目标：
我想将t1和t2中的值从df data转换为查找表lookup中的其他值（PWT）。我已经看过一些关于如何为单个列执行此操作的教程，但我想以编程方式为无限数量的t列（例如t1，t2，t3，t4，t5，...）执行此操作来自data。
Lookup
# A tibble: 6 x 4 (HEAD)
Response `Final Fil.` Adjustment PWT
<chr> <dbl> <dbl> <dbl>
1 00000 9.00 0.500 9.50
2 00001 9.00 -0.500 8.50
3 00010 7.00 0.500 7.50
4 00011 7.00 -0.500 6.50
5 00100 7.00 0.500 7.50
6 00101 7.00 -0.500 6.50
lookup w / dput
structure(list(Response = c("00000", "00001", "00010", "00011",
"00100", "00101", "00110", "00111", "01000", "01001", "01010",
"01011", "01100", "01101", "01110", "01111", "10000", "10001",
"10010", "10011", "10100", "10101", "10110", "10111", "11000",
"11001", "11010", "11011", "11100", "11101", "11110", "1111"),
`Final Fil.` = c(9, 9, 7, 7, 7, 7, 5, 5, 7, 7, 5, 5, 5, 5,
3, 3, 7, 7, 5, 5, 5, 5, 3, 3, 5, 5, 3, 3, 3, 3, 1, 2), Adjustment = c(0.5,
-0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5,
0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5,
-0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5), PWT = c(9.5,
8.5, 7.5, 6.5, 7.5, 6.5, 5.5, 4.5, 7.5, 6.5, 5.5, 4.5, 5.5,
4.5, 3.5, 2.5, 7.5, 6.5, 5.5, 4.5, 5.5, 4.5, 3.5, 2.5, 5.5,
4.5, 3.5, 2.5, 3.5, 2.5, 1.5, 1.5)), .Names = c("Response",
"Final Fil.", "Adjustment", "PWT"), row.names = c(NA, -32L), class = c("tbl_df",
"tbl", "data.frame"))
Data
# A tibble: 6 x 4 (HEAD)
Mouse Group t1 t2
<dbl> <chr> <chr> <chr>
1 1.00 SNI 00011 00000
2 2.00 Sham 00011 00001
3 3.00 SNI 00000 00001
4 4.00 Sham 00110 00000
5 5.00 SNI 00001 00001
6 6.00 Sham 00010 00101
data w / dput
structure(list(Mouse = c(1, 2, 3, 4, 5, 6, 7, 8), Group = c("SNI",
"Sham", "SNI", "Sham", "SNI", "Sham", "SNI", "Sham"), t1 = c("00011",
"00011", "00000", "00110", "00001", "00010", "01001", "00110"
), t2 = c("00000", "00001", "00001", "00000", "00001", "00101",
"00100", "00010")), .Names = c("Mouse", "Group", "t1", "t2"), row.names = c(NA,
-8L), class = c("tbl_df", "tbl", "data.frame"))
我可以使用以下代码在t1中为data执行此操作：
indices <- (match(x = data$t1, table = lookup$Response))
response <- mutate(data, t1=lookup$PWT[indices])
新表response
Mouse Group t1 t2 t3 t4 t5 t6
<dbl> <chr> <dbl> <chr> <lgl> <lgl> <lgl> <lgl>
1 1.00 SNI 6.50 00000 NA NA NA NA
2 2.00 Sham 6.50 00001 NA NA NA NA
3 3.00 SNI 9.50 00001 NA NA NA NA
4 4.00 Sham 5.50 00000 NA NA NA NA
5 5.00 SNI 8.50 00001 NA NA NA NA
6 6.00 Sham 7.50 00101
我现在正在寻找以更多编程方式执行此操作以获得与我一样多的t列。
答案 0 :(得分：1)
我认为最简单的方法是将其重新组合为连接表而不是匹配。我得到了一个dplyr，purrr和base::merge()处理字符串的解决方案。这应该适合你！
library(dplyr)
library(purrr)
data <- structure(list(Mouse = c(1, 2, 3, 4, 5, 6, 7, 8), Group = c("SNI",
"Sham", "SNI", "Sham", "SNI", "Sham", "SNI", "Sham"), t1 = c("00011",
"00011", "00000", "00110", "00001", "00010", "01001", "00110"
), t2 = c("00000", "00001", "00001", "00000", "00001", "00101",
"00100", "00010")), .Names = c("Mouse", "Group", "t1", "t2"), row.names = c(NA,
-8L), class = c("tbl_df", "tbl", "data.frame"))
lookup <- structure(list(Response = c("00000", "00001", "00010", "00011",
"00100", "00101", "00110", "00111", "01000", "01001", "01010",
"01011", "01100", "01101", "01110", "01111", "10000", "10001",
"10010", "10011", "10100", "10101", "10110", "10111", "11000",
"11001", "11010", "11011", "11100", "11101", "11110", "1111"),
`Final Fil.` = c(9, 9, 7, 7, 7, 7, 5, 5, 7, 7, 5, 5, 5, 5,
3, 3, 7, 7, 5, 5, 5, 5, 3, 3, 5, 5, 3, 3, 3, 3, 1, 2), Adjustment = c(0.5,
-0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5,
0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5,
-0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5, 0.5, -0.5), PWT = c(9.5,
8.5, 7.5, 6.5, 7.5, 6.5, 5.5, 4.5, 7.5, 6.5, 5.5, 4.5, 5.5,
4.5, 3.5, 2.5, 7.5, 6.5, 5.5, 4.5, 5.5, 4.5, 3.5, 2.5, 5.5,
4.5, 3.5, 2.5, 3.5, 2.5, 1.5, 1.5)), .Names = c("Response",
"Final Fil.", "Adjustment", "PWT"), row.names = c(NA, -32L), class = c("tbl_df",
"tbl", "data.frame"))
not_matched <- c("Mouse", "Group")
to_match <- colnames(data)[!colnames(data) %in% not_matched]
to_match
#> [1] "t1" "t2"
lookup_subset <- lookup[c("Response", "PWT")]
lookup_subset
#> # A tibble: 32 x 2
#> Response PWT
#> <chr> <dbl>
#> 1 00000 9.5
#> 2 00001 8.5
#> 3 00010 7.5
#> 4 00011 6.5
#> 5 00100 7.5
#> 6 00101 6.5
#> 7 00110 5.5
#> 8 00111 4.5
#> 9 01000 7.5
#> 10 01001 6.5
#> # ... with 22 more rows
to_match %>%
map_dfc(function(col) {
data[col] %>%
merge(lookup_subset, by.x = col, by.y = "Response", all.x = TRUE) %>%
select(-1) %>%
set_names(col)
}) %>%
bind_cols(data[not_matched], .)
#> # A tibble: 8 x 4
#> Mouse Group t1 t2
#> <dbl> <chr> <dbl> <dbl>
#> 1 1 SNI 9.5 9.5
#> 2 2 Sham 8.5 9.5
#> 3 3 SNI 7.5 8.5
#> 4 4 Sham 6.5 8.5
#> 5 5 SNI 6.5 8.5
#> 6 6 Sham 5.5 7.5
#> 7 7 SNI 5.5 7.5
#> 8 8 Sham 6.5 6.5