指示特定值第一次出现的新变量

Question

我想创建一个新变量来指示对变量值的第一次特定观察。

在下面的示例数据集中，我想要一个新变量 "firstna"，它是“1”，用于此玩家 "NA" 的第一次观察。

game_data <- data.frame(player = c(1,1,1,1,2,2,2,2), level = c(1,2,3,4,1,2,3,4), points = c(20,NA,NA,NA,20,40,NA,NA))

game_data
  player level points
1      1     1     20
2      1     2     NA
3      1     3     NA
4      1     4     NA
5      2     1     20
6      2     2     40
7      2     3     NA
8      2     4     NA

生成的数据框应如下所示：

game_data_new <- data.frame(player = c(1,1,1,1,2,2,2,2), level = c(1,2,3,4,1,2,3,4), points = c(20,NA,NA,NA,20,40,NA,NA), firstna = c(0,1,0,0,0,0,1,0))

game_data_new
  player level points firstna
1      1     1     20       0
2      1     2     NA       1
3      1     3     NA       0
4      1     4     NA       0
5      2     1     20       0
6      2     2     40       0
7      2     3     NA       1
8      2     4     NA       0

老实说，我不知道该怎么做。如果有 dplyr 选项就完美了。

Answer 1

这里是 data.table 的解决方案：

library("data.table")

game_data <- data.table(player = c(1,1,1,1,2,2,2,2), level = c(1,2,3,4,1,2,3,4), points = c(20,NA,NA,NA,20,40,NA,NA))

game_data[, firstna:=is.na(points) & !is.na(shift(points)), player][]
# > game_data[, firstna:=is.na(points) & !is.na(shift(points)), player][]
#    player level points firstna
# 1:      1     1     20   FALSE
# 2:      1     2     NA    TRUE
# 3:      1     3     NA   FALSE
# 4:      1     4     NA   FALSE
# 5:      2     1     20   FALSE
# 6:      2     2     40   FALSE
# 7:      2     3     NA    TRUE
# 8:      2     4     NA   FALSE

Answer 2

您可以通过按玩家分组然后进行变异以检查某行是否具有 NA 值而前一行没有来做到这一点

game_data %>%
  group_by(player) %>%
  mutate(firstna = ifelse(is.na(points) & lag(!is.na(points)),1,0)) %>%
  ungroup()

结果：

# A tibble: 8 x 4
# Groups:   player [2]
  player level points firstna
   <dbl> <dbl>  <dbl>   <dbl>
1      1     1     20       0
2      1     2     NA       1
3      1     3     NA       0
4      1     4     NA       0
5      2     1     20       0
6      2     2     40       0
7      2     3     NA       1
8      2     4     NA       0

Answer 3

game_data %>% 
  group_by(player) %>% 
  mutate(firstna=as.numeric(is.na(points) & !duplicated(points)))

按玩家分组，然后为既不适用又不重复的案例创建布尔向量。

# A tibble: 8 x 4
# Groups:   player [2]
  player level points firstna
   <dbl> <dbl>  <dbl>   <dbl>
1      1     1     20       0
2      1     2     NA       1
3      1     3     NA       0
4      1     4     NA       0
5      2     1     20       0
6      2     2     40       0
7      2     3     NA       1
8      2     4     NA       0

如果您想要在 NA 之前的最后一个非 NA 行上使用 1，请将 mutate 行替换为：

mutate(lastnonNA=as.numeric(!is.na(points) & is.na(lead(points))))

一直到玩家组末尾的 NA 块的第一行：

game_data %>% 
  group_by(player) %>% 
  mutate(firstna=as.numeric(is.na(points) & !duplicated(cbind(points,cumsum(!is.na(points))))))

Answer 4

library(tidyverse)
library(data.table)

data.frame(
  player = c(1,1,1,1,2,2,2,2),
  level = c(1,2,3,4,1,2,3,4),
  points = c(20,NA,NA,NA,20,40,NA,NA)
) -> game_data

game_data_base1 <- game_data
game_data_dt <- data.table(game_data)

microbenchmark::microbenchmark(

  better_base = game_data$first_na <- ave(
    game_data$points,
    game_data$player,
    FUN=function(x) seq_along(x)==match(NA,x,nomatch=0)
  ),

  brute_base = do.call(
    rbind.data.frame,
    lapply(
      split(game_data, game_data$player),
      function(x) {
        x$firstna <- 0
        na_loc <- which(is.na(x$points))
        if (length(na_loc) > 0) x$firstna[na_loc[1]] <- 1
        x
      }
    )
  ),

  tidy = game_data %>%
    group_by(player) %>%
    mutate(firstna=as.numeric(is.na(points) & !duplicated(points))) %>%
    ungroup(),

  dt = game_data_dt[, firstna:=as.integer(is.na(points) & !is.na(shift(points))), player]

)
## Unit: microseconds
##         expr     min       lq      mean    median        uq        max neval
##  better_base 125.188  156.861  362.9829  191.6385  355.6675   3095.958   100
##   brute_base 366.642  450.002 2782.6621  658.0380 1072.6475 174373.974   100
##         tidy 998.924 1119.022 2528.3687 1509.0705 2516.9350  42406.778   100
##           dt 330.428  421.211 1031.9978  535.8415 1042.1240   9671.991   100

Answer 5

基础R解法：

ave(game_data$points, game_data$player,
    FUN = function(x) seq_along(x) == match(NA, x, nomatch = 0))

Answer 6

另一个 ave 选项首先 NA 按组 (player) 查找。

game_data$firstna <- ave(game_data$points, game_data$player, 
                         FUN = function(x) cumsum(is.na(x)) == 1)

game_data
#  player level points firstna
#1      1     1     20       0
#2      1     2     NA       1
#3      1     3     NA       0
#4      1     4     NA       0
#5      2     1     20       0
#6      2     2     40       0
#7      2     3     NA       1
#8      2     4     NA       0

Answer 7

另一种使用基数的方法：

game_data$firstna <-
unlist(
tapply(game_data$points, game_data$player, function(x) {i<-which(is.na(x))[1];x[]<-0;x[i]<-1;x})
)

或作为另一个 ?ave 克隆：

ave(game_data$points, game_data$player, FUN = function(x) {
    i<-which(is.na(x))[1];x[]<-0;x[i]<-1;x
})

Answer 8

一个选项使用diff

transform(game_data, firstna = ave(is.na(points), player, FUN = function(x) c(0,diff(x))))
#   player level points firstna
# 1      1     1     20       0
# 2      1     2     NA       1
# 3      1     3     NA       0
# 4      1     4     NA       0
# 5      2     1     20       0
# 6      2     2     40       0
# 7      2     3     NA       1
# 8      2     4     NA       0

及其 dplyr 等价物：

library(dplyr)
game_data %>% group_by(player) %>% mutate(firstna = c(0,diff(is.na(points))))
# # A tibble: 8 x 4
# # Groups:   player [2]
#   player level points firstna
#    <dbl> <dbl>  <dbl>   <dbl>
# 1      1     1     20       0
# 2      1     2     NA       1
# 3      1     3     NA       0
# 4      1     4     NA       0
# 5      2     1     20       0
# 6      2     2     40       0
# 7      2     3     NA       1
# 8      2     4     NA       0

指示特定值第一次出现的新变量

New variable that indicates the first occurrence of a specific value

r

transformation

panel

hierarchical-data

dplyr