Combining columns into one in MongoDB Aggregate Framework - mongodb

Question

Is it possible to group by values across multiple columns?
Let's say I'm storing interactions between people by day, and keep track of from's and to's with a count as follows.
db.collection =
[
{ from : 'bob', to : 'mary', day : 1, count : 2 },
{ from : 'bob', to : 'steve', day : 2, count : 1 },
{ from : 'mary', to : 'bob', day : 1, count : 3 },
{ from : 'mary', to : 'steve', day : 3, count : 1 },
{ from : 'steve', to : 'bob', day : 2, count : 2 },
{ from : 'steve', to : 'mary', day : 1, count : 1 }
]
This allows me to get all interactions for, lets say, 'bob' with any one by grouping on from:, and summing count:.
Now I want to get all interaction for a user, so basically group by values across from: and to:. Essentially, sum up count: for each name, regardless whether it was in from: or to:
[UPDATE]
The desired output would be:
[
{ name : 'bob', count : 8 },
{ name : 'mary', count : 7 },
{ name : 'steve', count : 3 }
]
The easiest would be to create a new column names: and store from: and to: inside, then $unwind, but that seems wasteful.
Any hints?
Thanks

Answer 1

Is it possible to group by values across multiple columns?
Yes, it's possible in MongoDB to group values across different columns.
It's very straight forward to do it via MapReduce. But it's also possible to do it with aggregation framework, even if you don't store an array of participants (if you had array of names with both participants, then it's just an $unwind, and a $group - quite simple and I think more elegant than either MapReduce or the pipeline you'd have to use with the current schema).
Pipeline that works with your schema as is:
db.collection.aggregate( [
{
"$group" : {
"_id" : "$from",
"sum" : {
"$sum" : "$count"
},
"tos" : {
"$push" : {
"to" : "$to",
"count" : "$count"
}
}
}
}
{ "$unwind" : "$tos" }
{
"$project" : {
"prev" : {
"id" : "$_id",
"sum" : "$sum"
},
"tos" : 1
}
}
{
"$group" : {
"_id" : "$tos.to",
"count" : {
"$sum" : "$tos.count"
},
"prev" : {
"$addToSet" : "$prev"
}
}
}
{ "$unwind" : "$prev" }
{
"$group" : {
"_id" : "1",
"t" : {
"$addToSet" : {
"id" : "$_id",
"c" : "$count"
}
},
"f" : {
"$addToSet" : {
"id" : "$prev.id",
"c" : "$prev.sum"
}
}
}
}
{ "$unwind" : "$t" }
{ "$unwind" : "$f" }
{
"$project" : {
"name" : {
"$cond" : [
{
"$eq" : [
"$t.id",
"$f.id"
]
},
"$t.id",
"nobody"
]
},
"count" : {
"$add" : [
"$t.c",
"$f.c"
]
},
"_id" : 0
}
}
{ "$match" : { "name" : { "$ne" : "nobody" } } }
]);
On your sample input the output is:
{
"result" : [
{
"name" : "bob",
"count" : 8
},
{
"name" : "mary",
"count" : 7
},
{
"name" : "steve",
"count" : 5
}
],
"ok" : 1
}

Answer 2

$unwind can be expensive. Wouldn't this be easier to query?
db.collection =
[
{ name : 'bob', to : 'mary', day : 1, count : 2 },
{ name : 'mary', from : 'bob', day : 1, count : 2 },
{ name : 'bob', to : 'steve', day : 2, count : 1 },
{ name : 'bob', from : 'steve',day : 2, count : 1 },
{ name : 'mary', to : 'bob', day : 1, count : 3 },
{ name : 'mary', from : 'bob', day : 1, count : 3 },
{ name : 'mary', to : 'steve', day : 3, count : 1 },
{ name : 'mary', from : 'steve' day : 3, count : 1 },
{ name : 'steve', to : 'bob', day : 2, count : 2 },
{ name : 'steve', from : 'bob', day : 2, count : 2 },
{ name : 'steve', to : 'mary', day : 1, count : 1 }
{ name : 'steve', from : 'mary', day : 1, count : 1 }
]
[Update]
With your existing structure, here's how you can do it with Map-Reduce, but this isn't really for real-time results. It will be slower overall, but likely more efficient though than a massive $unwind operation in AF;
db.so.drop();
db.so.insert(
[
{ from: 'bob', to: 'mary', day: 1, count: 2 },
{ from: 'bob', to: 'steve', day: 2, count: 1 },
{ from: 'mary', to: 'bob', day: 1, count: 3 },
{ from: 'mary', to: 'steve', day: 3, count: 1 },
{ from: 'steve', to: 'bob', day: 2, count: 2 },
{ from: 'steve', to: 'mary', day: 1, count: 1 }
]);
db.runCommand(
{
"mapreduce": "so", // don't need the collection name here if it's above
"map": function(){
emit(this.from, {count: this.count});
emit(this.to, {count: this.count});
},
"reduce": function (name, values) {
var result = { count: 0 };
values.forEach(function (v) {
result.count += v.count;
});
return result;
},
query: {},
out: { inline: 1 },
}
);
which produces;
{
"results" : [
{
"_id" : "bob",
"value" : {
"count" : 8
}
},
{
"_id" : "mary",
"value" : {
"count" : 7
}
},
{
"_id" : "steve",
"value" : {
"count" : 5
}
}
],
"timeMillis" : 1,
"counts" : {
"input" : 6,
"emit" : 12,
"reduce" : 3,
"output" : 3
},
"ok" : 1
}