Multiple matching function in r - r

Question

I am trying to match two datasets using the following variables School (unique) with classes that need teachers. Some teachers have one specialty, some have more than one. I have been trying to use the match() and which( %in% ) base functions but I cannot get it to search for all the possible teacher matches. It always stops after the first match. Here is some sample data:
class<-c("english","history","art","art","math","history","art")
school<-c("C.H.S.","B.H.S.","D.H.S.","A.H.S.","Z.H.S.","M.H.S.","L.H.S.")
specialty<-c("math","history","English","history","literature","art","English")
teacher<-c("Jill","Jill","Sam","Liz","Liz","Liz","Rob")
teacher.skills<-data.frame(teacher, specialty)
school.needs<-data.frame(school,class)
teacher.match<-data.frame(Jill,Sam,Rob,Liz)
The final result would look like this:
Jill<-c("No","Yes","No","No","Yes","Yes","No")
Sam<-c("Yes","No","No","No","No","No","No")
Liz<-c("No","Yes","Yes","Yes","No","Yes","Yes")
Rob<-c("Yes","No","No","No","No","No","No")
match.result<-data.frame(school.needs, teacher.match)
match.result
I have even tried working on a little function like this but still can't get the final formatting right.
source.1<-school.needs
source.2<-teacher.skills
dist.name<-adist(source.1$class, source.2$specialty, partial = FALSE, ignore.case = TRUE)
min.name<-apply(dist.name, 1, min)
school.teacher.match<-NULL
for(i in 1:nrow(dist.name))
{
skills.ref<-match(min.name[i], dist.name[i,])
school.ref<-i
school.teacher.match<-rbind(data.frame(skills.ref=skills.ref, school.ref=school.ref, Teacher=source.2[skills.ref,]$teacher, Class=source.1[school.ref,]$class, School=source.1[school.ref,]$school, adist=min.name[i]), school.teacher.match)
school.teacher.match<-subset(school.teacher.match, school.teacher.match$adist==0)
}
school.teacher.match
Any help would be much appreciated, thanks!

Answer 1

Note that I had to modify your input data to change "English" to "english" for each match. The data is given by:
school.needs <- structure(list(school = structure(c(3L, 2L, 4L, 1L, 7L, 6L, 5L
), .Label = c("A.H.S.", "B.H.S.", "C.H.S.", "D.H.S.", "L.H.S.",
"M.H.S.", "Z.H.S."), class = "factor"), class = structure(c(2L,
3L, 1L, 1L, 4L, 3L, 1L), .Label = c("art", "english", "history",
"math"), class = "factor")), .Names = c("school", "class"), row.names = c(NA,
-7L), class = "data.frame")
teacher.skills <- structure(list(teacher = structure(c(1L, 1L, 4L, 2L, 2L, 2L,
3L), .Label = c("Jill", "Liz", "Rob", "Sam"), class = "factor"),
specialty = structure(c(5L, 3L, 2L, 3L, 4L, 1L, 2L), .Label = c("art",
"english", "history", "literature", "math"), class = "factor")), .Names = c("teacher",
"specialty"), row.names = c(NA, -7L), class = "data.frame")
Using merge and dcast from reshape2 (or data.table):
library(reshape2)
## use merge to match needs to skills
m <- merge(school.needs,teacher.skills,by.x="class",by.y="specialty")
m$val <- "Yes" ## add a column for the "Yes"
## go to wide format for the final result filling NA with "No"
result <- dcast(m,school+class~teacher,value.var="val",fill="No")
## school class Jill Liz Rob Sam
##1 A.H.S. art No Yes No No
##2 B.H.S. history Yes Yes No No
##3 C.H.S. english No No Yes Yes
##4 D.H.S. art No Yes No No
##5 L.H.S. art No Yes No No
##6 M.H.S. history Yes Yes No No
##7 Z.H.S. math Yes No No No

Answer 2

Here's how I'd do it:
(data)
schools <- data.frame(
school = c("C.H.S.", "B.H.S.", "D.H.S.", "A.H.S.","Z.H.S.", "M.H.S.", "L.H.S."),
class = c("english", "history", "art", "art", "math", "history", "art"),
stringsAsFactors = F)
teachers <- data.frame(
teacher = c("Jill", "Jill", "Sam", "Liz", "Liz", "Liz", "Rob"),
specialty = c("math", "history", "English", "history", "literature", "art", "English"),
stringsAsFactors = F)
(key concepts)
# you can get the specialties of a given teacher like this:
subset(teachers, teacher == 'Jill')$specialty
# [1] "math" "history"
# you can get the set of unique teachers like this:
unique(teachers$teacher)
# [1] "Jill" "Sam" "Liz" "Rob"
(solution)
# for each teacher, do any of their specialties match the class need of each school?
matches <-
sapply(unique(teachers$teacher), function(this_t) {
specs <- subset(teachers, teacher == this_t)$specialty
schools$class %in% specs
})
# combine with school data.frame
data.frame(schools, matches)
# school class Jill Sam Liz Rob
# 1 C.H.S. english FALSE FALSE FALSE FALSE
# 2 B.H.S. history TRUE FALSE TRUE FALSE
# 3 D.H.S. art FALSE FALSE TRUE FALSE
# 4 A.H.S. art FALSE FALSE TRUE FALSE
# 5 Z.H.S. math TRUE FALSE FALSE FALSE
# 6 M.H.S. history TRUE FALSE TRUE FALSE
# 7 L.H.S. art FALSE FALSE TRUE FALSE
Some notes:
1) It's way easier to read (and think about) when you include appropriate spacing in your code. Also, rather than create a bunch of vectors and then assemble into data.frames, do this in one step -- it's shorter, it helps show how the vectors relate to each other, and it won't clutter your global environment.
2) I'm leaving the match values as FALSE/TRUE, because since this is boolean data, it makes sense to use the appropriate data type. If you really want No/Yes, though, you can change these values into factors with those labels
3) The results are a little bit different than what you expected because 'English' == 'english' is FALSE. You might want to clean up your starting data. If you know that cases will be mixed and you case-insensitive matching, you can coerce all values to lowercase before comparing: tolower(schools$class) %in% tolower(specs)