获取 R 中每个"home team"的值

Question

有人知道如何执行以下操作吗：

我有一个数据框架(见下面的示例(，每个match_id由两支球队组成，球队的队形和动作(例如传球和铲球(。我想创建一个变量"；home_team"；，其在出现新的match_ id时捕获每个第一队队形。在该示例中，这将再次是433、4222和433。

dat <- data.frame(
match_id  = c(1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,3,3),
team_name = c("Barcelona", "Valencia", "Barcelona","Barcelona","Barcelona","Barcelona","Barcelona","Barcelona", "Getafe", "Barcelona",
"Getafe", "Getafe", "Getafe", "Barcelona", "Getafe", "Getafe", "Getafe", "Barcelona", "Barcelona", "Barcelona", "Real Madrid", "Barcelona"),
tactics.formation = c(433, 442, NA, NA, NA, NA, NA, NA, 4222, 433, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 433, 4132),
id = seq(1:22),
actions = c("STARTING XI", "STARTING XI", "pass", "pass", "pass", "pass", "dribble", "dribble", "STARTING XI", "STARTING XI", 
"pass", "pass", "pass", "pass", "dribble", "dribble", "tackle", "pass", "dribble", "pass", "STARTING XI", "STARTING XI")
)
dat
match_id   team_name tactics.formation id     actions
1         1   Barcelona               433  1 STARTING XI
2         1    Valencia               442  2 STARTING XI
3         1   Barcelona                NA  3        pass
4         1   Barcelona                NA  4        pass
5         1   Barcelona                NA  5        pass
6         1   Barcelona                NA  6        pass
7         1   Barcelona                NA  7     dribble
8         1   Barcelona                NA  8     dribble
9         2      Getafe              4222  9 STARTING XI
10        2   Barcelona               433 10 STARTING XI
11        2      Getafe                NA 11        pass
12        2      Getafe                NA 12        pass
13        2      Getafe                NA 13        pass
14        2   Barcelona                NA 14        pass
15        2      Getafe                NA 15     dribble
16        2      Getafe                NA 16     dribble
17        2      Getafe                NA 17      tackle
18        2   Barcelona                NA 18        pass
19        2   Barcelona                NA 19     dribble
20        2   Barcelona                NA 20        pass
21        3 Real Madrid               433 21 STARTING XI
22        3   Barcelona              4132 22 STARTING XI

现在我想创建一个新的专栏，对一支球队是否在进行主场比赛进行分类。当出现新的match_id时，它被认为是主场比赛。然而，我真的不知道如何迭代。

最后一个例子应该是这样的：

dat_new <- data.frame(
match_id =  c(1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,3,3),
team_name = c("Barcelona", "Valencia", "Barcelona","Barcelona","Barcelona","Barcelona","Barcelona","Barcelona", "Getafe", "Barcelona",
"Getafe", "Getafe", "Getafe", "Barcelona", "Getafe", "Getafe", "Getafe", "Barcelona", "Barcelona", "Barcelona", "Real Madrid", "Barcelona"),
tactics.formation = c(433, 442, NA, NA, NA, NA, NA, NA, 4222, 433, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 433, 4132),
id = seq(1:22),
actions = c("STARTING XI", "STARTING XI", "pass", "pass", "pass", "pass", "dribble", "dribble", "STARTING XI", "STARTING XI", 
"pass", "pass", "pass", "pass", "dribble", "dribble", "tackle", "pass", "dribble", "pass", "STARTING XI", "STARTING XI"),
home_team = c("TRUE", "FALSE", "TRUE", "TRUE", "TRUE", "TRUE", "TRUE", "TRUE", "TRUE", "FALSE", "TRUE", "TRUE", "TRUE", "FALSE", "TRUE",
"TRUE", "TRUE", "FALSE", "FALSE", "FALSE", "TRUE", "FALSE")
)
dat_new
match_id   team_name tactics.formation id     actions home_team
1         1   Barcelona               433  1 STARTING XI      TRUE
2         1    Valencia               442  2 STARTING XI     FALSE
3         1   Barcelona                NA  3        pass      TRUE
4         1   Barcelona                NA  4        pass      TRUE
5         1   Barcelona                NA  5        pass      TRUE
6         1   Barcelona                NA  6        pass      TRUE
7         1   Barcelona                NA  7     dribble      TRUE
8         1   Barcelona                NA  8     dribble      TRUE
9         2      Getafe              4222  9 STARTING XI      TRUE
10        2   Barcelona               433 10 STARTING XI     FALSE
11        2      Getafe                NA 11        pass      TRUE
12        2      Getafe                NA 12        pass      TRUE
13        2      Getafe                NA 13        pass      TRUE
14        2   Barcelona                NA 14        pass     FALSE
15        2      Getafe                NA 15     dribble      TRUE
16        2      Getafe                NA 16     dribble      TRUE
17        2      Getafe                NA 17      tackle      TRUE
18        2   Barcelona                NA 18        pass     FALSE
19        2   Barcelona                NA 19     dribble     FALSE
20        2   Barcelona                NA 20        pass     FALSE
21        3 Real Madrid               433 21 STARTING XI      TRUE
22        3   Barcelona              4132 22 STARTING XI     FALSE

有谁能帮忙吗？：(

Answer 1

您可以通过移位match_id并从match_id:中减去来获得new_match索引

new_match <- as.logical(dat$match_id - c(FALSE, head(dat$match_id, -1)))
#  [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE
# [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE

将每个new_match的home_team设置为team_name，并使用na.locf()传播丢失的值：

library(zoo)
dat$home_team <- na.locf(ifelse(new_match, dat$team_name, NA))
#    match_id   team_name tactics.formation id     actions   home_team
# 1         1   Barcelona               433  1 STARTING XI   Barcelona
# 2         1    Valencia               442  2 STARTING XI   Barcelona
# 3         1   Barcelona                NA  3        pass   Barcelona
# ...
# 19        2   Barcelona                NA 19     dribble      Getafe
# 20        2   Barcelona                NA 20        pass      Getafe
# 21        3 Real Madrid               433 21 STARTING XI Real Madrid
# 22        3   Barcelona              4132 22 STARTING XI Real Madrid

然后检查team_name是否与home_team:匹配

dat$home_team <- dat$team_name == dat$home_team
#    match_id   team_name tactics.formation id     actions home_team
# 1         1   Barcelona               433  1 STARTING XI      TRUE
# 2         1    Valencia               442  2 STARTING XI     FALSE
# 3         1   Barcelona                NA  3        pass      TRUE
# 4         1   Barcelona                NA  4        pass      TRUE
# 5         1   Barcelona                NA  5        pass      TRUE
# 6         1   Barcelona                NA  6        pass      TRUE
# 7         1   Barcelona                NA  7     dribble      TRUE
# 8         1   Barcelona                NA  8     dribble      TRUE
# 9         2      Getafe              4222  9 STARTING XI      TRUE
# 10        2   Barcelona               433 10 STARTING XI     FALSE
# 11        2      Getafe                NA 11        pass      TRUE
# 12        2      Getafe                NA 12        pass      TRUE
# 13        2      Getafe                NA 13        pass      TRUE
# 14        2   Barcelona                NA 14        pass     FALSE
# 15        2      Getafe                NA 15     dribble      TRUE
# 16        2      Getafe                NA 16     dribble      TRUE
# 17        2      Getafe                NA 17      tackle      TRUE
# 18        2   Barcelona                NA 18        pass     FALSE
# 19        2   Barcelona                NA 19     dribble     FALSE
# 20        2   Barcelona                NA 20        pass     FALSE
# 21        3 Real Madrid               433 21 STARTING XI      TRUE
# 22        3   Barcelona              4132 22 STARTING XI     FALSE