我有一个数据帧列表,其中每个数据帧都有1或2行名为“ mis”或“ syn”(形成名为cat的列)以及第二个具有数字频率的列。我想填写每个数据帧,以便如果缺少“ mis”行,则添加频率为0的mis行 如果缺少“ syn”行,则添加频率为1的syn行:
###exmaple:
#example list of dataframes:
df1<- as.data.frame(cbind(cat = c("mis", "syn"), freq= c(4, 2)))
df2<- as.data.frame(cbind(cat = "mis", freq= 1))
df3<- as.data.frame(cbind(cat = "syn", freq= 2))
df_list<- list(df1 = df1, df2 = df2, df3= df3)
看起来像:
> df_list
$df1
cat freq
1 mis 4
2 syn 2
$df2
cat freq
1 mis 1
$df3
cat freq
1 syn 2
预期输出:
> df_list
$df1
cat freq
mis 4
syn 2
$df2
cat freq
mis 1
syn 1
$df3
cat freq
syn 2
mis 0
我尝试过的方法: 首先,我更改行名称,以便可以通过它们进行搜索
df_list_named<- lapply(df_list, function(x){ row.names(x)<-as.character(x$cat); x})
df_list_named
$df1
cat freq
mis mis 4
syn syn 2
$df2
cat freq
mis mis 1
$df3
cat freq
syn syn 2
然后我一直在尝试使用ifelse循环将行追加到需要它的数据帧中,但是我无法使其工作:
test<- lapply(df_list_named, function (x) ifelse(!row.names(df_list_named[[x]]) %in% "mis", rbind(df_list_named[[x]], c(cat = "mis", freq= 0)),
ifelse(!row.names(df_list_named[[x]]) %in% "syn", rbind(df_list_named[[x]], c(cat = "syn", freq= 1))))
答案 0 :(得分:2)
这是使用lapply
lapply(df_list, function(x) {
if(all(c("mis", "syn") %in% x$cat))
x
else if("mis" %in% x$cat)
rbind(x, data.frame(cat = "syn", freq = 1))
else
rbind(x, data.frame(cat = "mis", freq = 0))
})
#$df1
# cat freq
#1 mis 4
#2 syn 2
#$df2
# cat freq
#1 mis 1
#2 syn 1
#$df3
# cat freq
#1 syn 2
#2 mis 0
数据
df1<- data.frame(cat = c("mis", "syn"), freq= c(4, 2), stringsAsFactors = FALSE)
df2<- data.frame(cat = "mis", freq= 1,stringsAsFactors = FALSE)
df3<- data.frame(cat = "syn", freq= 2, stringsAsFactors = FALSE)
df_list<- list(df1 = df1, df2 = df2, df3= df3)
答案 1 :(得分:0)
您可以使用"base"
数据帧,将merge
与列表中的所有数据帧一起使用Map
。在已经完整的数据框中创建的duplicated
行可以用!
安全地排除,因为它们总是放在最后。
(base <- data.frame(cat=factor(c("syn", "mis")), freq=factor(1:0)))
# cat freq
# 1 syn 1
# 2 mis 0
Map(function(x) {y <- (merge(x, base, all=TRUE));y[!duplicated(y$cat), ]}, df_list)
# $df1
# cat freq
# 1 mis 4
# 3 syn 2
#
# $df2
# cat freq
# 1 mis 1
# 3 syn 1
#
# $df3
# cat freq
# 1 syn 2
# 3 mis 0
df_list <- list(df1 = structure(list(cat = structure(1:2, .Label = c("mis",
"syn"), class = "factor"), freq = structure(2:1, .Label = c("2",
"4"), class = "factor")), class = "data.frame", row.names = c(NA,
-2L)), df2 = structure(list(cat = structure(c(cat = 1L), .Label = "mis", class = "factor"),
freq = structure(c(freq = 1L), .Label = "1", class = "factor")), class = "data.frame", row.names = c(NA,
-1L)), df3 = structure(list(cat = structure(c(cat = 1L), .Label = "syn", class = "factor"),
freq = structure(c(freq = 1L), .Label = "2", class = "factor")), class = "data.frame", row.names = c(NA,
-1L)))