Henry", "Mike Gesicki", 
    "Michael Thomas", "Davante Adams", "Julio Jones", "Tyreek Hill", 
    "DeAndre Hopkins", "Chris Godwin", "Kenny Golladay", "Allen Robinson", 
    "DJ Moore", "Odell Beckham"), adp = c(3, 3, 2, 2, 1, 1, 1, 1, 
    1, 1, 26, 23, 12, 11, 10, 9, 5, 4, 4, 4, 66, 57, 53, 50, 45, 
    43, 41, 40, 40, 39, 29, 26, 18, 15, 10, 8, 7, 6, 4, 4, 48, 40, 
    38, 37, 36, 34, 29, 27, 27, 27), WAR = c(0.27, 0.27, 0.1, 0.23, 
    0.09, 0.19, -0.83, -0.3, -0.1, -0.62, 2.26, 1.41, 0.91, 1.7, 
    2.28, 1.74, 0.28, 2.29, 1.12, 0.06, 1.02, -0.05, 1.36, 3.57, 
    3.48, 1.04, 2.91, 1.13, 0.69, 1.49, 2.79, 0.71, 0.85, -0.22, 
    1.67, 0.07, 0.26, 0.06, 0.35, 0.64, -0.04, 2.74, 0.63, 2.35, 
    1.49, 0.49, 0.33, 1.17, 0.61, 0.28), position = c("K", "K", "K", 
    "K", "K", "K", "K", "K", "K", "K", "QB", "QB", "QB", "QB", "QB", 
    "QB", "QB", "QB", "QB", "QB", "RB", "RB", "RB", "RB", "RB", "RB", 
    "RB", "RB", "RB", "RB", "TE", "TE", "TE", "TE", "TE", "TE", "TE", 
    "TE", "TE", "TE", "WR", "WR", "WR", "WR", "WR", "WR", "WR", "WR", 
    "WR", "WR")), row.names = c(NA, -50L), groups = structure(list(
    position = c("K", "QB", "RB", "TE", "WR"), .rows = structure(list(
        1:10, 11:20, 21:30, 31:40, 41:50), ptype = integer(0), class = c("vctrs_list_of", 
    "vctrs_vctr", "list"))), row.names = c(NA, -5L), class = c("tbl_df", 
    "tbl", "data.frame"), .drop = TRUE), class = c("grouped_df", 
    "tbl_df", "tbl", "data.frame"))

Answer 1

一个想法是您可以使用查找表来设置每组的样本数，然后通过从每个组中采样 n_samples 创建一个函数来运行“模拟”。不完全确定 WAR 的总和是什么，但一旦你进行了模拟操作，比如分组总和，应该很简单。

请注意，您的示例数据中没有“DST”位置，因此每次模拟仅出现 8 个。

library(tidyverse)

# lookup table
df_sample <- data.frame(position = c("K", "QB", "RB", "TE", "WR", "DST"),
                        n_samples =   c(1,     1,    2,   1,    3,    1))


df_nest <- df %>%
  left_join(df_sample) %>%
  group_by(position, n_samples) %>%
  nest

run_sim <- function(nested_df = df_nest){
  nested_df %>%
    mutate(sim = map2(data, n_samples, sample_n)) %>%
    ungroup() %>%
    select(-data, -n_samples) %>%
    unnest(sim)
}


map_dfr(1:10, ~run_sim(df_nest), .id = 'sim')

#----
# A tibble: 80 x 5
   sim   position player             adp   WAR
   <chr> <chr>    <chr>            <dbl> <dbl>
 1 1     K        Dan Bailey           1 -0.62
 2 1     QB       Patrick Mahomes     26  2.26
 3 1     RB       Miles Sanders       40  1.13
 4 1     RB       Joe Mixon           40  0.69
 5 1     TE       Evan Engram          8  0.07
 6 1     WR       Julio Jones         38  0.63
 7 1     WR       Michael Thomas      48 -0.04
 8 1     WR       DeAndre Hopkins     36  1.49
 9 2     K        Stephen Hauschka     1 -0.1 
10 2     QB       Russell Wilson      11  1.7 
# ... with 70 more rows