I have documents like this:
{
"_id" : ObjectId("5b3ced158735f1196d73a743"),
"cid" : 1,
"foo" : [
{
"k" : "sport",
"v" : "climbing"
},
{
"k" : "sport",
"v" : "soccer"
},
{
"k" : "sport",
"v" : "soccer"
}
]
}
This Query just return the documents which contains a soccer field.
db.coll.find({foo:{$elemMatch:{ v: "soccer"}} }, {"foo.$" : 1,cid:1})
returns:
{ "_id" : ObjectId("5b3ced158735f1196d73a743"), "cid" : 1, "node" : [ { "k" : "sport", "v" : "climbing" } ] }
But I want to know, how many soccer-Elements are in each returned document. How can I count them?
db.coll.aggregate(
// Pipeline
[
// Stage 1
{
$match: {
foo: {
$elemMatch: {
v: 'soccer'
}
}
}
},
// Stage 2
{
$unwind: {
path: '$foo'
}
},
// Stage 3
{
$project: {
cid: 1,
count: {
$cond: {
if: {
$eq: ['$foo.v', 'soccer']
},
then: {
$sum: 1
},
else: 0
}
}
}
},
// Stage 4
{
$group: {
_id: '$cid',
total_count: {
$sum: '$count'
}
}
}
]
);
You can use below query to $filter and $size the filtered array to count no of matching occurrences.
db.coll.aggregate([
{"$project":{
"cid":1,
"count":{
"$size":{
"$filter":{
"input":"$foo",
"cond":{"$eq":["$$this.v","soccer"]
}
}
}
}
}}
])
Related
I'm new to aggregation queries in Mongo and been really struggling trying to produce the output I want. I have the following aggregation query:
db.events.aggregate([
{ $match: { requestState: "APPROVED" } },
{ $unwind: { path: "$payload.description" } },
{ $group: { _id: { instr: "$payload.description", bu: "$createdByUser", count: { $sum: 1 } } } }
]);
that returns the following results:
{ "_id" : { "instr" : "ABC-123", "bu" : "BU2", "count" : 1 } }
{ "_id" : { "instr" : "ABC-123", "bu" : "BU1", "count" : 1 } }
{ "_id" : { "instr" : "DEF-456", "bu" : "BU1", "count" : 1 } }
How can I amend the aggregation query so that there are only 2 documents returned instead of 3? With the two "ABC-123" results combined into a single result with a new array of counts with the "bu" and "count" fields i.e.
{ "_id" : { "instr" : "ABC-123", "counts": [ { "bu" : "BU1", "count" : 1 }, { "bu" : "BU2", "count" : 1 } ] } }
Many thanks
You can add another stage to only $group by _id.instr and another stage to $project to your desired output shape
db.events.aggregate([
{
$match: { requestState: "APPROVED" }
},
{
$unwind: { path: "$payload.description" }
},
{
$group: {
_id: { instr: "$payload.description", bu: "$createdByUser", count: { $sum: 1 } }
}
},
{
$group: {
_id: { instr: "$_id.instr" },
counts: { $push: { bu: "$_id.bu", count: "$_id.count" } }
}
},
{
$project: {
_id: { instr: "$_id.instr", counts: "$counts" }
}
}
]);
How do we find keys which do not exist in collection.
Given an input list of keys ['3321', '2121', '5647'] , i want to return those that do not exist in the collection :
{ "_id" : { "$oid" : "5e2993b61886a22f400ea319" }, "scrip" : "5647" }
{ "_id" : { "$oid" : "5e2993b61886a22f400ea31a" }, "scrip" : "3553" }
So the expected output is ['3321', '2121']
This aggregation gets the desired output (works with MongoDB version 3.4 or later):
INPUT_ARRAY = ['3321', '2121', '5647']
db.test.aggregate( [
{
$match: {
scrip: {
$in: INPUT_ARRAY
}
}
},
{
$group: {
_id: null,
matches: { $push: "$scrip" }
}
},
{
$project: {
scrips_not_exist: { $setDifference: [ INPUT_ARRAY, "$matches" ] },
_id: 0
}
}
] )
The output:
{ "scrips_not_exist" : [ "3321", "2121" ] }
{
_id: ObjectId("5dbdacc28cffef0b94580dbd"),
"comments" : [
{
"_id" : ObjectId("5dbdacc78cffef0b94580dbf"),
"replies" : [
{
"_id" : ObjectId("5dbdacd78cffef0b94580dc0")
},
]
},
]
}
How to count the number of element in comments and sum with number of relies
My approach is do 2 query like this:
1. total elements of replies
db.posts.aggregate([
{$match: {_id:ObjectId("5dbdacc28cffef0b94580dbd")}},
{ $unwind: "$comments",},
{$project:{total:{$size:"$comments.replies"} , _id: 0} }
])
2. count total elements of comments
db.posts.aggregate([
{$match: {_id:ObjectId("5dbdacc28cffef0b94580dbd")}},
{$project:{total:{$size:"$comments.replies"} , _id: 0} }
])
Then sum up both, do we have any better solution to write the query like return the sum of of total element comments + replies
You can use $reduce and $concatArrays to "merge" an inner "array of arrays" into a single list and measure the $size of that. Then simply $add the two results together:
db.posts.aggregate([
{ "$match": { _id:ObjectId("5dbdacc28cffef0b94580dbd") } },
{ "$addFields": {
"totalBoth": {
"$add": [
{ "$size": "$comments" },
{ "$size": {
"$reduce": {
"input": "$comments.replies",
"initialValue": [],
"in": {
"$concatArrays": [ "$$value", "$$this" ]
}
}
}}
]
}
}}
])
Noting that an "array of arrays" is the effect of an expression like $comments.replies, so hence the operation to make these into a single array where you can measure all elements.
Try using the $unwind to flatten the list you get from the $project before using $count.
This is another way of getting the result.
Input documents:
{ "_id" : 1, "array1" : [ { "array2" : [ { id: "This is a test!"}, { id: "test1" } ] }, { "array2" : [ { id: "This is 2222!"}, { id: "test 222" }, { id: "222222" } ] } ] }
{ "_id" : 2, "array1" : [ { "array2" : [ { id: "aaaa" }, { id: "bbbb" } ] } ] }
The query:
db.arrsizes2.aggregate( [
{ $facet: {
array1Sizes: [
{ $project: { array1Size: { $size: "$array1" } } }
],
array2Sizes: [
{ $unwind: "$array1" },
{ $project: { array2Size: { $size: "$array1.array2" } } },
],
} },
{ $project: { result: { $concatArrays: [ "$array1Sizes", "$array2Sizes" ] } } },
{ $unwind: "$result" },
{ $group: { _id: "$result._id", total1: { $sum: "$result.array1Size" }, total2: { $sum: "$result.array2Size" } } },
{ $addFields: { total: { $add: [ "$total1", "$total2" ] } } },
] )
The output:
{ "_id" : 2, "total1" : 1, "total2" : 2, "total" : 3 }
{ "_id" : 1, "total1" : 2, "total2" : 5, "total" : 7 }
I need to a group by on x field and get the max value of other fields. Yes, using $max we can get max repetitive value. But, I also need to get count $max value in percent/count too. In other words, how many times this $max value exist in that group. Kindly help.
example:
db.getCollection("test").aggregate(
[
{ "$match" : { "doc_id" : 1.0 } },
{ "$group" : {
"_id" : { "name" : "$name" },
"total" : { "$sum" : "$amount" },
"l1_max" : { "$max" : "$l1" }
}
},
]
);
Here, I am getting l1_max = 'Computer' . But, I need it as 'Computer - (30%) Total 4/12'
Updated: 20/10/2019
#mickl : Thanks for the answer.
The field l1 is actually a referenced field. In normal find/project or mongoose populate(), it helps to get fields from other collection. Example:
if l1 is of type ObjectId then,
l1: {
_id, "4343434343sdsdsY",
name: "IT"
}
So l1.name will fetch name field from another collection in project/populate function.
I executed following code:
db.getCollection("test").aggregate(
[
{ "$match" : { "doc_id" : 1.0 } },
{ "$group" : {
"_id" : { "name" : "$name" },
"total" : { "$sum" : "$amount" },
"count": { '$sum': 1 },
"l1_max" : { "$max" : "$l1" },
"l1_values": { $push: "$l1" }
}
},
{
$project: {
_id: 1,
total: 1,
l1 : {"_id": "$l1_max", "count": "$count", "percent": { $divide: [ { $size: { $filter: { input: "$l1_values", cond: { $eq: [ "$$this", "$l1_max" ] } } } },"$count"]}}
}
}
]
);
Answer is like below: But I also need referenced name field too.
{
"_id" : {
"name" : "xzy"
},
"total" : 35.0,
"l1" : {
"_id" : "4343920239201W",
"name" : "IT", // **MISSING**
"count" : 4.0,
"percent" : 0.25
}
}
Hope I was clear this time.
You need to capture all l1 values in your group and the calculate the percent using $divide, $filter and $size:
db.getCollection("test").aggregate(
[
{ "$match" : { "doc_id" : 1.0 } },
{ "$group" : {
"_id" : { "name" : "$name" },
"total" : { "$sum" : "$amount" },
"l1_max" : { "$max" : "$l1" },
"l1_values": { $push: "$l1" }
}
},
{
$project: {
_id: 1,
total: 1,
l1_max: 1,
l1_perc: {
$divide: [
{ $size: { $filter: { input: "$l1_values", cond: { $eq: [ "$$this", "$l1_max" ] } } } },
{ $size: "$l1_values" }
]
}
}
}
]
);
Mongo Playground
I have highly nested mongodb set of objects and i want to sort subofdocuments according to the result of sum their votes for example :
{
"_id":17846384es,
"company_name":"company1",
"products":[
{
"product_id":"123785",
"product_name":"product1",
"user_votes":[
{
"user_id":1,
"vote":1
},
{
"user_id":2,
"vote":2
}
]
},
{
"product_id":"98765",
"product_name":"product2",
"user_votes":[
{
"user_id":5,
"vote":3
},
{
"user_id":3,
"vote":3
}
]
}
]
}
i want to sort as descending products according to the result of sum their votes
the expected output is
{
"_id":17846384es,
"company_name":"company1",
"products":[
{
"product_id":"98765",
"product_name":"product2",
"user_votes":[
{
"user_id":5,
"vote":3
},
{
"user_id":3,
"vote":3
}
]
"votes":8
},
{
"product_id":"123785",
"product_name":"product1",
"user_votes":[
{
"user_id":1,
"vote":1
},
{
"user_id":2,
"vote":2
}
],
"votes":3
}
]
}
Any Idea ?
The following pipeline
db.products.aggregate([
{ $unwind: "$products" },
{
$project: {
company_name: 1,
products: 1,
totalVotes: {
$sum: "$products.user_votes.vote"
}
}
},
{ $sort: { totalVotes: -1 } },
{
$group: {
_id: "$_id",
company_name: { $first: "$company_name" },
products: { $push: "$products" }
}
}
])
would output
{
"_id" : "17846384es",
"company_name" : "company1",
"products" : [
{
"product_id" : "98765",
"product_name" : "product2",
"user_votes" : [
{
"user_id" : 5,
"vote" : 3
},
{
"user_id" : 3,
"vote" : 3
}
]
},
{
"product_id" : "123785",
"product_name" : "product1",
"user_votes" : [
{
"user_id" : 1,
"vote" : 1
},
{
"user_id" : 2,
"vote" : 2
}
]
}
]
}
In case you want to keep the sum of the votes at the product level as shown in your expected output simply modify the $project stage as follows
...
{
$project: {
company_name: 1,
products: {
product_id: 1,
product_name: 1,
user_votes: 1,
votes: { $sum: "$products.user_votes.vote" }
}
}
}
...