我有以下输入数据：
Type Start End Value
Normal 14:10:01 14:20:00 0.05454545
Normal 14:50:01 15:00:00 0.05
Normal 15:00:01 15:10:00 0.056
Normal 15:10:01 15:20:00 0.05121951
Normal 15:20:01 15:30:00 0.05
Spl1 13:20:01 13:30:00 0.05089286
Spl1 13:40:01 13:50:00 0.05
Spl1 13:50:01 14:00:00 0.04848485
Spl2 14:30:01 14:40:00 0.05208333
Spl2 14:50:01 15:00:00 0.05
Spl2 15:20:01 15:30:00 0.05
输入表的数据结构：
$ Type : chr
$ Start : chr
$ End : chr
$ Value : num
输出表结构如下：
Start End Normal Spl1 Spl2
13:00:01 13:10:00
13:10:01 13:20:00
13:20:01 13:30:00
13:30:01 13:40:00
13:40:01 13:50:00
13:50:01 14:00:00
14:00:01 14:10:00
14:10:01 14:20:00
14:20:01 14:30:00
14:30:01 14:40:00
14:40:01 14:50:00
14:50:01 15:00:00
15:00:01 15:10:00
15:10:01 15:20:00
15:20:01 15:30:00
我希望根据以下标准填充数据：
(Input_table$Start == Output_table$Start) && (Input_table$End == Output_table$End) "Normal" type rows应将值填充到Output table's Normal Column。同样，"Up" and "Down" type rows应该是Up and Down columns in output table 0 所需的输出表应如下所示：
Start End Normal Spl1 Spl2
13:00:01 13:10:00 0 0 0
13:10:01 13:20:00 0 0 0
13:20:01 13:30:00 0 0.05089286 0
13:30:01 13:40:00 0 0 0
13:40:01 13:50:00 0 0.05 0
13:50:01 14:00:00 0 0.04848485 0
14:00:01 14:10:00 0 0 0
14:10:01 14:20:00 0.05454545 0 0
14:20:01 14:30:00 0 0 0
14:30:01 14:40:00 0 0 0.05208333
14:40:01 14:50:00 0 0 0
14:50:01 15:00:00 0.05 0 0.05
15:00:01 15:10:00 0.056 0 0
15:10:01 15:20:00 0.05121951 0 0
15:20:01 15:30:00 0.05 0 0.05
请建议可能的解决方案。在R。
注意：我不想为此解决方案使用循环。我正在寻找直接的方法。请建议是否有。
答案 0 :(得分：1)
我们可以left_join然后spread输出到＆＃39;范围
library(dplyr)
library(tidyr)
left_join(df2, df1) %>%
spread(Type, Value) %>%
select(1:5) %>%
mutate_at(vars(Normal, Spl1, Spl2), funs(replace(., is.na(.), 0)))
# Start End Normal Spl1 Spl2
#1 13:00:01 13:10:00 0.00000000 0.00000000 0.00000000
#2 13:10:01 13:20:00 0.00000000 0.00000000 0.00000000
#3 13:20:01 13:30:00 0.00000000 0.05089286 0.00000000
#4 13:30:01 13:40:00 0.00000000 0.00000000 0.00000000
#5 13:40:01 13:50:00 0.00000000 0.05000000 0.00000000
#6 13:50:01 14:00:00 0.00000000 0.04848485 0.00000000
#7 14:00:01 14:10:00 0.00000000 0.00000000 0.00000000
#8 14:10:01 14:20:00 0.05454545 0.00000000 0.00000000
#9 14:20:01 14:30:00 0.00000000 0.00000000 0.00000000
#10 14:30:01 14:40:00 0.00000000 0.00000000 0.05208333
#11 14:40:01 14:50:00 0.00000000 0.00000000 0.00000000
#12 14:50:01 15:00:00 0.05000000 0.00000000 0.05000000
#13 15:00:01 15:10:00 0.05600000 0.00000000 0.00000000
#14 15:10:01 15:20:00 0.05121951 0.00000000 0.00000000
#15 15:20:01 15:30:00 0.05000000 0.00000000 0.05000000
df1 <- structure(list(Type = c("Normal", "Normal", "Normal", "Normal",
"Normal", "Spl1", "Spl1", "Spl1", "Spl2", "Spl2", "Spl2"), Start = c("14:10:01",
"14:50:01", "15:00:01", "15:10:01", "15:20:01", "13:20:01", "13:40:01",
"13:50:01", "14:30:01", "14:50:01", "15:20:01"), End = c("14:20:00",
"15:00:00", "15:10:00", "15:20:00", "15:30:00", "13:30:00", "13:50:00",
"14:00:00", "14:40:00", "15:00:00", "15:30:00"), Value = c(0.05454545,
0.05, 0.056, 0.05121951, 0.05, 0.05089286, 0.05, 0.04848485,
0.05208333, 0.05, 0.05)), .Names = c("Type", "Start", "End",
"Value"), class = "data.frame", row.names = c(NA, -11L))
df2 <- structure(list(Start = c("13:00:01", "13:10:01", "13:20:01",
"13:30:01", "13:40:01", "13:50:01", "14:00:01", "14:10:01", "14:20:01",
"14:30:01", "14:40:01", "14:50:01", "15:00:01", "15:10:01", "15:20:01"
), End = c("13:10:00", "13:20:00", "13:30:00", "13:40:00", "13:50:00",
"14:00:00", "14:10:00", "14:20:00", "14:30:00", "14:40:00", "14:50:00",
"15:00:00", "15:10:00", "15:20:00", "15:30:00")), .Names = c("Start",
"End"), class = "data.frame", row.names = c(NA, -15L))
答案 1 :(得分：1)
这可以在data.table
dcast(dt1[dt2, on = c("Start", "End")], ... ~ Type, fill = 0)[, `NA` := NULL][]
将返回
Start End Normal Spl1 Spl2
1: 13:00:01 13:10:00 0.00000000 0.00000000 0.00000000
2: 13:10:01 13:20:00 0.00000000 0.00000000 0.00000000
3: 13:20:01 13:30:00 0.00000000 0.05089286 0.00000000
4: 13:30:01 13:40:00 0.00000000 0.00000000 0.00000000
5: 13:40:01 13:50:00 0.00000000 0.05000000 0.00000000
6: 13:50:01 14:00:00 0.00000000 0.04848485 0.00000000
7: 14:00:01 14:10:00 0.00000000 0.00000000 0.00000000
8: 14:10:01 14:20:00 0.05454545 0.00000000 0.00000000
9: 14:20:01 14:30:00 0.00000000 0.00000000 0.00000000
10: 14:30:01 14:40:00 0.00000000 0.00000000 0.05208333
11: 14:40:01 14:50:00 0.00000000 0.00000000 0.00000000
12: 14:50:01 15:00:00 0.05000000 0.00000000 0.05000000
13: 15:00:01 15:10:00 0.05600000 0.00000000 0.00000000
14: 15:10:01 15:20:00 0.05121951 0.00000000 0.00000000
15: 15:20:01 15:30:00 0.05000000 0.00000000 0.05000000
library(data.table)
dt1 <- fread(
"Type Start End Value
Normal 14:10:01 14:20:00 0.05454545
Normal 14:50:01 15:00:00 0.05
Normal 15:00:01 15:10:00 0.056
Normal 15:10:01 15:20:00 0.05121951
Normal 15:20:01 15:30:00 0.05
Spl1 13:20:01 13:30:00 0.05089286
Spl1 13:40:01 13:50:00 0.05
Spl1 13:50:01 14:00:00 0.04848485
Spl2 14:30:01 14:40:00 0.05208333
Spl2 14:50:01 15:00:00 0.05
Spl2 15:20:01 15:30:00 0.05"
)
dt2 <- fread(
"Start End
13:00:01 13:10:00
13:10:01 13:20:00
13:20:01 13:30:00
13:30:01 13:40:00
13:40:01 13:50:00
13:50:01 14:00:00
14:00:01 14:10:00
14:10:01 14:20:00
14:20:01 14:30:00
14:30:01 14:40:00
14:40:01 14:50:00
14:50:01 15:00:00
15:00:01 15:10:00
15:10:01 15:20:00
15:20:01 15:30:00 "
)