如何為每個id按多列連接表

Question

我被迫刪除了我之前的主題，因為它沒有得到很好的詢問，而且這個例子有點復雜，所以這里的內容很簡單。

我有2個數據幀：

DF1<-data.frame(id1=c(1,1,1,1,1,2),client_code=c("x1","x1","x1","x2","x2","x3"),id2=c("a","b","c","d","e","y"),value1=c(0.1,0.2,0.3,0.4,0.5,0.6),value2=c(1.1,1.2,1.3,1.4,1.5,1.6))

> DF1
  id1 client_code id2 value1 value2
1   1          x1   a    0.1    1.1
2   1          x1   b    0.2    1.2
3   1          x1   c    0.3    1.3
4   1          x2   d    0.4    1.4
5   1          x2   e    0.5    1.5
6   2          x3   y    0.6    1.6

DF2<-data.frame(id1=c(1,1,1,1,1,1,2,2),id2=c("a","b","c","d","e","f","x","y"),value1=c(10,11,12,13,14,15,16,17),value2=c(20,21,22,23,24,25,26,27))

> DF2
  id1 id2 value1 value2
1   1   a     10     20
2   1   b     11     21
3   1   c     12     22
4   1   d     13     23
5   1   e     14     24
6   1   f     15     25
7   2   x     16     26
8   2   y     17     27

每個客戶端屬於一組客戶端，由列（id1）標識

我要做的是在DF2中添加缺少的行，它們的id2在DF1中不存在。 應該對屬於DF1中的同一組客戶端（id1）的每個客戶端（client_code）執行此過程。

（我不知道自己是否足夠清楚）

所需的輸出：

output<-data.frame(id1=c(1,1,1,1,1,1,1,1,1,1,1,1,2,2),client_code=c("x1","x1","x1","x1","x1","x1","x2","x2","x2","x2","x2","x2","x3","x3"),id2=c("a","b","c","d","e","f","d","e","a","b","c","f","y","x"),                  value1=c(0.1,0.2,0.3,13,14,15,0.4,0.5,10,11,12,15,0.6,16),value2=c(1.1,1.2,1.3,23,24,25,1.4,1.5,20,21,22,25,1.6,26))

> output
   id1 client_code id2 value1 value2
1    1          x1   a    0.1    1.1
2    1          x1   b    0.2    1.2
3    1          x1   c    0.3    1.3
4    1          x1   d   13.0   23.0
5    1          x1   e   14.0   24.0
6    1          x1   f   15.0   25.0
7    1          x2   d    0.4    1.4
8    1          x2   e    0.5    1.5
9    1          x2   a   10.0   20.0
10   1          x2   b   11.0   21.0
11   1          x2   c   12.0   22.0
12   1          x2   f   15.0   25.0
13   2          x3   y    0.6    1.6
14   2          x3   x   16.0   26.0

提前致謝。

Answer 1

首先，創建一個表格，顯示每個客戶端應該存在的id2值：

library(tidyverse)

client_defaults <- df1 %>% 
  distinct(client_code, id1) %>% 
  left_join(df2, by = "id1")

client_defaults
#>    client_code id1 id2 value1 value2
#> 1           x1   1   a     10     20
#> 2           x1   1   b     11     21
#> 3           x1   1   c     12     22
#> 4           x1   1   d     13     23
#> 5           x1   1   e     14     24
#> 6           x1   1   f     15     25
#> 7           x2   1   a     10     20
#> 8           x2   1   b     11     21
#> 9           x2   1   c     12     22
#> 10          x2   1   d     13     23
#> 11          x2   1   e     14     24
#> 12          x2   1   f     15     25
#> 13          x3   2   x     16     26
#> 14          x3   2   y     17     27

然后，刪除df1中已存在的行，並添加其余行：

client_missing <- client_defaults %>% 
  anti_join(df1, by = c("client_code", "id2"))

bind_rows(df1, client_missing) %>% arrange(client_code)
#>    client_code id1 id2 value1 value2
#> 1           x1   1   a    0.1    1.1
#> 2           x1   1   b    0.2    1.2
#> 3           x1   1   c    0.3    1.3
#> 4           x1   1   d   13.0   23.0
#> 5           x1   1   e   14.0   24.0
#> 6           x1   1   f   15.0   25.0
#> 7           x2   1   d    0.4    1.4
#> 8           x2   1   e    0.5    1.5
#> 9           x2   1   a   10.0   20.0
#> 10          x2   1   b   11.0   21.0
#> 11          x2   1   c   12.0   22.0
#> 12          x2   1   f   15.0   25.0
#> 13          x3   2   y    0.6    1.6
#> 14          x3   2   x   16.0   26.0

數據：

df1 <- data.frame(client_code = c("x1", "x1", "x1", "x2", "x2", "x3"), id1 = c(1, 1, 1, 1, 1, 2), id2 = c("a", "b", "c", "d", "e", "y"), value1 = c(0.1, 0.2, 0.3, 0.4, 0.5, 0.6), value2 = c(1.1, 1.2, 1.3, 1.4, 1.5, 1.6), stringsAsFactors = FALSE)

df2 <- data.frame(id1 = c(1, 1, 1, 1, 1, 1, 2, 2), id2 = c("a", "b", "c", "d", "e", "f", "x", "y"), value1 = c(10, 11, 12, 13, 14, 15, 16, 17), value2 = c(20, 21, 22, 23, 24, 25, 26, 27), stringsAsFactors = FALSE)

^{由reprex包創建於2019-07-01（v0.2.1）}

Answer 2

這是一個可能的data.table解決方案，它更簡潔一些。 基本上它執行兩個步驟：

1. 通過在id1和client_code每個組上連接DF1和DF2來構造已完成的data.table
2. 按適當的DF1值更新value1和value2列

library(data.table)

setDT(DF1); setDT(DF2)

DF <- DF1[, DF2[.BY, .SD, on = "id1", .SDcols = id2:value2], by = .(id1, client_code)]
DF[DF1, `:=`(value1 = i.value1, value2 = i.value2), on = c("id1", "client_code", "id2")]

DF
#>     id1 client_code id2 value1 value2
#>  1:   1          x1   a    0.1    1.1
#>  2:   1          x1   b    0.2    1.2
#>  3:   1          x1   c    0.3    1.3
#>  4:   1          x1   d   13.0   23.0
#>  5:   1          x1   e   14.0   24.0
#>  6:   1          x1   f   15.0   25.0
#>  7:   1          x2   a   10.0   20.0
#>  8:   1          x2   b   11.0   21.0
#>  9:   1          x2   c   12.0   22.0
#> 10:   1          x2   d    0.4    1.4
#> 11:   1          x2   e    0.5    1.5
#> 12:   1          x2   f   15.0   25.0
#> 13:   2          x3   x   16.0   26.0
#> 14:   2          x3   y    0.6    1.6

^{由reprex包創建於2019-07-01（v0.3.0）}

Answer 3

這是使用sql查詢的解決方案。

library(sqldf)

sqldf('
select  distinct
        a.id1
        , a.client_code
        , b.id2
        , coalesce(d.value1, e.value1) as value1
        , coalesce(d.value2, e.value2) as value2
from    df1 a
        left join df2 b
          on  a.id1 = b.id1
        left join df1 d
          on  a.id1 = d.id1
              and b.id2 = d.id2
              and a.client_code = d.client_code
        left join df2 e
          on  a.id1 = e.id1
              and b.id2 = e.id2
')

#    id1 client_code id2 value1 value2
# 1    1          x1   a    0.1    1.1
# 2    1          x1   b    0.2    1.2
# 3    1          x1   c    0.3    1.3
# 4    1          x1   d   13.0   23.0
# 5    1          x1   e   14.0   24.0
# 6    1          x1   f   15.0   25.0
# 7    1          x2   a   10.0   20.0
# 8    1          x2   b   11.0   21.0
# 9    1          x2   c   12.0   22.0
# 10   1          x2   d    0.4    1.4
# 11   1          x2   e    0.5    1.5
# 12   1          x2   f   15.0   25.0
# 13   2          x3   x   16.0   26.0
# 14   2          x3   y    0.6    1.6

Answer 4

另一種選擇是檢查DF2中的每一行。

我們重新創建你的表並將一些列作為字符：

library(data.table)

DF1<-data.frame(id1=c(1,1,1,1,1,2),client_code=c("x1","x1","x1","x2","x2","x3"),id2=c("a","b","c","d","e","y"),value1=c(0.1,0.2,0.3,0.4,0.5,0.6),value2=c(1.1,1.2,1.3,1.4,1.5,1.6))
DF1$id2 <- as.character(DF1$id2)

DF2<-data.frame(id1=c(1,1,1,1,1,1,2,2),id2=c("a","b","c","d","e","f","x","y"),value1=c(10,11,12,13,14,15,16,17),value2=c(20,21,22,23,24,25,26,27))
DF2$id2 <- as.character(DF2$id2)

然后我們保存DF1的列順序（稍后將需要它）

column_order <- colnames(DF1)

現在我們將每個客戶代碼分開

client_codes <- as.character(unique(DF1$client_code))

我們定義了將包含最終結果作為數據框的New表

New_Table <- data.frame()

現在我們創建一個嵌套的for循環，以考慮不同的客戶端代碼，並檢查DF2中的每一行。

for(i in client_codes){
#So here we subset the DF1 data frame to only a certain client code  
New_DF1 <- DF1[DF1$client_code == i,]

temp_id <- unique(New_DF1$id1)
#and here we select the correct ids
New_DF2 <- DF2[DF2$id1 %in% temp_id,]

temp_df <- data.frame()
#And with this second for loop we perform a check on each of the new_DF2 rows
#to see if they have a matching client id
for(j in 1:nrow(New_DF2)){

  temp_row <- New_DF2[j,]
  if(nrow((New_DF1[New_DF1$id1 == temp_row$id1 & New_DF1$id2 == temp_row$id2,])) == 0){
    temp_row$client_code <- i
    setcolorder(temp_row, column_order)
    temp_df <- rbind(temp_df, temp_row)
  }

}

New_DF1 <- rbind(New_DF1, temp_df)

New_Table <- rbind(New_Table, New_DF1)

}