将组数据与用户数据匹配并获取组

Question

I have two dataset, one which is various products like this

User Product
A .   1
A .   2
A .   3
B .   1
B .   3
B .   4

And another table

Group Product
X1 .   1
X1 .   2
X1 .   4
X2 .   1
X2 .   3

My requirement is if all product in a group are present for a user then user belong to the group and would look like this

User X1 X2
A .   1  0
B .   0 .1

I have tried manually doing with loops, tried to match with customize functions but my actual data size is quite large and solutions are not perfect.

Need help on this.

Answer 1

You can accomplish this with some tidy code.

First, some dot-less data (I took the dots to be not necessary, correct me if I'm wrong):

x1 <- read.table(header=TRUE, stringsAsFactors=FALSE, text='
User Product
A    1
A    2
A    3
B    1
B    3
B    4')
x2 <- read.table(header=TRUE, stringsAsFactors=FALSE, text='
Group Product
X1    1
X1    2
X1    4
X2    1
X2    3')
out <- read.table(header=TRUE, stringsAsFactors=FALSE, text='
User X1 X2
A    1  0
B    0  1')

The needed packages:

library(dplyr)
library(tidyr)
library(purrr)

x1n <- group_by(x1, User) %>% nest(.key = "x1prod")
x2n <- group_by(x2, Group) %>% nest(.key = "x2prod")

crossing(User = x1n$User, Group = x2n$Group) %>%
  left_join(x1n, by = "User") %>%
  left_join(x2n, by = "Group") %>%
  mutate(allx = map2_lgl(x1prod, x2prod, ~ all(.y$Product %in% .x$Product)))
# # A tibble: 4 x 5
#   User  Group x1prod           x2prod           allx 
#   <chr> <chr> <list>           <list>           <lgl>
# 1 A     X1    <tibble [3 x 1]> <tibble [3 x 1]> FALSE
# 2 A     X2    <tibble [3 x 1]> <tibble [2 x 1]> TRUE 
# 3 B     X1    <tibble [3 x 1]> <tibble [3 x 1]> FALSE
# 4 B     X2    <tibble [3 x 1]> <tibble [2 x 1]> TRUE 

This is of course not your desired result, but I show that output to demonstrate what nesting is doing and that we are row-wise comparing x1prod (single column, Product ) and x2prod (same). From here, simply removing columns and spreading is sufficient:

crossing(User = x1n$User, Group = x2n$Group) %>%
  left_join(x1n, by = "User") %>%
  left_join(x2n, by = "Group") %>%
  mutate(allx = map2_lgl(x1prod, x2prod, ~ all(.y$Product %in% .x$Product))) %>%
  select(-x1prod, -x2prod) %>%
  spread(Group, allx)
# # A tibble: 2 x 3
#   User  X1    X2   
#   <chr> <lgl> <lgl>
# 1 A     FALSE TRUE 
# 2 B     FALSE TRUE 

(I'm also assuming your desired output is slightly mistaken, as A does not have "4" from group X1 .)

Answer 2

Another answer that uses dplyr only and a loop would be:

library(dplyr)
myFunction = function(df1, df2, user, group, product){
  user = deparse(substitute(user))
  product = deparse(substitute(product))
  group = deparse(substitute(group))
  answer = data.frame(User = as.character(df1[1, user]))
  for(i in unique(df2[,group])){
    temp = df1 %>% summarise(!!i := if_else(all(df2[which(df2[,group] == i),][,product] %in% unique(df1[[product]])), 1, 0))
    answer = cbind(answer, temp[,i])
  }
  return(answer)
}

df1 %>% group_by(User) %>% do(myFunction(., df2, User, Group, Product))
df1

# A tibble: 2 x 3
# Groups:   User [2]
  User     X1    X2
  <chr> <dbl> <dbl>
1 1         0     1
2 2         0     1

Answer 3

Here's a solution using only dplyr and tidyr -

library(dplyr)
library(tidyr)

user_product <- data.frame(User = rep(LETTERS[1:2], each = 3), Product = c(1:3, 1, 3, 4))
group_product <- data.frame(Group = c("x1", "x1", "x1", "x2", "x2"), Product = c(1,2,4,1,3))

left_join(user_product, group_product, by = "Product") %>%
  left_join(group_product, by = "Group") %>%
  group_by(User, Group) %>%
  summarize(
    test = all(Product.y %in% Product.x)
  ) %>%
  spread(Group, test)

# A tibble: 2 x 3
# Groups:   User [2]
  User  x1    x2   
  <fct> <lgl> <lgl>
1 A     FALSE TRUE 
2 B     FALSE TRUE

Somewhat similar to what's already shared by @r2evans but much less verbose, easier to understand, and one less package dependency.