Question

我有以下数据表：

dt <- fread("
  ID   | EO_1 | EO_2 | EO_3 | GROUP
ID_001 | 0.5  |  1.2 |      |   A  
ID_002 |      |      |      |   A
ID_003 |      |      |      |   A
ID_004 |      |      |      |   A
ID_001 | 0.4  |  2.5 |      |   B
ID_002 |      |      |      |   B
ID_003 |      |      |      |   B
ID_004 |      |      |      |   B  
            ", 
            sep = "|",
            colClasses = c("character", "numeric", "numeric", "numeric", "character"))

，我正在尝试执行一些按行的操作，这些操作有时取决于前几行中的数据。更具体地说：

calc_EO_1 <- function(
  EO_1,
  EO_2
){
  EO_1 <- shift(EO_1, type = "lag") * shift(EO_2, type = "lag")
  return(EO_1)
}

calc_EO_2 <- function(
  EO_1,
  EO_2,
  EO_3
){
  EO_2 <- EO_1 * shift(EO_2, type = "lag") * shift(EO_3, type = "lag")
  return(EO_2)
}

calc_EO_3 <- function(
  EO_1,
  EO_2
){
  EO_3 <- EO_1 * EO_2
  return(EO_3)
}

最后一个需要从第一行开始计算，因为它取决于其他字段（应该很容易），然后，这三个操作都必须连续且逐行进行。

离我最近的是：

first_row_bygroup_index <- dt[, .I[1], by = GROUP]$V1

dt[first_row_bygroup_index, 
   EO_3 := calc_EO_3(EO_1, EO_2)
     ]

dt[!first_row_bygroup_index, 
   `:=` (
     EO_1 = calc_EO_1(EO_1, EO_2),
     EO_2 = calc_EO_2(EO_1, EO_2, EO_3),
     EO_3 = calc_EO_3(EO_1, EO_2)
     ),
   by = row.names(dt[!first_row_bygroup_index])]

但它只能正确计算第一行：

  ID   | EO_1 | EO_2 | EO_3 | GROUP
ID_001 | 0.5  |  1.2 |  0.6 |   A  
ID_002 |      |      |      |   A
ID_003 |      |      |      |   A
ID_004 |      |      |      |   A
ID_001 | 0.4  |  2.5 |  1.0 |   B
ID_002 |      |      |      |   B
ID_003 |      |      |      |   B
ID_004 |      |      |      |   B

成为那些空格NAs。

我认为我离解决方案不太远，但是我找不到找到使之可行的方法。问题是我无法使用子集外部的行在行子集中执行操作。

编辑我错过了预期的结果：

  ID   |   EO_1      |     EO_2      |       EO_3      | GROUP
ID_001 |  0.50000000 |   1.20000000  |      0.60000000 |   A  
ID_002 |  0.60000000 |   0.43200000  |      0.25920000 |   A
ID_003 |  0.25920000 |   0.02902376  |      0.00752296 |   A
ID_004 |  0.00752296 |   0.00000164  |      0.00000001 |   A
ID_001 |  0.40000000 |   2.50000000  |      1.00000000 |   B
ID_002 |  1.00000000 |   2.50000000  |      2.50000000 |   B
ID_003 |  2.50000000 |  15.62500000  |     39.06250000 |   B
ID_004 | 39.06250000 | 23841.8580000 | 931322.57810000 |   B

NEW EDIT 我想出了以下代码段，但我宁愿稍等一下，看看是否有人可以获得比此方法更有效的解决方案：

while(any(is.na(dt))){
  dt[, `:=` (
    EO_3 = calc_EO_3(EO_1, EO_2),
    EO_1 = ifelse(ID == "ID_001", EO_1, calc_EO_1(EO_1, EO_2)),
    EO_2 = ifelse(ID == "ID_001", EO_2, calc_EO_2(EO_1, EO_2, EO_3))
  )]  
}

我已经提出了一个类似的dplyr解决方案，同时也提供了难看的while循环修复。关键是找到一种进行按行计算的方法，该方法可以从前一行获取信息，即使该行位于所选子集之外。我希望有人可以改善它，因此我将稍等一下，然后将其标记为解决方案。

Answer 1

这是另一种可能的方法：

dt[!is.na(EO_1), EO_3 := EO_1 * EO_2, by=.(GROUP)]
dt[ID!="ID_001", c("EO_1", "EO_2", "EO_3") :=
    dt[,
        {
            eo1 <- EO_1[1L]; eo2 <- EO_2[1L]; eo3 <- EO_3[1L]
            .SD[ID!="ID_001",
                {
                    eo1 <- eo1 * eo2
                    eo2 <- eo1 * eo2 * eo3
                    eo3 <- eo1 * eo2
                    .(eo1, eo2, eo3)
                },
                by=.(ID)]
        },
        by=.(GROUP)][, -1L:-2L]
]

输出：

       ID        EO_1         EO_2         EO_3 GROUP
1: ID_001  0.50000000 1.200000e+00 6.000000e-01     A
2: ID_002  0.60000000 4.320000e-01 2.592000e-01     A
3: ID_003  0.25920000 2.902376e-02 7.522960e-03     A
4: ID_004  0.00752296 1.642598e-06 1.235720e-08     A
5: ID_001  0.40000000 2.500000e+00 1.000000e+00     B
6: ID_002  1.00000000 2.500000e+00 2.500000e+00     B
7: ID_003  2.50000000 1.562500e+01 3.906250e+01     B
8: ID_004 39.06250000 2.384186e+04 9.313226e+05     B

Answer 2

您希望最终产品看起来像这样的数据吗？

go <- function(x, y, n) {
  z <- x * y
  for (i in 1:(n - 1)) {
    x <- c(x[1] * y[1], x)
    y <- c(x[1] * y[1] * z[1], y)
    z <- x * y
  }
  data.table(EO_1 = x, EO_2 = y, EO_3 = z)[.N:1][, lapply(.SD, round, 8)]
}

go(.5, 1.2, 4)

         EO_1       EO_2       EO_3
1: 0.50000000 1.20000000 0.60000000
2: 0.60000000 0.43200000 0.25920000
3: 0.25920000 0.02902376 0.00752296
4: 0.00752296 0.00000164 0.00000001

Answer 3

棘手的问题！我尝试使用dplyr中的nest并应用costum函数。

options("scipen"=999, "digits"=8)
library(tidyverse)

# Custom function
logic <- function(.df){
  for(i in 2:nrow(.df)){
    .df[i, "EO_1"] <- .df[i-1, "EO_1"] * .df[i-1, "EO_2"]
    .df[i, "EO_2"] <- .df[i, "EO_1"] * .df[i-1, "EO_2"] * .df[i-1, "EO_3"]
    .df[i, "EO_3"] <- .df[i, "EO_1"] * .df[i, "EO_2"]
  }
  .df
}

# Answers the question
dt <- dt %>% 
  mutate(EO_3 = EO_1 * EO_2) %>% 
  nest(-GROUP) %>% 
  mutate(data = map(data, ~logic(.))) %>% 
  unnest()

# Fixing nice output
dt %>% 
  mutate_at(vars(contains("EO_")), ~round(., 8)) %>% 
  select(-GROUP, everything(), GROUP) %>% 
  as.data.frame()

给你

      ID        EO_1           EO_2            EO_3 GROUP
1 ID_001  0.50000000     1.20000000      0.60000000     A
2 ID_002  0.60000000     0.43200000      0.25920000     A
3 ID_003  0.25920000     0.02902376      0.00752296     A
4 ID_004  0.00752296     0.00000164      0.00000001     A
5 ID_001  0.40000000     2.50000000      1.00000000     B
6 ID_002  1.00000000     2.50000000      2.50000000     B
7 ID_003  2.50000000    15.62500000     39.06250000     B
8 ID_004 39.06250000 23841.85791016 931322.57461548     B

如何使用[r] data.table（如果可能）与前几行相关地执行多个逐行操作

3 个答案: