在R中的矩阵中使用多个变量进行范围查找

Question

我觉得我遇到了一个复杂的问题（或者至少对我来说是这样！）。

我有一张价格表，需要从 csv 中读取，看起来就像这样：

V1 <- c("","Destination","Spain","Spain","Spain","Portugal","Portugal","Portugal","Italy","Italy","Italy")
V2 <- c("","Min_Duration",rep(c(1,3,6),3))
V3 <- c("","Max_Duration",rep(c(2,5,10),3))
V4 <- c("Full-board","Level_1",runif(9,100,200))
V5 <- c("Full-board","Level_2",runif(9,201,500))
V6 <- c("Full-board","Level_3",runif(9,501,1000))
V7 <- c("Half-board","Level_1",runif(9,100,200))
V8 <- c("Half-board","Level_2",runif(9,201,500))
V9 <- c("Half-board","Level_3",runif(9,501,1000))
Lookup_matrix <- as.data.frame(cbind(V1,V2,V3,V4,V5,V6,V7,V8))

上表中的价格当然会有点奇怪，因为它们是完全随机的——但我们可以忽略...

我也有这样一张桌子：

Destination <- c("Spain", "Italy", "Portugal")
Duration <- c(2,4,8)
Level <- c(1,3,3)
Board <- c("Half-board","Half-board","Full-board")
Price <- "Empty"
Price_matrix <- as.data.frame(cbind(Destination,Duration,Level,Board,Price))

我的问题是 - 如何使用查找矩阵中可以找到的相应价格填充价格矩阵的“价格”列？请注意，价格矩阵的持续时间变量必须适合查找矩阵中“Min_Duration”和“Max_Duration”列之间的范围。

在 Excel 中，我会使用 Index,Match 公式。但我被 R 难住了。

提前致谢， 丹

Answer 1

这是tidyverse 的可能性

首先，请注意我重命名了您的输入对象； Price_matrix 和 Lookup_matrix 都是 data.frames（不是矩阵）。

df1 <- Price_matrix
df2 <- Lookup_matrix

接下来我们需要修复df2 = Lookup_matrix的列名。

# Fix column names
colnames(df2) <- gsub("^_", "", apply(df2[1:2, ], 2, paste0, collapse = "_"))
df2 <- df2[-(1:2), ]

我们现在基本上做df1和df2的左连接；为了使df2 具有合适的格式，我们将数据从宽向长传播，为每个Board 和Level 提取Price 值，并将条目从Min_Duration 扩展到Max_Duration。然后我们通过Destination、Duration、Level 和Board 加入。

请注意，在您的示例中，Destination = Italy 在Lookup_matrix 中没有Level = 3 条目；因此，我们为此条目获得Price = NA。

library(tidyverse)
left_join(
    df1 %>%
        mutate_if(is.factor, as.character) %>%
        select(-Price),
    df2 %>%
        mutate_if(is.factor, as.character) %>%
        gather(key, Price, -Destination, -Min_Duration, -Max_Duration) %>%
        separate(key, into = c("Board", "Level"), sep = "_", extra = "merge") %>%
        mutate(Level = sub("Level_", "", Level)) %>%
        rowwise() %>%
        mutate(Duration = list(seq(as.numeric(Min_Duration), as.numeric(Max_Duration)))) %>%
        unnest() %>%
        select(-Min_Duration, -Max_Duration) %>%
        mutate(Duration = as.character(Duration)))
#Joining, by = c("Destination", "Duration", "Level", "Board")
#  Destination Duration Level      Board            Price
#1       Spain        2     1 Half-board 119.010942545719
#2       Italy        4     3 Half-board             <NA>
#3    Portugal        8     3 Full-board 764.536124917446

Answer 2

使用数据表：

library(data.table)

nms = trimws(do.call(paste, transpose(Lookup_matrix[1:2, ])))# column names

cat(do.call(paste, c(collapse="\n", Lookup_matrix[-(1:2), ])), file = "mm.csv") 
  # Rewrite the data in the correct format. You do not have to.
  # Just doing Lookup_matrix1 = setNames(Lookup_matrix[-(1:2),],nms) is enough 
  # but it will not have rectified the column classes. 

Lookup_matrix1 = fread("mm.csv", col.names = nms)  

melt(Lookup_matrix1, 1:3)[,
        c("Board", "Level") := .(sub("[.]", "-", sub("\\.Leve.*", "", variable)), sub("\\D+", "", variable))][
        Price_matrix[, -5], on=c("Destination", "Board", "Level", "Min_Duration <= Duration", "Max_Duration >= Duration")]

  Destination Min_Duration Max_Duration           variable    value      Board Level
1:       Spain            2            2 Half.board.Level_1 105.2304 Half-board     1
2:       Italy            4            4               <NA>       NA Half-board     3
3:    Portugal            8            8 Full.board.Level_3 536.5132 Full-board     3