按条件合并OR

Question

我需要在R中合并两个表。

表X看起来像这样：

    company_name country_code country  cost1          cost2
1      Test1         FR         <NA>     NA          9.945000e-02
2      Test1         BR        Brazil    NA               NA
3      Test2        <NA>        USA      1           1.053000e-01

表Y看起来像这样：

country country_code tier
France    FR          1
Brazil    BR          2
USA       US          1

我需要合并X和Y来获得Z：

name country_code tier
Test1    FR         1
Test2    BR         2
....

我应该怎么做以OR条件或其他东西合并？

Answer 1

以下将会这样做。请注意，我使用了包zoo中的函数，因此您需要安装它。

m <- merge(df1, df2, all = TRUE)
m$country <- zoo::na.locf(m$country)
m <- lapply(split(m, m$country), function(.m) zoo::na.locf(.m, fromLast = TRUE))
m <- lapply(m, function(.m) zoo::na.locf(.m))
m <- do.call(rbind, m)
m <- m[!duplicated(m), c(3, 2, 4)]
row.names(m) <- NULL
m
#    name country_code tier
#1  First           FR    1
#2  Third           US    1
#3 Second           BR    2

数据。

df1 <-
structure(list(name = structure(1:3, .Label = c("First", "Second", 
"Third"), class = "factor"), country = structure(c(1L, NA, 2L
), .Label = c("France", "USA"), class = "factor"), country_code = structure(c(NA, 
1L, 2L), .Label = c("BR", "US"), class = "factor")), .Names = c("name", 
"country", "country_code"), class = "data.frame", row.names = c(NA, 
-3L))

df2 <-
structure(list(country = structure(c(2L, 1L, 3L), .Label = c("Brazil", 
"France", "USA"), class = "factor"), country_code = structure(c(2L, 
1L, 3L), .Label = c("BR", "FR", "US"), class = "factor"), tier = c(1L, 
2L, 1L)), .Names = c("country", "country_code", "tier"), class = "data.frame", row.names = c(NA, 
-3L))

修改
在OP的评论和问题编辑之后，输入数据已更改，以下代码和新df1反映了此更改。

fun <- function(DF, col){
    sp <- split(DF, DF[[col]])
    m <- lapply(sp, function(.m) zoo::na.locf(.m, fromLast = TRUE))
    m <- lapply(m, function(.m) zoo::na.locf(.m))
    m <- do.call(rbind, m)
    row.names(m) <- NULL
    m
}

m <- merge(df1, df2, all = TRUE)
m$country <- zoo::na.locf(m$country)
m$country_code <- zoo::na.locf(m$country_code)
m <- fun(m, "country_code")

m <- m[!duplicated(m), ]
m
#  country_code country company_name cost1   cost2 tier
#1           BR  Brazil         Test  <NA>  0.0819    2
#2           FR  France         Test  <NA> 0.09945    1
#4           US     USA         Test  <NA>  0.1053    1

df1 <-
structure(list(company_name = structure(c(1L, 1L, 1L), .Label = "Test", class = "factor"), 
    country_code = structure(c(2L, 1L, NA), .Label = c("BR", 
    "FR"), class = "factor"), country = structure(c(NA, 1L, 2L
    ), .Label = c("Brazil", "USA"), class = "factor"), cost1 = c(NA, 
    NA, NA), cost2 = c(0.09945, 0.0819, 0.1053)), .Names = c("company_name", 
"country_code", "country", "cost1", "cost2"), class = "data.frame", row.names = c("1", 
"2", "3"))