我有以下提到的数据框：
ID Date Status Category
TR-1 2018-01-10 Passed A
TR-2 2018-01-09 Passed B
TR-3 2018-01-09 Failed C
TR-3 2018-01-09 Failed A
TR-4 2018-01-08 Failed B
TR-5 2018-01-08 Passed C
TR-5 2018-01-08 Failed A
TR-6 2018-01-07 Passed A
通过利用以上给定的数据帧，我想要一种如下所示的输出格式：
Date应该按降序排列，类别顺序应该类似于C，A和B。
Date count distinct_count Passed Failed
2018-01-10 1 1 1 0
A 1 1 1 0
B 0 0 0 0
C 0 0 0 0
2018-01-09 3 2 1 2
A 1 1 1 0
B 1 1 1 0
C 1 1 1 0
要获得上面的输出，我尝试了下面的代码，但是它不起作用并且无法获得预期的输出。
Output<-DF %>%
group_by(Date=Date,A,B,C) %>%
summarise(`Count` = n(),
`Distinct_count` = n_distinct(ID),
Passed=sum(Status=='Passed'),
A=count(category='A'),
B=count(category='B'),
C=count(category='C'),
Failed=sum(Status=='Failed'))
投放：
structure(list(ID = structure(c(1L, 2L, 3L, 3L, 4L, 5L, 5L, 6L
), .Label = c("TR-1", "TR-2", "TR-3", "TR-4", "TR-5", "TR-6"), class = "factor"),
Date = structure(c(4L, 3L, 3L, 3L, 2L, 2L, 2L, 1L), .Label = c("07/01/2018",
"08/01/2018", "09/01/2018", "10/01/2018"), class = "factor"),
Status = structure(c(2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L), .Label = c("Failed",
"Passed"), class = "factor"), Category = structure(c(1L,
2L, 3L, 1L, 2L, 3L, 1L, 1L), .Label = c("A", "B", "C"), class = "factor")), .Names = c("ID",
"Date", "Status", "Category"), class = "data.frame", row.names = c(NA,
-8L))
答案 0 :(得分：6)
那是一个艰难的过程：
# I'm converting some variables to factors to get the "order" right and to fill in missing unobserved values later in dcast.
df1$Category <- factor(df1$Category, levels = unique(df1$Category))
date_lvls <- as.Date(df1$Date, "%Y-%m-%d") %>% unique %>% sort(decreasing = TRUE) %>% as.character
df1$Date <- factor(df1$Date, date_lvls)
# lets use data.table
library(data.table)
setDT(df1)
# make a lookup table to deal with the duplicated ID issue. Not sure how to do this elegant
tmp <- dcast.data.table(df1, Date ~ ID, fun.aggregate = length)
tmp <- structure(rowSums(tmp[,-1] == 2), .Names = as.character(unlist(tmp[, 1])))
# precaution! Boilerplate incoming in 3, 2, .. 1
dcast.data.table(df1, Date + Category ~ Status, drop = FALSE)[
,`:=`(Failed=+!is.na(Failed), Passed=+!is.na(Passed))][
, c("count","distinct_count") := rowSums(cbind(Failed,Passed))][
, Category := as.character(Category)][
, rbind(
cbind(Category = as.character(Date[1]), count = sum(count), distinct_count = sum(distinct_count) - tmp[as.character(Date[1])], Passed = sum(Passed), Failed = sum(Failed)),
.SD
, fill = TRUE), by = Date][
, Date := NULL ][]
结果：
# Category count distinct_count Passed Failed
#1: 2018-01-10 1 1 1 0
#2: A 1 1 1 0
#3: B 0 0 0 0
#4: C 0 0 0 0
#5: 2018-01-09 3 2 1 2
#6: A 1 1 0 1
#7: B 1 1 1 0
#8: C 1 1 0 1
#9: 2018-01-08 3 2 1 2
#10: A 1 1 0 1
#11: B 1 1 0 1
#12: C 1 1 1 0
#13: 2018-01-07 1 1 1 0
#14: A 1 1 1 0
#15: B 0 0 0 0
#16: C 0 0 0 0
数据：
df1<-
structure(list(ID = c("TR-1", "TR-2", "TR-3", "TR-3", "TR-4",
"TR-5", "TR-5", "TR-6"), Date = c("2018-01-10", "2018-01-09",
"2018-01-09", "2018-01-09", "2018-01-08", "2018-01-08", "2018-01-08",
"2018-01-07"), Status = c("Passed", "Passed", "Failed", "Failed",
"Failed", "Passed", "Failed", "Passed"), Category = c("A", "B",
"C", "A", "B", "C", "A", "A")), row.names = c(NA, -8L), class = "data.frame")
请注意：
请逐行运行每一行代码。为此，您可以关闭每个 ENDING 右括号，然后将代码行放到最后：例如
运行：dcast.data.table(df1, Date + Category ~ Status, drop = FALSE)[]
运行：dcast.data.table(df1, Date + Category ~ Status, drop = FALSE)[
,：= (Failed=+!is.na(Failed), Passed=+!is.na(Passed))][]
...直到最后
如果还有什么不清楚的地方，请问我有关这件事的详细信息。
答案 1 :(得分：4)
我确定必须有一个更优雅的解决方案，但是使用tidyverse可以做到：
bind_rows(df %>%
arrange(Date) %>%
group_by(Date, Category) %>%
summarise(count = n(),
distinct_count = n_distinct(ID),
passed = length(Status[Status == "Passed"]),
failed = length(Status[Status == "Failed"])) %>%
complete(Category) %>%
mutate_all(funs(coalesce(., 0L))) %>%
ungroup() %>%
mutate(Date = Category,
date_id = gl(nrow(.)/3, 3)) %>%
select(-Category), df %>%
arrange(Date) %>%
group_by(Date) %>%
summarise(count = n(),
distinct_count = n_distinct(ID),
passed = length(Status[Status == "Passed"]),
failed = length(Status[Status == "Failed"])) %>%
mutate(date_id = gl(nrow(.), 1))) %>%
arrange(date_id, Date)
Date count distinct_count passed failed date_id
<chr> <int> <int> <int> <int> <fct>
1 07/01/2018 1 1 1 0 1
2 A 1 1 1 0 1
3 B 0 0 0 0 1
4 C 0 0 0 0 1
5 08/01/2018 3 2 1 2 2
6 A 1 1 0 1 2
7 B 1 1 0 1 2
8 C 1 1 1 0 2
9 09/01/2018 3 2 1 2 3
10 A 1 1 0 1 3
11 B 1 1 1 0 3
12 C 1 1 0 1 3
13 10/01/2018 1 1 1 0 4
14 A 1 1 1 0 4
15 B 0 0 0 0 4
16 C 0 0 0 0 4
首先，它基于“日期”和“类别”创建一个带有计数，distinct_count，已通过和失败列的df。其次，通过使用complete()生成“类别”中的所有级别，然后coalesce()用0填充不存在的级别。第三，它使用计数，distinct_count，传递的和创建第二个df。仅基于“日期”的失败列。最后，它按行组合了两个df。
样本数据：
df <- read.table(text = "ID Date Status Category
TR-1 2018-01-10 Passed A
TR-2 2018-01-09 Passed B
TR-3 2018-01-09 Failed C
TR-3 2018-01-09 Failed A
TR-4 2018-01-08 Failed B
TR-5 2018-01-08 Passed C
TR-5 2018-01-08 Failed A
TR-6 2018-01-07 Passed A", header = TRUE)
答案 2 :(得分：4)
在同一列中混合/data/data/package name/files/file name (ex config.txt)
和$Date之类的变量是一个坏主意，因为正如@Luminata指出的那样，这使得进一步处理数据非常困难。
虽然目前尚不清楚要实现什么目标，因此任何答案都必须是暂定的，但这是一个可能使您更接近目标的解决方案：
如果这是您的数据：
$Category您想要的是用df <- data.frame(
ID = c("TR-1","TR-2", "TR-3", "TR-3", "TR-4", "TR-5", "TR-5", "TR-6"),
Date = c("2018-01-10", "2018-01-09", "2018-01-09", "2018-01-09", "2018-01-08", "2018-01-08", "2018-01-08", "2018-01-07"),
Status = c("Passed","Passed","Failed","Failed","Failed","Passed","Failed", "Passed"),
Category = c("A","B","C","A","B","C","A","A")
)
分离出数据，然后为什么不使用$Date和by函数为每个日期创建一个可分离的数据帧列表：
unique答案 3 :(得分：2)
您可以在要使用的两列的不同级别上混合使用lapply，并与do.call("rbind",x)混合使用，以将其作为数组返回。
类似这样的东西：
res=do.call("rbind",lapply(levels(DF$Date),function(d)do.call("rbind",lapply(levels(DF$Category),function(c)
{
tbl=table(DF$Status[DF$Category == c & DF$Date == d])
cbind(Date=d,Category=c,count=sum(tbl),distinct_count=sum(tbl>0),t(tbl))
}))))
res=as.data.frame(res)
我向数据集添加了几行，因此输入框应为：
DF <- read.table(text =
"fD Date Status Category
TR-1 2018-01-10 Passed A
TR-2 2018-01-09 Passed B
TR-3 2018-01-09 Failed C
TR-4 2018-01-09 Failed A
TR-5 2018-01-08 Failed B
TR-6 2018-01-08 Passed C
TR-7 2018-01-08 Failed A
TR-8 2018-01-08 Passed B
TR-9 2018-01-08 Failed A
TR-10 2018-01-08 Failed A
TR-11 2018-01-07 Passed A"
, header = TRUE)
第一行代码将输出：
> res
Date Category count distinct_count Failed Passed
1 2018-01-07 A 1 1 0 1
2 2018-01-07 B 0 0 0 0
3 2018-01-07 C 0 0 0 0
4 2018-01-08 A 3 1 3 0
5 2018-01-08 B 2 2 1 1
6 2018-01-08 C 1 1 0 1
7 2018-01-09 A 1 1 1 0
8 2018-01-09 B 1 1 0 1
9 2018-01-09 C 1 1 1 0
10 2018-01-10 A 1 1 0 1
11 2018-01-10 B 0 0 0 0
12 2018-01-10 C 0 0 0 0
编辑：我想我终于猜到了您所说的“非重复计数”是什么意思，所以我更新了答案。
答案 4 :(得分：0)
正如其他人指出的那样，将变量混合在一列中可能不是最好的主意，但是我已经做到了，只需将随后的行合并即可。
library(tidyr)
library(dplyr)
Output <- DF %>%
group_by(Date, Category) %>%
summarise('Count'=n(),
'Distinct_Count'=n_distinct(ID),
Passed=sum(Status=='Passed'),
Failed=sum(Status=='Failed')) %>%
ungroup() %>%
complete(Date, Category, fill=list(Count=0, Distinct_Count=0, Passed=0, Failed=0))
perDay <- Output %>%
group_by(Date) %>%
summarise('Count'=sum(Count),
'Distinct_Count'=sum(Distinct_Count),
Passed=sum(Passed),
Failed=sum(Failed)) %>%
arrange(desc(Date))
Output$indate <- Output$Date
Output$Date <- Output$Category
Combined <- bind_rows(lapply(perDay$Date, function(date) {
rbind(perDay[perDay$Date==date,], Output[Output$indate==date,c(1,3:6)])
}))
每个类别的data.frames每天和Output计数值（必要时完成它们），每天以后绑定在一起。