帧:
df 1:包含多个具有500列值的相同id的行
id|val.1|val.2|...|val.500
---------------------------------
1 | 240 | 234 |...|228
1 | 224 | 222 |...|230
1 | 238 | 240 |...|240
2 | 277 | 270 |...|255
2 | 291 | 290 |...|265
2 | 284 | 282 |...|285
df 2:只包含一个与df-1 id列匹配的唯一ID(行)和500列值
id|val.1|val.2|...|val.500
---------------------------------
1 | 250 | 240 |...|245
2 | 280 | 282 |...|281
我想根据dd将df 1列值除以df 2中的相应列值,最后得到df 3:
id|val.1|val.2|...|val.500
---------------------------------
1 | 0.96| 0.98|...|0.93
1 | 0.90| 0.93|...|0.94
1 | 0.95| 1.00|...|0.98
2 | 0.99| 0.96|...|0.91
2 | 1.04| 1.03|...|0.94
2 | 1.01| 1.00|...|1.01
基本上根据ID和列值将df 1值加权df 2。我现在已经摸不着头脑了解最好的方法,并没有取得多大进展。任何指导将不胜感激。感谢
答案 0 :(得分:3)
两种可能的方法:
1:'广泛'方法
使用dplyr
和purrr
个包:
library(dplyr)
library(purrr)
df12 <- left_join(df1, df2, by = 'id')
cbind(id=df12[,1], map2_df(df12[,2:4], df12[,5:7], `/`))
使用data.table
包(从here借来的方法):
library(data.table)
# convert to 'data.tables'
setDT(df1)
setDT(df2)
# creates two vectors of matching columnnames
xcols = names(df1)[-1]
icols = paste0("i.", xcols)
# join and do the calculation
df1[df2, on = 'id', Map('/', mget(xcols), mget(icols)), by = .EACHI]
两者都给出了:
id val.1 val.2 val.3
1: 1 0.9600000 0.9750000 0.9306122
2: 1 0.8960000 0.9250000 0.9387755
3: 1 0.9520000 1.0000000 0.9795918
4: 2 0.9892857 0.9574468 0.9074733
5: 2 1.0392857 1.0283688 0.9430605
6: 2 1.0142857 1.0000000 1.0142349
2:'长'接近
另一种选择是将数据帧重新整形为长格式,然后merge
/ join
,并进行计算。
使用data.table
- 包:
library(data.table)
dt1 <- melt(setDT(df1), id = 1)
dt2 <- melt(setDT(df2), id = 1)
dt1[dt2, on = c('id','variable'), value := value/i.value][]
使用dplyr
和tidyr
个包:
library(dplyr)
library(tidyr)
df1 %>%
gather(variable, value, -id) %>%
left_join(., df2 %>% gather(variable, value, -id), by = c('id','variable')) %>%
mutate(value = value.x/value.y) %>%
select(id, variable, value)
两者都给出了:
id variable value
1: 1 val.1 0.9600000
2: 1 val.1 0.8960000
3: 1 val.1 0.9520000
4: 2 val.1 0.9892857
5: 2 val.1 1.0392857
6: 2 val.1 1.0142857
7: 1 val.2 0.9750000
8: 1 val.2 0.9250000
9: 1 val.2 1.0000000
10: 2 val.2 0.9574468
11: 2 val.2 1.0283688
12: 2 val.2 1.0000000
13: 1 val.3 0.9306122
14: 1 val.3 0.9387755
15: 1 val.3 0.9795918
16: 2 val.3 0.9074733
17: 2 val.3 0.9430605
18: 2 val.3 1.0142349
使用过的数据:
df1 <- structure(list(id = c(1, 1, 1, 2, 2, 2), val.1 = c(240, 224, 238, 277, 291, 284),
val.2 = c(234, 222, 240, 270, 290, 282), val.3 = c(228, 230, 240, 255, 265, 285)),
.Names = c("id", "val.1", "val.2", "val.3"), class = "data.frame", row.names = c(NA, -6L))
df2 <- structure(list(id = c(1, 2), val.1 = c(250, 280), val.2 = c(240, 282), val.3 = c(245, 281)),
.Names = c("id", "val.1", "val.2", "val.3"), class = "data.frame", row.names = c(NA, -2L))
答案 1 :(得分:0)
只要data.frames按列正确排序并且两者具有相同的列,我认为以下基本R代码将完成您想要的任务。
cbind(df1[1], df1[-1] / df2[match(df1$id, df2$id), -1])
id val.1 val.2 val.500
1 1 0.9600000 0.9750000 0.9306122
2 1 0.8960000 0.9250000 0.9387755
3 1 0.9520000 1.0000000 0.9795918
4 2 0.9892857 0.9574468 0.9074733
5 2 1.0392857 1.0283688 0.9430605
6 2 1.0142857 1.0000000 1.0142349
这里,match(df1$id, df2$id)
将返回与df2的id相对应的df1的行索引,因此df2[match(df1$id, df2$id), -1]
将返回相应的df2行作为data.frame并删除了id变量。然后,当删除id变量并且df1[-1] / df2[match(df1$id, df2$id), -1]
执行除法时,此data.frame将匹配形状中的df1。最后cbind
将id变量添加到最终的data.frame。
数据强>
df1 <- structure(list(id = c(1L, 1L, 1L, 2L, 2L, 2L), val.1 = c(240L,
224L, 238L, 277L, 291L, 284L), val.2 = c(234L, 222L, 240L, 270L,
290L, 282L), val.500 = c(228L, 230L, 240L, 255L, 265L, 285L)), .Names = c("id",
"val.1", "val.2", "val.500"), class = "data.frame", row.names = c(NA,
-6L))
df2 <- structure(list(id = 1:2, val.1 = c(250L, 280L), val.2 = c(240L,
282L), val.500 = c(245L, 281L)), .Names = c("id", "val.1", "val.2",
"val.500"), class = "data.frame", row.names = c(NA, -2L))