My documents looks like this:
{
"_id" : "53ce85eda2579da8b40c1f0f",
"name" : "Autokino",
"tags" : [
"forMen"
],
"ratings" : [
{ "rating" : 5, "uuid" : "..."},
{ "rating" : 4, "uuid" : "..."},
{ "rating" : 4, "uuid" : "..."},
{ "rating" : 1, "uuid" : "..."},
]
}
Now I need the average of ratings.rating (here it should be 3.5). My query looks like this:
activities.aggregate([
{ $match: { _id: ObjectID(req.params.id) } },
{ $unwind: '$ratings' },
{ $group: {
_id: '$_id',
rating: { $avg: '$ratings.rating'},
}},
]);
It works, but what I get is:
{
"_id" : "53ce85eda2579da8b40c1f0f",
"rating" : 3.5
}
and this is what I need to get:
{
"_id" : "53ce85eda2579da8b40c1f0f",
"name" : "Autokino",
"tags" : [
"forMen"
],
"rating" : 3.5
}
(The original document without ratings array but with rating average)
How can I solve this problem?
Pipeline stages like $group and $project are "absolute" in that only the declared fields are emitted. You need another operator here. $first will do:
activities.aggregate([
{ "$match": { "_id": ObjectID(req.params.id) } },
{ "$unwind": "$ratings" },
{ "$group": {
"_id": "$_id",
"name": { "$first": "$name" },
"tags": { "$first": "$tags" },
"rating": { "$avg": "$ratings.rating" },
}},
]);
Since $unwind makes many documents out of the array contents de-normalized, you can use $first here to just take the "first" occurrence of the additional field that you are not otherwise aggregating.
If you are worried about lots of fields to declare this way MongoDB 2.6 does offer the $$ROOT variable. I'ts usage and output are likely not what you really want:
activities.aggregate([
{ "$match": { "_id": ObjectID(req.params.id) } },
{ "$project": {
"_id": "$$ROOT",
"ratings": 1
}},
{ "$unwind": "$ratings" },
{ "$group": {
"_id": "$_id",
"rating": { "$avg": "$ratings.rating" },
}},
]);
This gives you something like:
{
"_id" : {
"_id": "53ce85eda2579da8b40c1f0f",
"name" : "Autokino",
"tags" : [
"forMen"
],
"ratings" : [
{ "rating" : 5, "uuid" : "..."},
{ "rating" : 4, "uuid" : "..."},
{ "rating" : 4, "uuid" : "..."},
{ "rating" : 1, "uuid" : "..."},
]
},
"rating": 3.5
}
This is okay here since grouping by _id is the same as grouping on the whole document. So you can always add a final $project to return to similar state. But there are no wildcards here.
I just went through this whole song and dance as well and ended up having to re-add all my fields back. Not ideal!
So I just found this - much easier: I have a reviews array field, which has a rating property of 1 - 5
{
$addFields: { avg: { $avg: '$reviews.rating'}}
},
Related
I am currently trying to aggregate list of documents by filtering them with data taken with $lookup
Product.aggregate([
{
$lookup: {
from: "categories",
localField: "category",
foreignField: "_id",
as: "category",
},
},
{ $unwind: "$category" }])
I was hoping adding { $match: { "category.left": {$gte: 3}} }, would be able to get all of the products with categories that's left property is greater than specified, but so far I get nothing. what would be the solution for this?
category documents
{ "_id" : ObjectId("570557d4094a4514fc1291d6"), "left" : 1, "right" : "2" }
{ "_id" : ObjectId("570557d4094a4514fc1291d7"), "left" : 3, "right" : "8"}
{ "_id" : ObjectId("570557d4094a4514fc1291d8"), "left" : 4, "right" : "5"}
{ "_id" : ObjectId("570557d4094a4514fc1291d9"), "left" : 6, "right" : "7" }
product documents
{ "_id" : ObjectId("570557d4094a4514fc129120"), "category": ObjectId("570557d4094a4514fc1291d6") }
{ "_id" : ObjectId("570557d4094a4514fc129121"), "category": ObjectId("570557d4094a4514fc1291d7")}
{ "_id" : ObjectId("570557d4094a4514fc129122"), "category": ObjectId("570557d4094a4514fc1291d8")}
{ "_id" : ObjectId("570557d4094a4514fc129123"), "category": ObjectId("570557d4094a4514fc1291d9") }
I was expecting to get
{ "_id" : ObjectId("570557d4094a4514fc129121"), "category": ObjectId("570557d4094a4514fc1291d7")}
{ "_id" : ObjectId("570557d4094a4514fc129122"), "category": ObjectId("570557d4094a4514fc1291d8")}
{ "_id" : ObjectId("570557d4094a4514fc129123"), "category": ObjectId("570557d4094a4514fc1291d9") }
for my response
I am trying to modify query to get expected output.I am able to write the query but not getting the output as expected so that I may bind in the front end.
Actual output:-
{
"_id" : null,
"first" : 3571.0,
"second" : 24.0
}
Expected output:-
{ "_id" : null,
"opertion":edit,
"count" : 3571.0,
}
{ "_id" : null,
"opertion":read,
"count" : 24,
}
{ "_id" : null,
"opertion":update,
"count" : 9000,
}
Myquery:-
db.getCollection('blog').aggregate([
{ "$group": {
"_id": null,
"first": {
"$sum": {
"$cond": [{ "$in": ["$Operation", ["edit1", "edit2"]] }, 1, 0]
}
},
"second": {
"$sum": {
"$cond": [{ "$in": ["$Operation", ["read1", "read2"]] }, 1, 0]
}
}
},
},
])
if you have collection which is like as below:
[
{
"_id" : 1,
"operation" : "edit1" # some extra fields
},
{
"_id" : 2,
"operation" : "read1"
},
{
"_id" : 3,
"operation" : "update1"
}
]
by using $project and $cond you can rename the "read1", "read2" to read or updates to update, or edits to edit then by grouping on the new operation field you can get the count of each operation.
you can use this query:
db.aggregate([
{
"$project": {
"new_operation":
{
"$cond": [
{"$in":
["$Operation", ["edit1", "edit2"]]
}, "edit", {
"$cond": [
{"$in":
["$operation", ["read1", "read2"]]
}, "read", "update"]
}
]
}
}
},
{
"$group": {
"_id": "$new_operation",
"count": {"$sum": 1}
}
}
])
I am using MongoDB 3.6 for my project.
I have 2 collections "users" and "follow". I want to extract out details of user's followers and following (like an Instagram app).
users collection
{
"id" : "1",
"name" : "abc",
"age" : "26"
},
{
"id" : "2",
"name" : "xyz",
"age" : "22"
},
{
"id" : "3",
"name" : "qwe",
"age" : "23"
}
follow collection
{
"id" : "2",
"follow id" : "1"
},
{
"id" : "3",
"follow id" : "1"
},
{
"id" : "1",
"follow id" : "2"
},
{
"id" : "2",
"follow id" : "3"
},
{
"id" : "1",
"follow id" : "3"
}
Now i want following list of id 2 So id 2 is following id 1 and id 3
So, Output should be like this
{
"id" : "1",
"name" : "abc",
"age" : "26"
},
{
"id" : "3",
"name" : "qwe",
"age" : "23"
}
For that, I am using $lookup aggregation. But this is not giving the desired output which I want.
Here is my code -
Follow.aggregate([
{
$lookup:{
from:"users",
localField:"id",
foreignField:"id",
as:"fromItems"
}
},
{
$replaceRoot:{newRoot: {$mergeObjects: [ { $arrayElemAt: ["$fromItems", 0 ] }, "$$ROOT" ] } }
},
{ $project :
{
fromItems : 0
}
}
], callback)
For more understanding please refer the image
To get following list of id 2 you can use following query:
Follow.aggregate([
{
$match: { "id": "2" }
},
{
$lookup:{
from:"users",
localField:"follow id",
foreignField:"id",
as:"fromItems"
}
},
{
$replaceRoot:{newRoot: {$mergeObjects: [ { $arrayElemAt: ["$fromItems", 0 ] }, "$$ROOT" ] } }
},
{ $project :
{
id : "$follow id",
name: 1,
age: 1
}
}
])
So the point here is that you have a relation between id and follow id and after $lookup phase follow id becomes the new id since it's parent-child relation.
EDIT:
3.4 solution below
Follow.aggregate([
{
$match: { "id": "2" }
},
{
$lookup:{
from:"users",
localField:"follow id",
foreignField:"id",
as:"fromItems"
}
},
{
$project: {
id: "$follow id",
from: { $arrayElemAt: ["$fromItems", 0 ] }
}
},
{ $project :
{
id : 1,
name: "$from.name",
age: "$from.age"
}
}
])
I have a data in profile collection
[
{
name: "Harish",
gender: "Male",
caste: "Vokkaliga",
education: "B.E"
},
{
name: "Reshma",
gender: "Female",
caste: "Vokkaliga",
education: "B.E"
},
{
name: "Rangnath",
gender: "Male",
caste: "Lingayath",
education: "M.C.A"
},
{
name: "Lakshman",
gender: "Male",
caste: "Lingayath",
education: "B.Com"
},
{
name: "Reshma",
gender: "Female",
caste: "Lingayath",
education: "B.E"
}
]
here I need to calculate total Number of different gender, total number of different caste and total number of different education.
Expected o/p
{
gender: [{
name: "Male",
total: "3"
},
{
name: "Female",
total: "2"
}],
caste: [{
name: "Vokkaliga",
total: "2"
},
{
name: "Lingayath",
total: "3"
}],
education: [{
name: "B.E",
total: "3"
},
{
name: "M.C.A",
total: "1"
},
{
name: "B.Com",
total: "1"
}]
}
using mongodb aggregation how can I get the expected result.
There are different approaches depending on the version available, but they all essentially break down to transforming your document fields into separate documents in an "array", then "unwinding" that array with $unwind and doing successive $group stages in order to accumulate the output totals and arrays.
MongoDB 3.4.4 and above
Latest releases have special operators like $arrayToObject and $objectToArray which can make transfer to the initial "array" from the source document more dynamic than in earlier releases:
db.profile.aggregate([
{ "$project": {
"_id": 0,
"data": {
"$filter": {
"input": { "$objectToArray": "$$ROOT" },
"cond": { "$in": [ "$$this.k", ["gender","caste","education"] ] }
}
}
}},
{ "$unwind": "$data" },
{ "$group": {
"_id": "$data",
"total": { "$sum": 1 }
}},
{ "$group": {
"_id": "$_id.k",
"v": {
"$push": { "name": "$_id.v", "total": "$total" }
}
}},
{ "$group": {
"_id": null,
"data": { "$push": { "k": "$_id", "v": "$v" } }
}},
{ "$replaceRoot": {
"newRoot": {
"$arrayToObject": "$data"
}
}}
])
So using $objectToArray you make the initial document into an array of it's keys and values as "k" and "v" keys in the resulting array of objects. We apply $filter here in order to select by "key". Here using $in with a list of keys we want, but this could be more dynamically used as a list of keys to "exclude" where that was shorter. It's just using logical operators to evaluate the condition.
The end stage here uses $replaceRoot and since all our manipulation and "grouping" in between still keeps that "k" and "v" form, we then use $arrayToObject here to promote our "array of objects" in result to the "keys" of the top level document in output.
MongoDB 3.6 $mergeObjects
As an extra wrinkle here, MongoDB 3.6 includes $mergeObjects which can be used as an "accumulator" in a $group pipeline stage as well, thus replacing the $push and making the final $replaceRoot simply shifting the "data" key to the "root" of the returned document instead:
db.profile.aggregate([
{ "$project": {
"_id": 0,
"data": {
"$filter": {
"input": { "$objectToArray": "$$ROOT" },
"cond": { "$in": [ "$$this.k", ["gender","caste","education"] ] }
}
}
}},
{ "$unwind": "$data" },
{ "$group": { "_id": "$data", "total": { "$sum": 1 } }},
{ "$group": {
"_id": "$_id.k",
"v": {
"$push": { "name": "$_id.v", "total": "$total" }
}
}},
{ "$group": {
"_id": null,
"data": {
"$mergeObjects": {
"$arrayToObject": [
[{ "k": "$_id", "v": "$v" }]
]
}
}
}},
{ "$replaceRoot": { "newRoot": "$data" } }
])
This is not really that different to what is being demonstrated overall, but simply demonstrates how $mergeObjects can be used in this way and may be useful in cases where the grouping key was something different and we did not want that final "merge" to the root space of the object.
Note that the $arrayToObject is still needed to transform the "value" back into the name of the "key", but we just do it during the accumulation rather than after the grouping, since the new accumulation allows the "merge" of keys.
MongoDB 3.2
Taking it back a version or even if you have a MongoDB 3.4.x that is less than the 3.4.4 release, we can still use much of this but instead we deal with the creation of the array in a more static fashion, as well as handling the final "transform" on output differently due to the aggregation operators we don't have:
db.profile.aggregate([
{ "$project": {
"data": [
{ "k": "gender", "v": "$gender" },
{ "k": "caste", "v": "$caste" },
{ "k": "education", "v": "$education" }
]
}},
{ "$unwind": "$data" },
{ "$group": {
"_id": "$data",
"total": { "$sum": 1 }
}},
{ "$group": {
"_id": "$_id.k",
"v": {
"$push": { "name": "$_id.v", "total": "$total" }
}
}},
{ "$group": {
"_id": null,
"data": { "$push": { "k": "$_id", "v": "$v" } }
}},
/*
{ "$replaceRoot": {
"newRoot": {
"$arrayToObject": "$data"
}
}}
*/
]).map( d =>
d.data.map( e => ({ [e.k]: e.v }) )
.reduce((acc,curr) => Object.assign(acc,curr),{})
)
This is exactly the same thing, except instead of having a dynamic transform of the document into the array, we actually "explicitly" assign each array member with the same "k" and "v" notation. Really just keeping those key names for convention at this point since none of the aggregation operators here depend on that at all.
Also instead of using $replaceRoot, we just do exactly the same thing as what the previous pipeline stage implementation was doing there but in client code instead. All MongoDB drivers have some implementation of cursor.map() to enable "cursor transforms". Here with the shell we use the basic JavaScript functions of Array.map() and Array.reduce() to take that output and again promote the array content to being the keys of the top level document returned.
MongoDB 2.6
And falling back to MongoDB 2.6 to cover the versions in between, the only thing that changes here is the usage of $map and a $literal for input with the array declaration:
db.profile.aggregate([
{ "$project": {
"data": {
"$map": {
"input": { "$literal": ["gender","caste", "education"] },
"as": "k",
"in": {
"k": "$$k",
"v": {
"$cond": {
"if": { "$eq": [ "$$k", "gender" ] },
"then": "$gender",
"else": {
"$cond": {
"if": { "$eq": [ "$$k", "caste" ] },
"then": "$caste",
"else": "$education"
}
}
}
}
}
}
}
}},
{ "$unwind": "$data" },
{ "$group": {
"_id": "$data",
"total": { "$sum": 1 }
}},
{ "$group": {
"_id": "$_id.k",
"v": {
"$push": { "name": "$_id.v", "total": "$total" }
}
}},
{ "$group": {
"_id": null,
"data": { "$push": { "k": "$_id", "v": "$v" } }
}},
/*
{ "$replaceRoot": {
"newRoot": {
"$arrayToObject": "$data"
}
}}
*/
])
.map( d =>
d.data.map( e => ({ [e.k]: e.v }) )
.reduce((acc,curr) => Object.assign(acc,curr),{})
)
Since the basic idea here is to "iterate" a provided array of the field names, the actual assignment of values comes by "nesting" the $cond statements. For three possible outcomes this means only a single nesting in order to "branch" for each outcome.
Modern MongoDB from 3.4 have $switch which makes this branching simpler, yet this demonstrates the logic was always possible and the $cond operator has been around since the aggregation framework was introduced in MongoDB 2.2.
Again, the same transformation on the cursor result applies as there is nothing new there and most programming languages have the ability to do this for years, if not from inception.
Of course the basic process can even be done way back to MongoDB 2.2, but just applying the array creation and $unwind in a different way. But no-one should be running any MongoDB under 2.8 at this point in time, and official support even from 3.0 is even fast running out.
Output
For visualization, the output of all demonstrated pipelines here has the following form before the last "transform" is done:
/* 1 */
{
"_id" : null,
"data" : [
{
"k" : "gender",
"v" : [
{
"name" : "Male",
"total" : 3.0
},
{
"name" : "Female",
"total" : 2.0
}
]
},
{
"k" : "education",
"v" : [
{
"name" : "M.C.A",
"total" : 1.0
},
{
"name" : "B.E",
"total" : 3.0
},
{
"name" : "B.Com",
"total" : 1.0
}
]
},
{
"k" : "caste",
"v" : [
{
"name" : "Lingayath",
"total" : 3.0
},
{
"name" : "Vokkaliga",
"total" : 2.0
}
]
}
]
}
And then either by the $replaceRoot or the cursor transform as demonstrated the result becomes:
/* 1 */
{
"gender" : [
{
"name" : "Male",
"total" : 3.0
},
{
"name" : "Female",
"total" : 2.0
}
],
"education" : [
{
"name" : "M.C.A",
"total" : 1.0
},
{
"name" : "B.E",
"total" : 3.0
},
{
"name" : "B.Com",
"total" : 1.0
}
],
"caste" : [
{
"name" : "Lingayath",
"total" : 3.0
},
{
"name" : "Vokkaliga",
"total" : 2.0
}
]
}
So whilst we can put some new and fancy operators into the aggregation pipeline where we have those available, the most common use case is in these "end of pipeline transforms" in which case we may as well simply do the same transformation on each document in the cursor results returned instead.
I have the following document in my collection.
{
"_id" : ObjectId("55961a28bffebcb8058b4570"),
"title" : "BackOffice 2",
"cts" : NumberLong(1435900456),
"todo_items" : [
{
"id" : "55961a42bffebcb7058b4570",
"task_desc" : "test 1",
"completed_by" : "557fccb5bffebcf7048b457c",
"completed_date" : NumberLong(1436161096)
},
{
"id" : "559639afbffebcc7098b45a6",
"task_desc" : "test 2",
"completed_by" : "557fccb5bffebcf7048b457c",
"completed_date" : NumberLong(1435911809)
},
{
"id" : "559a22f5bffebcb0048b476c",
"task_desc" : "test 3",
}
],
"uts" : NumberLong(1436164853)
}
I need an aggregation query to perform following, if there is field "completed_by" and "completed_date" and if there is a value which is not null push in to the "completed" array field, otherwise push them into the "incomplete" field.
Following is a sample result I want.
{
"_id" : ObjectId("55961a28bffebcb8058b4570"),
"completed" : [
{
"id":"557fccb5bffebcf7048b457c",
"title":"test 1",
"completed_by" : "557fccb5bffebcf7048b457c",
"completed_date" : NumberLong(1436161096)
},
{
"id":"557fccb5bffebcf7048b457c",
"title":"test 1",
"completed_by" : "557fccb5bffebcf7048b457c",
"completed_date" : NumberLong(1436161096)
}
],
"incomplete":[
{
"id" : "559a22f5bffebcb0048b476c",
"title" : "test 3"
}
]
}
As long as your "array" items have "distinct" identifiers ( which they have ) there are a couple of approaches to this;
Firstly, without actually "aggregating accross documents":
db.collection.aggregate([
{ "$project": {
"title": 1,
"cts": 1,
"completed": { "$setDifference": [
{ "$map": {
"input": "$todo_items",
"as": "i",
"in": {
"$cond": [
"$$i.completed_date",
"$$i",
false
]
}
}},
[false]
]},
"incomplete": { "$setDifference": [
{ "$map": {
"input": "$todo_items",
"as": "i",
"in": {
"$cond": [
"$$i.completed_date",
false,
"$$i"
]
}
}},
[false]
]}
}}
])
That requires that you at least have MongoDB 2.6 available on the server in order to use the required $map and $setDifference operators. It's pretty fast considering that all the work is done in a single $project stage.
The alternative, which you should only use when "aggregating across documents", is available to all versions supporting the aggregation framework post MongoDB 2.2:
db.collection.aggregate([
{ "$unwind": "$todo_items" },
{ "$group": {
"_id": "$_id",
"title": { "$first": "$title" },
"cts": { "$first": "$cts" },
"completed": {
"$addToSet": {
"$cond": [
"$todo_items.completed_date",
"$todo_items",
null
]
}
},
"incomplete": {
"$addToSet": {
"$cond": [
"$todo_items.completed_date",
null,
"$todo_items",
]
}
}
}},
{ "$unwind": "$completed" },
{ "$match": { "completed": { "$ne": null } } },
{ "$group": {
"_id": "$_id",
"title": { "$first": "$title" },
"cts": { "$first": "$cts" },
"completed": { "$push": "$completed" },
"incomplete": { "$first": "$incomplete" }
}}
{ "$unwind": "$incomplete" },
{ "$match": { "incomplete": { "$ne": null } } },
{ "$group": {
"_id": "$_id",
"title": { "$first": "$title" },
"cts": { "$first": "$cts" },
"completed": { "$first": "$completed" },
"incomplete": { "$push": "$incomplete" }
}}
])
Which isn't entirely all there since you need to cater for conditions where an array may end up empty. But that is not the real lesson here since MongoDB 2.6 is already a couple of years in circulation.
In aggregation, you cannot really exclude the "null/false" results, but you can "filter" them.
Also, unless you are actually "aggregating accross documents" as mentioned already, then the second form with $unwind to process the arrays comes with a "lot" of overhead. So you really should be altering the array contents in your client code as each document is read.
Can you please check the below :
db.collection.aggregate([
{$unwind : "$todo_items"},
{$group: {_id : "$_id" , completed : {{$cond :
{
if : { $and : [ {"todo_items.completed_by" : {$exists: true, $ne : null }},
{"todo_items.completed_date" : {$exists : true, $ne : null}} ] } },
then : {$push : {"old_completed" : "$todo_items"}},
else: {$push : {"old_incompleted" : "$todo_items"}}
} } } },
{$project: {_id : "$_id", completed : "$completed.old_completed" ,
incompleted : "$completed.old_incompleted"}}
]);