library(dplyr)
library(tidyr)
df <- data.frame(
First = c("MW3", "MW3", "MW4", "MW5", "MW6", "MW7", "MW7", "MW8"),
Second = c("MW4; MW5; MW6", "MW5; MW3; MW7", "MW8; MW7; MW3",
"MW5; MW6; MW4", "MW3; MW7; MW8", "MW6; MW8; MW4",
"MW3; MW4; MW5", "MW6; MW3; MW7")
)
df <- df %>%
mutate(
ID = row_number(),
lmt = n_distinct(ID)
) %>%
separate_rows(Second, sep = "; ") %>%
group_by(ID) %>%
mutate(
wgt = row_number()
) %>% ungroup()
让我们说，对于每个ID，我只想保留First和Second的1种组合（即df中唯一ID的长度应始终等于{{1} }。
但是，我想通过优化某些参数来做到这一点。解决方案的设计方式应为：
应尽可能选择与lmt 1的组合，或者也选择2，但应避免3（即wgt的总和应最小）；
wgt中的值的频率与Second中的频率的差应接近0。
关于如何在R中实现这一点的任何想法？
在上述情况下的预期输出为：
First为什么？仅仅是因为有了这种组合，右侧（ ID First Second wgt lmt
1 1 MW3 MW4 1 8
2 2 MW3 MW7 3 8
3 3 MW4 MW7 2 8
4 4 MW5 MW5 1 8
5 5 MW6 MW3 1 8
6 6 MW7 MW8 2 8
7 7 MW7 MW3 1 8
8 8 MW8 MW6 1 8
）的任何元素都没有在左侧（Second）的更多。例如，右侧和左侧都有两个MW3元素。
但是，这里要付出的代价是First并不总是1（wgt的总和不是8而是12）。
澄清：如果两个标准不能同时最小化，则应优先考虑第二个标准（频率之间的差异）的最小化。
答案 0 :(得分：3)
我解决了这个问题，并且可以使用 minconflicts 算法的变体来共享解决方案。这里的关键是找到一个可以结合您的要求的评分功能。以下实现遵循您的建议“ 说，我们的目标应该是优先考虑最小化第二个标准（频率之间的差异）”。在您的实际数据上尝试其他评分功能，让我们看看您能获得多大的帮助。
在您的原始数据（8个ID）上，我得到的解决方案与您发布的解决方案同样好：
> solution_summary(current_solution)
Name FirstCount SecondCount diff
1: MW3 2 2 0
2: MW4 1 1 0
3: MW5 1 1 0
4: MW6 1 1 0
5: MW7 2 2 0
6: MW8 1 1 0
[1] "Total freq diff: 0"
[1] "Total wgt: 12"
对于具有10000个ID的随机数据，该算法能够找到第一/第二频率没有差异（但wgt的总和大于最小值）的解决方案：
> solution_summary(current_solution)
Name FirstCount SecondCount diff
1: MW3 1660 1660 0
2: MW4 1762 1762 0
3: MW5 1599 1599 0
4: MW6 1664 1664 0
5: MW7 1646 1646 0
6: MW8 1669 1669 0
[1] "Total freq diff: 0"
[1] "Total wgt: 19521"
以下代码：
library(data.table)
df <- as.data.table(df)
df <- df[, .(ID, First, Second, wgt)]
# PLAY AROUND WITH THIS PARAMETER
freq_weight <- 0.9
wgt_min <- df[, uniqueN(ID)]
wgt_max <- df[, uniqueN(ID) * 3]
freq_min <- 0
freq_max <- df[, uniqueN(ID) * 2] #verify if this is the worst case scenario
score <- function(solution){
# compute raw scores
current_wgt <- solution[, sum(wgt)]
second_freq <- solution[, .(SecondCount = .N), by = Second]
names(second_freq)[1] <- "Name"
compare <- merge(First_freq, second_freq, by = "Name", all = TRUE)
compare[is.na(compare)] <- 0
compare[, diff := abs(FirstCount - SecondCount)]
current_freq <- compare[, sum(diff)]
# normalize
wgt_score <- (current_wgt - wgt_min) / (wgt_max - wgt_min)
freq_score <- (current_freq - freq_min) / (freq_max - freq_min)
#combine
score <- (freq_weight * freq_score) + ((1 - freq_weight) * wgt_score)
return(score)
}
#initialize random solution
current_solution <- df[, .SD[sample(.N, 1)], by = ID]
#get freq of First (this does not change)
First_freq <- current_solution[, .(FirstCount = .N), by = First]
names(First_freq)[1] <- "Name"
#get mincoflict to be applied on each iteration
minconflict <- function(df, solution){
#pick ID
change <- solution[, sample(unique(ID), 1)]
#get permissible values
values <- df[ID == change, .(Second, wgt)]
#assign scores
values[, score := NA_real_]
for (i in 1:nrow(values)) {
solution[ID == change, c("Second", "wgt") := values[i, .(Second, wgt)]]
set(values, i, "score", score(solution))
}
#return the best combination
scores <<- c(scores, values[, min(score)])
solution[ID == change, c("Second", "wgt") := values[which.min(score), .(Second, wgt)]]
}
#optimize
scores <- 1
iter <- 0
while(TRUE){
minconflict(df, current_solution)
iter <- iter + 1
#SET MAX NUMBER OF ITERATIONS HERE
if(scores[length(scores)] == 0 | iter >= 1000) break
}
# summarize obtained solution
solution_summary <- function(solution){
second_freq <- solution[, .(SecondCount = .N), by = Second]
names(second_freq)[1] <- "Name"
compare <- merge(First_freq, second_freq, by = "Name", all = TRUE)
compare[is.na(compare)] <- 0
compare[, diff := abs(FirstCount - SecondCount)]
print(compare)
print(paste("Total freq diff: ", compare[, sum(diff)]))
print(paste("Total wgt: ", solution[, sum(wgt)]))
}
solution_summary(current_solution)
答案 1 :(得分：1)
这基本上是一个二部图匹配问题，因此可以在合理的时间内通过maxflow或线性编程（bipartite graph matching to match two sets）完全解决。
library(lpSolve)
MISMATCH.COST <- 1000
.create.row <- function(row.names, first) {
row <- vector(mode="numeric", length=length(first))
for (i in 1:length(row.names))
row = row + (-MISMATCH.COST+i)*(row.names[i]==first)
return(row)
}
find.pairing <- function(First, Second) {
row.names = sapply(Second, strsplit, "; ")
# Create cost matrix for assignment
mat = sapply(row.names, .create.row, First)
assignment <- lp.assign(mat)
print("Total cost:")
print(assignment$objval+length(First)*MISMATCH.COST)
solution <- lp.assign(mat)$solution
pairs <- which(solution>0, arr.ind=T)
matches = First[pairs[,1]]
# Find out where a mismatch has occured, and replace match
for (i in 1:length(matches)) {
if (!(matches[i] %in% row.names[[i]])) {
matches[i] = row.names[[i]][1]
}
}
result = data.frame(
First[pairs[,2]],
matches)
return(result)
}
在您的示例上运行它可以提供最佳解决方案（应始终如此）
> First = c("MW3", "MW3", "MW4", "MW5", "MW6", "MW7", "MW7", "MW8")
> Second = c("MW4; MW5; MW6", "MW5; MW3; MW7", "MW8; MW7; MW3",
"MW5; MW6; MW4", "MW3; MW7; MW8", "MW6; MW8; MW4",
"MW3; MW4; MW5", "MW6; MW3; MW7")
Second = c("MW4; MW5; MW6", "MW5; MW3; MW7", "MW8; MW7; MW3",
+ "MW5; MW6; MW4", "MW3; MW7; MW8", "MW6; MW8; MW4",
+ "MW3; MW4; MW5", "MW6; MW3; MW7")
> find.pairing(First, Second)
[1] "Total cost:"
[1] 12
First.pairs...2.. matches
1 MW3 MW4
2 MW3 MW3
3 MW4 MW7
4 MW5 MW5
5 MW6 MW7
6 MW7 MW8
7 MW7 MW3
8 MW8 MW6