两个数据表上的 R 变异和子集数据

Question

我正在尝试获取与每行中的项目编号相似（在整个数据表中）的所有项目的 ECDF，并将 ECDF 列添加到数据表的末尾（EstimatePrediction）。

这适用于单个项目，因此可以一一检查。

    #Set Current ItemNumber
    currentItemNumber = “XXXXX”
     #Set Estimate Days
    currentEstimate = 5
    #Gets the index of the ItemNumber from the Matches table
    itemNoIndex = ((matches%>%subset(Item_No ==itemNumber))$ItemIndex[1])
    #Gets all the matching indexs that equal the index and select data
    matchingItems = matches%>%filter(ItemIndex == itemNoIndex) %>%
                             filter(MatchItemIndex != ItemIndex) %>%
                             merge(data.filter %>%
                             select(ITEM_NO,ACTUAL_DAYS),by = 'ITEM_NO')
    #Get the ECDF of all matching items at the estimate
    ecdf(matchingItems $ACTUAL_DAYS)( currentEstimate )

我正在尝试采用上述 R 代码并进行修改以适用于整个 data.filter 数据表。问题是它仅适用于 data.filter 数据中的第一行。第一行之后的行基于第一行的数据，而不是它们自己的数据。

EstimatePrediction = data.filter %>% mutate(PROBABILITY_PREDICTION = ecdf((matches%>%subset(ItemIndex == ((matches%>%subset(Item_No== ITEM_NO))$ItemIndex[1])) %>%
subset(MatchItemIndex != ItemIndex) %>%
merge(data.filter, by = 'ITEM_NO'))$ACTUAL_DAYS)(ESTIMATE_DAYS) )

我对 R 很陌生，所以我愿意接受任何建议。我可以通过遍历 data.filter 得到正确的输出，但是速度非常慢。

样本数据

    Matches

 MatchItemIndex ItemIndex MatchItemOrder  Item_No Count Cumulative
           <int>     <int>          <int>   <chr> <int>      <int>
1              1         1              1 CBL233J    14         14
2              2         2              1 CGW112N     4          4
3              3         3              1 CAT418D     5          5
4              4         4              1 BRH131T    29         29
5              5         5              1 CQD390A    17         17
6              6         6              1 CEE533J    11         11

    data.filter

   ITEM_NO ESTIMATE_DAYS ACTUAL_DAYS
1: CBL233J            10           6
2: CGW112N            22          12
3: CAT418D            22          18
4: BRH131T            33          16
5: CQD390A            21          15
6: CEE533J             7           2

编辑**** 我现在能够得到我需要的输出，它真的很慢：

data.filter = data.filter%>%mutate(Index = 1:n())
loopData = data.filter%>%select(ITEM_NO, ACTUAL_DAYS, ESTIMATE_DAYS, Index)
simpleV = unlist(loopData)
outputTest = 1:nrow(loopData)
ptm <- proc.time()
for(i in 1:nrow(loopData)){

  #Get Index for Item Number
  itemNoIndex = (matches%>%subset(ITEM_NO == simpleV[paste('ITEM_NO',i,sep="")]))$ItemIndex[1]
  #Find all the matches that have the same index 
  allNNItemData = matches%>%subset(ItemIndex == itemNoIndex) %>%
    subset(MatchItemIndex != ItemIndex) %>%
    merge(data.filter, by = 'ITEM_NO')

  outputTest[i] = ecdf(allNNItemData$ACTUAL_DAYS)(simpleV[paste('ESTIMATE_DAYS',i,sep="")])
} 
proc.time() - ptm

Answer 1

看看这是否解决了它：

library(tidyverse)

#-- Declare objects
Matches <- tibble(MatchItemIndex = 1:6, ItemIndex = 1:6,
                  MatchItemOrder = rep(1,6), Item_No = c("CBL233J", "CGW112N",
                                                         "CAT418D", "BRH131T",
                                                         "CQD390A", "CEE533J"), 
                  Count = c(14,4,5,29,17,11), Cumulative = c(14,4,5,29,17,11))

data.filter <- tibble(ITEM_NO = c("CBL233J", "CGW112N",
                                  "CAT418D", "BRH131T",
                                  "CQD390A", "CEE533J"),
                      ESTIMATE_DAYS = c(10, 22, 22, 33, 21, 7),
                      ACTUAL_DAYS = c(6, 12, 18, 16, 15, 2))

#-- Get matching items by item no
matchingItems <- intersect(Matches$Item_No, data.filter$ITEM_NO)

#-- Filter data.filter to matching items
df <- filter(data.filter, ITEM_NO == matchingItems)

#-- Do analysis
ecdf(df$ACTUAL_DAYS)(currentEstimate)