我有关于客户及其访问过的商店的数据(至少一次)。
Customer | Store
1 A
1 B
2 A
2 C
3 A
4 A
4 B
4 C
我想知道有多少用户访问了每个两个商店的组合。
如何转换以前的数据结构(使用R)以获得以下结构?
Store 1 | Store 2 | Nb_Customer
A B 2 (Customer 1 & 4 visited store A & B )
A C 2 (Customer 2 & 4 visited store A & C)
修改 关于Henrik的解决方案:正如您所看到的,我对配对存在问题。
# number of visits for each customer in each store
> df <- data.frame(Customer=c(1,1,2,2,3,4,4,4), Store=c('A', 'B', 'A', 'C', 'A', 'A', 'B', 'C'))
> # number of visits for each customer in each store
> tt <- with(df, table(df$Customer, df$Store))
> tt
A B C
1 1 1 0
2 1 0 1
3 1 0 0
4 1 1 1
>
> # number of stores
> n <- with(df, length(unique(df$Store)))
> n
[1] 3
>
> # all pairs of column numbers, to be selected from the table tt
> cols <- with(df, combn(n, 2))
> cols
[,1] [,2] [,3]
[1,] 1 1 2
[2,] 2 3 3
>
> # pairs of stores
> pair <- t(with(df, combn(unique(df$Store), 2)))
> pair
[,1] [,2]
[1,] "A" "B"
[2,] "1" "3"
[3,] "2" "3"
答案 0 :(得分:2)
另一种可能性:
# number of visits for each customer in each store
tt <- with(df, table(Customer, Store))
tt
# number of stores
n <- with(df, length(unique(Store)))
n
# all pairs of column numbers, to be selected from the table tt
cols <- with(df, combn(n, 2))
cols
# pairs of stores
pair <- t(with(df, combn(unique(Store), 2)))
pair
# select pairs of columns from tt
# count number of rows for which each customer has visited more than one store
# combine the counts with names of stores from 'pairs' to a data frame
ll <- lapply(seq(ncol(cols)), function(x){
tt2 <- tt[ , cols[ , x]]
n_cust <- sum(rowSums(tt2) > 1)
data.frame(store1 = pair[x, 1], store2 = pair[x, 2], n_cust = n_cust)
})
ll
# convert list to data frame
df2 <- do.call(rbind, ll)
df2
# store1 store2 n_cust
# 1 A B 2
# 2 A C 2
# 3 B C 1
答案 1 :(得分:1)
也许这不是最有效的方法,但它有效:
df <- data.frame(Customer=c(1,1,2,2,3,4,4,4), Store=c('A', 'B', 'A', 'C', 'A', 'A', 'B', 'C'))
cmb <- t(combn(unique(as.character(df$Store)),m=2))
count <- rep(0,nrow(cmb))
for (i in unique(df$Customer)){
for (j in 1:nrow(cmb)){
count[j] <- count[j]+as.numeric(all(cmb[j,] %in% df$Store[df$Customer==i]))
}
}
res <- data.frame(Store1=cmb[,1], Store2=cmb[,2], Nb_customer=count)
Store1 Store2 Nb_customer
1 A B 2
2 A C 2
3 B C 1
修改强>
使用关联规则,您可以这样做:
# load library arulas
library(arules)
#original data frame
df <- data.frame(Customer=c(1,1,2,2,3,4,4,4), Store=c('A', 'B', 'A', 'C', 'A', 'A', 'B', 'C'))
# create list
a_list <- lapply(unique(df$Customer),function(x)df$Store[df$Customer==x])
## set transaction names
names(a_list) <- paste("Tr",unique(df$Customer), sep = "")
a_list
## coerce into transactions
trans <- as(a_list, "transactions")
# create association rules
rules <- apriori(trans, parameter=list(minlen=2, maxlen=2, ext=TRUE, originalSupport=FALSE))
# calculate frequency of pairs of stores
rules@quality$abs_support <- rules@quality$support*length(trans)
inspect(rules)
lhs rhs support confidence lhs.support lift abs_support
1 {B} => {A} 0.5 1 0.5 1 2
2 {C} => {A} 0.5 1 0.5 1 2
abs_support
是同时发生的次数
答案 2 :(得分:0)
这样的东西?
d<-data.frame(v1=c(1,1,2,2,3,4,4,4),v2=c("A","B","A","C","A","A","B","C"))
df<-as.data.frame.matrix(table(d))
which(df$A==1 & df$B==1)
which(df$A==1 & df$C==1)
which(df$B==1 & df$C==1)