Question

我是data.table的初学者，并在周围搜索连接，然后改变列。我发现data.table join then add columns to existing data.frame without re-copy线程，但我无法继续进行。

请注意，我能够使用dplyr执行我想要的操作，但由于尺寸的原因，在实际数据上运行此代码是不可行的。另外，由于上述原因，我无法创建中间表。

以下是使用dplyr

的数据和解决方案

输入

DFI = structure(list(PO_ID = c("P1234", "P1234", "P1234", "P1234", 
"P1234", "P1234", "P2345", "P2345", "P3456", "P4567"), SO_ID = c("S1", 
"S1", "S1", "S2", "S2", "S2", "S3", "S4", "S7", "S10"), F_Year = c(2012, 
2012, 2012, 2013, 2013, 2013, 2011, 2011, 2014, 2015), Product_ID = c("385X", 
"385X", "385X", "450X", "450X", "900X", "3700", "3700", "A11U", 
"2700"), Revenue = c(1, 2, 3, 34, 34, 6, 7, 88, 9, 100), Quantity = c(1, 
2, 3, 8, 8, 6, 7, 8, 9, 40), Location1 = c("MA", "NY", "WA", 
"NY", "WA", "NY", "IL", "IL", "MN", "CA")), .Names = c("PO_ID", 
"SO_ID", "F_Year", "Product_ID", "Revenue", "Quantity", "Location1"
), row.names = c(NA, 10L), class = "data.frame")

查找表

DF_Lookup = structure(list(PO_ID = c("P1234", "P1234", "P1234", "P2345", 
"P2345", "P3456", "P4567"), SO_ID = c("S1", "S2", "S2", "S3", 
"S4", "S7", "S10"), F_Year = c(2012, 2013, 2013, 2011, 2011, 
2014, 2015), Product_ID = c("385X", "450X", "900X", "3700", "3700", 
"A11U", "2700"), Revenue = c(50, 70, 35, 100, -50, 50, 100), 
    Quantity = c(3, 20, 20, 20, -10, 20, 40)), .Names = c("PO_ID", 
"SO_ID", "F_Year", "Product_ID", "Revenue", "Quantity"), row.names = c(NA, 
7L), class = "data.frame")

输出

DFO = structure(list(PO_ID = c("P1234", "P1234", "P1234", "P1234", 
"P1234", "P1234", "P2345", "P2345", "P3456", "P4567"), SO_ID = c("S1", 
"S1", "S1", "S2", "S2", "S2", "S3", "S4", "S7", "S10"), F_Year = c(2012, 
2012, 2012, 2013, 2013, 2013, 2011, 2011, 2014, 2015), Product_ID = c("385X", 
"385X", "385X", "450X", "450X", "900X", "3700", "3700", "A11U", 
"2700"), Revenue = c(16.6666666666667, 16.6666666666667, 16.6666666666667, 
35, 35, 35, 100, -50, 50, 100), Quantity = c(1, 1, 1, 10, 10, 
20, 20, -10, 20, 40), Location1 = c("MA", "NY", "WA", "NY", "WA", 
"NY", "IL", "IL", "MN", "CA")), .Names = c("PO_ID", "SO_ID", 
"F_Year", "Product_ID", "Revenue", "Quantity", "Location1"), row.names = c(NA, 
10L), class = "data.frame")

这是我使用dplyr

的代码

我在这里使用了两个库：dplyr和compare

我使用左连接将查找表中的新条目添加到DFI。然后我根据组中的行数划分收入和列。这是因为我希望在分组时防止数字膨胀。

DF_Generated <- DFI %>% 
  dplyr::left_join(DF_Lookup,by = c("PO_ID", "SO_ID", "F_Year", "Product_ID")) %>%
  dplyr::group_by(PO_ID, SO_ID, F_Year, Product_ID) %>%
  dplyr::mutate(Count = n()) %>%
  dplyr::ungroup()%>%
  dplyr::mutate(Revenue = Revenue.y/Count, Quantity = Quantity.y/Count) %>%
  dplyr::select(PO_ID:Product_ID,Location1,Revenue,Quantity)

以下是输出的匹配方式：

compare(DF_Generated,DFO,allowAll = TRUE)
TRUE

我真诚地感谢任何帮助。

Answer 1

简单地向DFI添加列（在“更新连接”中），而不是创建新表更有效：

DFI[DF_Lookup, on=.(PO_ID, SO_ID, F_Year, Product_ID), 
  `:=`(newrev = i.Revenue/.N, newqty = i.Quantity/.N)
, by=.EACHI]

    PO_ID SO_ID F_Year Product_ID Revenue Quantity Location1    newrev newqty
 1: P1234    S1   2012       385X       1        1        MA  16.66667      1
 2: P1234    S1   2012       385X       2        2        NY  16.66667      1
 3: P1234    S1   2012       385X       3        3        WA  16.66667      1
 4: P1234    S2   2013       450X      34        8        NY  35.00000     10
 5: P1234    S2   2013       450X      34        8        WA  35.00000     10
 6: P1234    S2   2013       900X       6        6        NY  35.00000     20
 7: P2345    S3   2011       3700       7        7        IL 100.00000     20
 8: P2345    S4   2011       3700      88        8        IL -50.00000    -10
 9: P3456    S7   2014       A11U       9        9        MN  50.00000     20
10: P4567   S10   2015       2700     100       40        CA 100.00000     40

这是在OP中链接的Q＆amp; A的非常自然的扩展。

by=.EACHI中每行i的{{1}}组;和x[i,on=,j]是该组的行数。

如果您希望覆盖rev和qty cols，请使用.N。

加入然后使用data.table进行mutate而不使用中间表

1 个答案: