Question

我希望获得一些帮助来确定：

不存在NA值时缺失观测值的位置（缺少整行）。
根据某些类别的平均值为平均值的缺失数据创建一行。

我的df：

曲棍球运动员在整个赛季练习期间的数值负荷数据
有时候，即使玩家进行了练习，加速度计也无法正常工作。因此，为了确保我们仍然可以跟踪他们在练习中所做的工作，我想在练习中从他们的位置（前锋，防守或守门员）中插入平均值。（即，如果守门员的加速度计不起作用，我想取其他守门员的平均负荷并将其插入该球员的观察行进行练习）。
如果从在线云下载csv中的数据时，如果加速度计不起作用，但是当加速度计不起作用时，如果有排所有的玩家各自练习和负载的NA值，这将是一个更简单的任务，工作单位。所以那部分是我无法控制的。

> head(DummyLoads)  
 Name       Date Load Position    
1   Jim 2019-10-19  900    2.100  Forward 
2   Bob 2019-10-19  900    2.100  Forward 
3  Dave 2019-10-19  900    2.100  Forward 
4 Steve 2019-10-19  850    2.312  Forward 
5  Fred 2019-10-19  850    2.312  Defense 
6   Ray 2019-10-19  850    2.312  Defense

DummyLoads <- structure(list(Name = structure(c(4L, 1L, 2L, 6L, 3L, 5L, 4L, 1L, 2L, 3L, 5L, 4L, 1L, 2L, 6L, 3L, 5L, 2L, 6L, 3L, 5L),
 .Label = c("Bob",  "Dave", "Fred", "Jim", "Ray", "Steve"), 
class = "factor"), 
Date = structure(c(1L,  1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L,  4L, 4L, 4L, 4L), 
.Label = c("2019-10-19", "2019-10-20", "2019-10-21",  "2019-10-22"), class = "factor"), 
Load = c(900L, 900L, 900L,  850L, 850L, 850L, 789L, 789L, 789L, 960L, 960L, 909L, 909L, 909L,  991L, 991L, 991L, 720L, 717L, 717L, 717L), 
Load.Min = c(2.1,  2.1, 2.1, 2.312, 2.312, 2.312, 2.22, 2.22, 2.22, 2, 2, 1.88,  1.88, 1.88, 1.99, 1.99, 1.99, 2.1, 2.3, 2.3, 2.3), Position = structure(c(2L,  2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,  2L, 2L, 1L, 1L), 
.Label = c("Defense", "Forward"), class = "factor")), class = "data.frame", row.names = c(NA,  -21L))

ggplot(DummyLoads, aes(x = Name, y = Load, fill = Position))+
  geom_bar(stat = "identity")+
  facet_grid(~Date)

以下是显示缺少数据的玩家的图表。

Missing Player Loads

理想情况下，我希望能够识别那些缺失的数据点，而不必先绘制它。我还希望避免每次都要手动计算均值然后再输入。希望找到一个自动化的解决方案，因为我将有一个完整的实践季节来执行此操作，但是请理解，这可能很棘手！

在此先感谢您的任何建议。如果我没有清楚说明问题，我深表歉意。

实际df：

structure(list(Athlete = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 
2L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 
7L, 7L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 11L, 
11L, 11L, 11L, 12L, 12L, 12L, 13L, 13L, 13L, 13L, 14L, 14L, 14L, 
14L, 15L, 15L, 15L, 16L, 16L, 16L, 17L, 17L, 17L, 17L, 18L, 18L, 
18L, 18L, 19L, 19L, 19L, 19L, 20L, 20L, 20L, 20L, 21L, 21L, 21L, 
21L, 22L, 22L, 22L, 23L, 23L, 23L, 23L, 24L, 24L, 24L, 24L, 25L, 
25L, 25L, 25L, 26L, 26L, 26L, 26L, 27L, 27L, 27L, 27L, 28L, 28L, 
28L), .Label = c("Agosta", "Ambrose", "Bach", "Bettez", "Clark", 
"Daoust", "Desbiens", "Eldridge", "Fast", "Fortino", "Gabel", 
"Jenner", "Johnston", "Lacasse", "Lacquette", "Larocque", "Leslie", 
"Maschmeyer", "Mikkelson", "Nurse", "Poulin", "Pozzebon", "Rattray", 
"Rougeau", "Saulnier", "Stacey", "Tiley", "Turnbull"), class = "factor"), 
    Date = structure(c(18170, 18171, 18172, 18169, 18170, 18171, 
    18172, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 18169, 
    18170, 18171, 18172, 18169, 18170, 18171, 18170, 18171, 18172, 
    18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 18169, 
    18170, 18171, 18172, 18169, 18170, 18171, 18172, 18170, 18171, 
    18172, 18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 
    18170, 18171, 18172, 18170, 18171, 18172, 18169, 18170, 18171, 
    18172, 18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 
    18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 18170, 
    18171, 18172, 18169, 18170, 18171, 18172, 18169, 18170, 18171, 
    18172, 18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 
    18169, 18170, 18171, 18172, 18170, 18171, 18172), class = "Date"), 
    Position = structure(c(2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 
    2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 
    1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 
    1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 
    3L, 2L, 2L, 2L), .Label = c("Defense", "Forward", "Goalie"
    ), class = "factor"), PL_Avg = c(178.5, 123, 174, 191, 163.5, 
    169, 155, 158.5, 158.5, 172, 214, 169, 220.5, 175, 235, 191.5, 
    217.5, 145, 217, 184.5, 181, 135, 68, 104, 190, 127.5, 129, 
    136, 210, 194, 208.5, 168, 220, 189.5, 213, 192, 180, 204, 
    167.5, 187, 178, 196.5, 151, 204, 200, 170.5, 165, 107, 116, 
    100.5, 88, 189.5, 131.5, 178, 176, 200.5, 157, 315, 174, 
    182.5, 168, 100, 130.5, 114.5, 75, 205, 154.5, 198, 175, 
    163, 160.5, 200, 149, 185, 154, 149.5, 182, 177, 192, 161, 
    287, 179.5, 166, 157, 188, 163.5, 171.5, 153, 220, 111.5, 
    197, 110, 214, 188.5, 184, 173, 100, 103, 99, 64, 173.5, 
    137, 143), PL_Min_Avg = c(2.41, 2.68, 2.46, 2.21, 2.205, 
    2.4, 2.19, 2.075, 2.185, 2.08, 2.46, 2.22, 2.615, 2.48, 2.7, 
    2.5, 2.57, 2.06, 2.5, 2.42, 2.505, 1.515, 1.43, 1.75, 1.67, 
    1.675, 1.785, 1.92, 2.42, 2.645, 2.485, 2.38, 2.54, 2.6, 
    2.5, 2.72, 2.08, 2.56, 2.315, 2.27, 2.33, 2.325, 2.13, 2.36, 
    2.28, 2.355, 2.33, 1.38, 1.3, 1.19, 1.47, 2.56, 2.33, 2.52, 
    2.385, 2.39, 2.23, 2.58, 2.28, 2.525, 2.38, 1.41, 1.465, 
    1.325, 1.82, 2.36, 2.58, 2.38, 2.48, 1.88, 2.115, 2.37, 2.11, 
    2.13, 2.02, 2.075, 1.8, 2.395, 2.29, 2.27, 2.35, 2.345, 2.29, 
    2.23, 2.16, 2.225, 2.02, 2.17, 2.53, 2.115, 2.72, 2.16, 2.47, 
    2.465, 2.555, 2.45, 1.29, 1.145, 1.145, 1.57, 1.97, 1.82, 
    2.03)), row.names = c(NA, -103L), class = c("grouped_df", 
"tbl_df", "tbl", "data.frame"), groups = structure(list(Athlete = structure(c(1L, 
1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 
5L, 6L, 6L, 6L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 10L, 
10L, 10L, 10L, 11L, 11L, 11L, 11L, 12L, 12L, 12L, 13L, 13L, 13L, 
13L, 14L, 14L, 14L, 14L, 15L, 15L, 15L, 16L, 16L, 16L, 17L, 17L, 
17L, 17L, 18L, 18L, 18L, 18L, 19L, 19L, 19L, 19L, 20L, 20L, 20L, 
20L, 21L, 21L, 21L, 21L, 22L, 22L, 22L, 23L, 23L, 23L, 23L, 24L, 
24L, 24L, 24L, 25L, 25L, 25L, 25L, 26L, 26L, 26L, 26L, 27L, 27L, 
27L, 27L, 28L, 28L, 28L), .Label = c("Agosta", "Ambrose", "Bach", 
"Bettez", "Clark", "Daoust", "Desbiens", "Eldridge", "Fast", 
"Fortino", "Gabel", "Jenner", "Johnston", "Lacasse", "Lacquette", 
"Larocque", "Leslie", "Maschmeyer", "Mikkelson", "Nurse", "Poulin", 
"Pozzebon", "Rattray", "Rougeau", "Saulnier", "Stacey", "Tiley", 
"Turnbull"), class = "factor"), Date = structure(c(18170, 18171, 
18172, 18169, 18170, 18171, 18172, 18170, 18171, 18172, 18169, 
18170, 18171, 18172, 18169, 18170, 18171, 18172, 18169, 18170, 
18171, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 18169, 
18170, 18171, 18172, 18169, 18170, 18171, 18172, 18169, 18170, 
18171, 18172, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 
18169, 18170, 18171, 18172, 18170, 18171, 18172, 18170, 18171, 
18172, 18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 
18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 18169, 
18170, 18171, 18172, 18170, 18171, 18172, 18169, 18170, 18171, 
18172, 18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 
18169, 18170, 18171, 18172, 18169, 18170, 18171, 18172, 18170, 
18171, 18172), class = "Date"), .rows = 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, 27L, 28L, 29L, 
    30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L, 
    42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L, 52L, 53L, 
    54L, 55L, 56L, 57L, 58L, 59L, 60L, 61L, 62L, 63L, 64L, 65L, 
    66L, 67L, 68L, 69L, 70L, 71L, 72L, 73L, 74L, 75L, 76L, 77L, 
    78L, 79L, 80L, 81L, 82L, 83L, 84L, 85L, 86L, 87L, 88L, 89L, 
    90L, 91L, 92L, 93L, 94L, 95L, 96L, 97L, 98L, 99L, 100L, 101L, 
    102L, 103L)), row.names = c(NA, -103L), class = c("tbl_df", 
"tbl", "data.frame"), .drop = TRUE))

Answer 1

已更新至当前问题：

DummyLoads <- DummyLoads %>% 
  ungroup()
full_data <- expand.grid(
  Athlete = DummyLoads %>% 
    pull(Athlete) %>% 
    unique(),
  Date = DummyLoads %>% 
    pull(Date) %>% 
    unique())


full_data %>% 
  # join incomplete data onto full data
  left_join(DummyLoads, by = c("Athlete", "Date")) %>% 
  # assign the position to each player
  # in the example data, some players do ahve different positions
  # if this is true, than it would be unclear which average should be
  # considered. Therefore, I assumed their position is constant
  left_join(DummyLoads %>% 
              select(Athlete, Position) %>% 
              distinct(Athlete, .keep_all=TRUE),
            by = "Athlete") %>% 
  # keep both to check the differences
  rename(Position = Position.y) %>% 
  group_by(Date, Position) %>% 
  # if Load is missing, take the mean of Loads which is grouped
  mutate(Load2 = coalesce(PL_Avg, 
                          mean(PL_Avg, na.rm = T)))

Answer 2

通用Base R解决方案：

# Mark out NA rows flatten in single observation (each element denoting a vector of the df):

    is_val_na <- apply(data.frame(lapply(DummyLoads,

                                         function(x){is.na(x)})), 1, paste, collapse = ", " )

    # Split up using the grouping var "Name", and impute the mean where NA, coerce list to df: 

    DummyLoads_imputed <- do.call("rbind", lapply(split(DummyLoads, DummyLoads$Position), 
                              function(x){
                                if(is.numeric(x)){
                                  ifelse(is.na(x), mean(x, na.rm = TRUE), x)
                                  }else{x}
                                }
                              )
                            )

    # Bind the data.frame with a factor vector holding the T/F values: 

    DummyLoads_imputed <- cbind(DummyLoads_imputed, row_na = as.factor(is_val_na))

使用的数据：

DummyLoads <- structure(list(Name = structure(c(4L, 1L, 2L, 6L, 3L, 5L, 4L, 1L, 2L, 3L, 5L, 4L, 1L, 2L, 6L, 3L, 5L, 2L, 6L, 3L, 5L), 
                                          .Label = c("Bob",  "Dave", "Fred", "Jim", "Ray", "Steve"),
                                          class = "factor"), Date = structure(c(1L,  1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
                                                                                3L, 3L, 3L,  4L, 4L, 4L, 4L), .Label = c("2019-10-19", "2019-10-20", "2019-10-21",  "2019-10-22"), 
                                                                              class = "factor"), Load = c(900L, 900L, 900L,  850L, 850L, 850L, 789L, 789L, 789L, 960L, 
                                                                                                          960L, 909L, 909L, 909L,  991L, 991L, 991L, 720L, 717L, 717L, 717L), 
                         Position = structure(c(2L,  2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,  1L, 2L, 1L, 1L), 
                                              .Label = c("Defense", "Forward"), class = "factor")), row.names = c(NA,  -21L), class = "data.frame")

用平均值查找和填充缺失的观测值（整行不是NA值）

2 个答案: