我想使用map_dfr和group_split通过while循环运行data.frame组并存储结果。
我可以像这样一个小组这样做。
# df dput below
# this code finds the closet match for DIFF for Sample.x in Sample.y, then finds the next closest match, until
df_f <- df %>% filter(grp == "AB" & VAR == "Var1")
HowMany <- length(unique(df_f$Sample.y))
i <- 1
MyList <- list()
while (i <= HowMany){
res1 <- df_f %>%
group_by(grp, VAR, Sample.x) %>%
filter(DIFF == min(DIFF)) %>%
ungroup() %>%
mutate(Rank1 = dense_rank(DIFF))
res2 <- res1 %>% group_by(grp, VAR) %>% filter(rank(Rank1, ties.method="first")==1)
SY <- as.numeric(res2$Sample.y)
SX <- as.numeric(res2$Sample.x)
res3 <- df_f %>% filter(Sample.y != SY)
res4 <- res3 %>% filter(Sample.x != SX)
df_f <- res4
MyList[[i]] <- res2
i <- i + 1
}
df.result <- do.call("rbind", MyList)
但是，当尝试使用while循环使函数与map_dfr和group_split一起使用时，我不确定和/或不确定如何存储输出。
MyResult <- df %>%
dplyr::group_split(grp, VAR) %>%
map_dfr(fun) # fun below
df.store <- data.frame() # attempt to store results
fun <- function(df){
HowMany <- length(unique(df$Sample.y))
i <- 1
MyList_FF <- list()
ThisDF <- df
while (i <= HowMany){
res1 <- ThisDF %>%
group_by(grp, VAR, Sample.x) %>%
filter(DIFF == min(DIFF)) %>%
ungroup() %>%
mutate(Rank1 = dense_rank(DIFF))
res2 <- res1 %>% group_by(grp, VAR) %>% filter(rank(Rank1, ties.method="first")==1)
# print(res2) # when printed to screen the desired output looks correct
SY <- as.numeric(res2$Sample.y)
SX <- as.numeric(res2$Sample.x)
res3 <- ThisDF %>% filter(Sample.y != SY)
res4 <- res3 %>% filter(Sample.x != SX)
# df.store <- rbind(df.store, res4)
# MyList_FF[[i]] <- res2
ThisDF <- res4
i <- i + 1
}
}
我尝试rbind或使用list来存储输出，但是我的尝试不正确。如果在屏幕上打印“ res2”，则一次可以看到所需的输出。如何存储fun中每个group_split的输出？
# df dput
df <- structure(list(Location.x = 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, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L), .Label = c("A", "C", "B"), class = "factor"),
Sample.x = c(6L, 6L, 10L, 10L, 9L, 9L, 6L, 6L, 10L, 10L,
9L, 9L, 6L, 6L, 6L, 10L, 10L, 10L, 9L, 9L, 9L, 6L, 6L, 6L,
10L, 10L, 10L, 9L, 9L, 9L, 1L, 1L, 1L, 9L, 9L, 9L, 1L, 1L,
1L, 9L, 9L, 9L), VAR = c("Var1", "Var1", "Var1", "Var1",
"Var1", "Var1", "Var2", "Var2", "Var2", "Var2", "Var2", "Var2",
"Var1", "Var1", "Var1", "Var1", "Var1", "Var1", "Var1", "Var1",
"Var1", "Var2", "Var2", "Var2", "Var2", "Var2", "Var2", "Var2",
"Var2", "Var2", "Var1", "Var1", "Var1", "Var1", "Var1", "Var1",
"Var2", "Var2", "Var2", "Var2", "Var2", "Var2"), value.x = c(56.48,
56.48, 57.03, 57.03, 55.04, 55.04, 6, 6, 10, 10, 9, 9, 56.48,
56.48, 56.48, 57.03, 57.03, 57.03, 55.04, 55.04, 55.04, 6,
6, 6, 10, 10, 10, 9, 9, 9, 55.62, 55.62, 55.62, 55.65, 55.65,
55.65, 1, 1, 1, 9, 9, 9), Location.y = structure(c(2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("A",
"C", "B"), class = "factor"), Sample.y = c(1L, 9L, 1L, 9L,
1L, 9L, 1L, 9L, 1L, 9L, 1L, 9L, 3L, 7L, 9L, 3L, 7L, 9L, 3L,
7L, 9L, 3L, 7L, 9L, 3L, 7L, 9L, 3L, 7L, 9L, 3L, 7L, 9L, 3L,
7L, 9L, 3L, 7L, 9L, 3L, 7L, 9L), value.y = c(55.62, 55.65,
55.62, 55.65, 55.62, 55.65, 1, 9, 1, 9, 1, 9, 1.4, 111.6,
111.8, 1.4, 111.6, 111.8, 1.4, 111.6, 111.8, 10.2, 14.4,
20.9, 10.2, 14.4, 20.9, 10.2, 14.4, 20.9, 1.4, 111.6, 111.8,
1.4, 111.6, 111.8, 10.2, 14.4, 20.9, 10.2, 14.4, 20.9), DIFF = c(0.859999999999999,
0.829999999999998, 1.41, 1.38, 0.579999999999998, 0.609999999999999,
5, 3, 9, 1, 8, 0, 55.08, 55.12, 55.32, 55.63, 54.57, 54.77,
53.64, 56.56, 56.76, 4.2, 8.4, 14.9, 0.199999999999999, 4.4,
10.9, 1.2, 5.4, 11.9, 54.22, 55.98, 56.18, 54.25, 55.95,
56.15, 9.2, 13.4, 19.9, 1.2, 5.4, 11.9), grp = c("AC", "AC",
"AC", "AC", "AC", "AC", "AC", "AC", "AC", "AC", "AC", "AC",
"AB", "AB", "AB", "AB", "AB", "AB", "AB", "AB", "AB", "AB",
"AB", "AB", "AB", "AB", "AB", "AB", "AB", "AB", "CB", "CB",
"CB", "CB", "CB", "CB", "CB", "CB", "CB", "CB", "CB", "CB"
)), row.names = c(NA, -42L), class = "data.frame")
答案 0 :(得分：1)
唯一缺少的部分是您的映射函数fun没有返回值。它是 计算并建立临时列表，MyList_FF正确，您可以通过print()调用看到，但是没有返回，它就消失了。
fun <- function(df) {
HowMany <- length(unique(df$Sample.y))
i <- 1
MyList_FF <- list()
df_f <- df
while (i <= HowMany){
res1 <- df_f %>%
group_by(grp, VAR, Sample.x) %>%
filter(DIFF == min(DIFF)) %>%
ungroup() %>%
mutate(Rank1 = dense_rank(DIFF))
res2 <- res1 %>% group_by(grp, VAR) %>% filter(rank(Rank1, ties.method="first")==1)
SY <- as.numeric(res2$Sample.y)
SX <- as.numeric(res2$Sample.x)
res3 <- df_f %>% filter(Sample.y != SY)
res4 <- res3 %>% filter(Sample.x != SX)
df_f <- res4
MyList_FF[[i]] <- res2
i <- i + 1
}
# this is the magic line
do.call("rbind", MyList_FF)
# this returns the list built inside of the function
}
最后一行是魔术，类似于您在单个示例之后所做的，将中间结果列表绑定在一起。在R中，return()函数仅在尝试尽早返回时才需要，因为默认情况下R函数将返回最后一个值。因此，在这里我们不需要明确地说出return(do.call("rbind", MyList_FF))，尽管这样做对您没有任何伤害。在不工作的示例中，自分配i以来没有最后一个值，因此您没有找回任何对象，但是也没有收到任何错误。
有关完整的工作示例：
MyResult <- df %>%
dplyr::group_split(grp, VAR) %>%
map_df(fun)
MyResult
# A tibble: 16 x 10
# Groups: grp, VAR [1]
Location.x Sample.x VAR value.x Location.y Sample.y value.y DIFF grp Rank1
<fct> <int> <chr> <dbl> <fct> <int> <dbl> <dbl> <chr> <int>
1 A 9 Var1 55.0 B 3 1.4 53.6 AB 1
2 A 10 Var1 57.0 B 7 112. 54.6 AB 1
3 A 6 Var1 56.5 B 9 112. 55.3 AB 1
4 A 9 Var1 55.0 B 3 1.4 53.6 AB 1
5 A 10 Var1 57.0 B 7 112. 54.6 AB 1
6 A 6 Var1 56.5 B 9 112. 55.3 AB 1
7 A 9 Var1 55.0 B 3 1.4 53.6 AB 1
8 A 10 Var1 57.0 B 7 112. 54.6 AB 1
9 A 9 Var1 55.0 B 3 1.4 53.6 AB 1
10 A 10 Var1 57.0 B 7 112. 54.6 AB 1
11 A 9 Var1 55.0 B 3 1.4 53.6 AB 1
12 A 10 Var1 57.0 B 7 112. 54.6 AB 1
13 A 6 Var1 56.5 B 9 112. 55.3 AB 1
14 A 9 Var1 55.0 B 3 1.4 53.6 AB 1
15 A 10 Var1 57.0 B 7 112. 54.6 AB 1
16 A 6 Var1 56.5 B 9 112. 55.3 AB 1
如果经常使用do.call("xbind", list)，则可能会喜欢dplyr::bind_rows(list)和dplyr::bind_cols(list)。