I have the following stage in my MongoDB aggregation pipeline that returns the qty and sum of sales, which works fine:
{
$lookup: {
from: 'sales',
let: { part: '$_id' },
pipeline: [
{ $match: { $and: [{ $expr: { $eq: ['$partner', '$$part'] } }] } },
{ $group: { _id: null, qty: { $sum: 1 }, soldFor: { $sum: '$soldFor' } } },
{ $project: { _id: 0, qty: 1, soldFor: 1 } }],
as: 'sales'}},
{ $unwind: { path: '$sales', preserveNullAndEmptyArrays: true } },
{ $project: { _id: 1, sales: 1 }
}
However, if there are no sales, then the $project projection returns an empty sales object, but what I'd really like is it to return a completed object, but with 0 - like this:
{
sales: {
qty: 0,
soldFor: 0
}
}
You can use $cond operator here
{
"$project": {
"_id": 1,
"sales": {
"$cond": [
{ "$eq": [{ "$size": "$sales" }, 0] },
{
"sales": {
"qty": 0,
"soldFor": 0
}
},
"$sales"
]
}
}
}
Related
I am running the following aggregation pipeline:
const agg = [
{
'$match': {
'aaa': 'bbb'
}
}, {
'$group': {
'_id': '',
'total': {
'$sum': '$num'
}
}
}
];
My problem is, when $match matches nothing, the pipeline returns 0 documents. How do I get the pipeline to always return 1 document?
In MongoDB version 6.0 you can do it like this one:
db.collection.aggregate([
{ $match: { aaa: 'bbb' } },
{
$group: {
_id: null,
total: { $sum: "$num" }
}
},
{
$densify: {
field: "total",
range: { step: 1, bounds: [0, 0] }
}
},
{ $set: { _id: { $cond: [{ $eq: [{ $type: "$_id" }, "missing"] }, MaxKey, "$_id"] } } },
{ $sort: { _id: 1 } },
{ $limit: 1 }
])
In version < 6.0 you can try this one:
db.collection.aggregate([
{
$facet: {
data: [
{ $match: { aaa: 'bbb' } },
{ $group: { _id: null, total: { $sum: "$num" } } }
],
default: [
{ $limit: 1 },
{ $group: { _id: null, total: { $sum: 0 } } },
{ $set: { _id: MaxKey } }
]
}
},
{ $replaceWith: { $mergeObjects: [{ $first: "$default" }, { $first: "$data" }] } },
])
Or this one:
db.collection.aggregate([
{ $match: { aaa: 'bbb' } },
{ $group: { _id: null, total: { $sum: "$num" } } },
{
$unionWith: {
coll: "collection",
pipeline: [
{ $limit: 1 },
{ $set: { _id: MaxKey, total: 0 } },
{ $project: { _id: 1, total: 1 } }
]
}
},
{ $sort: { _id: 1 } },
{ $limit: 1 }
])
I've created an aggregate query but for some reason it doesn't seem to work for custom fields created in the aggregation pipeline.
return this.repository.mongo().aggregate([
{
$match: { q1_avg: { $regex: baseQuery['value'], $options: 'i' } }, // NOT WORKING
},
{
$group: {
_id: '$product_sku',
id: { $first: "$_id" },
product_name: { $first: '$product_name' },
product_category: { $first: '$product_category' },
product_sku: { $first: '$product_sku' },
q1_cnt: { $sum: 1 },
q1_votes: { $push: "$final_rating" }
},
},
{
$facet: {
pagination: [ { $count: 'total' } ],
data: [
{
$project: {
_id: 1,
id: 1,
product_name: 1,
product_category: 1,
product_sku: 1,
q1_cnt: 1,
q1_votes: {
$filter: {
input: '$q1_votes',
as: 'item',
cond: { $ne: ['$$item', null] }
}
},
},
},
{
$set: {
q1_avg: { $round: [ { $avg: '$q1_votes' }, 2 ] },
}
},
{ $unset: ['q1_votes'] },
{ $skip: skip },
{ $limit: limit },
{ $sort: sortList }
]
}
},
{ $unwind : "$pagination" },
]).next();
q1_avg value is an integer and as far as I know, regex only works with strings. Could that be the reason
I need help to count the elements of an array when it is in another array.
My command, when I tried to select the second array is,
db.artysci.aggregate([
{
$project: {
_id:0,
nazwa: 1,
nazwisko: 1,
numberOfSongs: { "album": {$size: "$utwor"}}
}
}
] )
Grid:
db.artysci.insert({
imie: 'Laurie',
nazwisko: 'Adkins',
rok_debiutu: 2006,
kraj_pochodzenia: ['Wielka Brytania'],
gatunek: 'neo soul',
album: [{
tytul:"19",
rok_edycji:2007,
gatunek: 'pop',
typ_nosnika: 'CD',
utwor: [{
numer: 1,
tytul_utworu: 'Daydreamer',
dlugosc_trwania: 3.41
},
{
numer: 2,
tytul_utworu: 'Best for Last',
dlugosc_trwania: 4.19
},
{
numer: 3,
tytul_utworu: 'Chasing Pavements',
dlugosc_trwania: 3.31
}
]
}]
})
Output when counting by $size:"$album",
{
"nazwisko" : "Adkins",
"numberOfSongs" : {
"album" : NumberInt(3)
}
}
How can I count elements of an array in an array by $size?
You can achieve this using Map and then summing it up. It works..
db.artysci.aggregate({
"$project": {
_id: 0,
nazwa: 1,
nazwisko: 1,
"numberOfAlbums": { "$size": { $ifNull: ["$album", []] } },
"numberOfSongs": {
"$sum": {
"$map": {
"input": "$album",
"in": { "$size": { $ifNull: ["$$this.utwor", []] } }
}
}
}
}
})
#Kacper,
Here is the soultion for your second question.
Yes, you can achieve it in either way, using the above method or using unwind and do the average..
Lets see an example using unwind:
Without divide/second:
db.notifications.aggregate([
{ $unwind: "$album" },
{ $unwind: "$album.utwor" },
{
$group: {
_id: "$_id",
avgDuration: { $avg: "$album.utwor.dlugosc_trwania" }
}
},
]);
With divide/second:
db.notifications.aggregate([
{ $unwind: "$album" },
{ $unwind: "$album.utwor" },
{
$group: {
_id: "$_id",
avgDuration: { $avg: { $divide: ["$album.utwor.dlugosc_trwania", 60] } }
}
},
]);
You can use $unwind and $group to get the counts.
db.collection.aggregate([
{
$unwind: "$album"
},
{
$unwind: "$album.utwor"
},
{
$group: {
_id: 0,
total: {
$sum: 1
}
}
}
])
Play
If you need more information, add it to your question.
Given documents such as
{
_id: 'abcd',
userId: '12345',
activities: [
{ status: 'login', timestamp: '10000001' },
{ status: 'logout', timestamp: '10000002' },
{ status: 'login', timestamp: '10000003' },
{ status: 'logout', timestamp: '10000004' },
]
}
I am trying to create a pipeline such as all users that have their latest login/logout activities recorded between two timestamps will be returned. For example, if the two timestamp values are between 10000002 and 10000003, the expected document should be
{
_id: 'abcd',
userId: '12345',
login: '10000003',
logout: '10000002'
}
Of if the two timestamp values are between -1 and 10000001, the expected document should be :
{
_id: 'abcd',
userId: '12345',
login: '10000001',
logout: null
}
Etc.
I know it has to do with aggregations, and I need to $unwind, etc., but I'm not sure about the rest, namely evaluating two fields from the same document array
You can try below aggregation:
db.col.aggregate([
{
$unwind: "$activities"
},
{
$match: {
$and: [
{ "activities.timestamp": { $gte: "10000001" } },
{ "activities.timestamp": { $lte: "10000002" } }
]
}
},
{
$sort: {
"activities.timestamp": -1
}
},
{
$group: {
_id: "$_id",
userId: { $first: "$userId" },
activities: { $push: "$activities" }
}
},
{
$addFields: {
login: { $arrayElemAt: [ { $filter: { input: "$activities", as: "a", cond: { $eq: [ "$$a.status", "login" ] } } } , 0 ] },
logout: { $arrayElemAt: [ { $filter: { input: "$activities", as: "a", cond: { $eq: [ "$$a.status", "logout" ] } } } , 0 ] }
}
},
{
$project: {
_id: 1,
userId: 1,
login: { $ifNull: [ "$login.timestamp", null ] },
logout: { $ifNull: [ "$logout.timestamp", null ] }
}
}
])
We need to use $unwind + $sort + $group to make sure that our activities will be sorted by timestamp. After $unwind you can use $match to apply filtering condition. Then you can use $filter with $arrayElemAt to get first (latest) value of filtered array. In the last $project you can explicitly use $ifNull (otherwise JSON key will be skipped if there's no value)
You can use below aggregation
Instead of $unwind use $lte and $gte with the $fitler aggregation.
db.collection.aggregate([
{ "$project": {
"userId": 1,
"login": {
"$max": {
"$filter": {
"input": "$activities",
"cond": {
"$and": [
{ "$gte": ["$$this.timestamp", "10000001"] },
{ "$lte": ["$$this.timestamp", "10000004"] },
{ "$lte": ["$$this.status", "login"] }
]
}
}
}
},
"logout": {
"$max": {
"$filter": {
"input": "$activities",
"cond": {
"$and": [
{ "$gte": ["$$this.timestamp", "10000001"] },
{ "$lte": ["$$this.timestamp", "10000004"] },
{ "$lte": ["$$this.status", "logout"] }
]
}
}
}
}
}}
])
I have a collection with documents similar to the following format:
{
departure:{name: "abe"},
arrival:{name: "tom"}
},
{
departure:{name: "bob"},
arrival:{name: "abe"}
}
And to get output like so:
{
name: "abe",
departureCount: 1,
arrivalCount: 1
},
{
name: "bob",
departureCount: 1,
arrivalCount: 0
},
{
name: "tom",
departureCount: 0,
arrivalCount: 1
}
I'm able to get the counts individually by doing a query for the specific data like so:
db.sched.aggregate([
{
"$group":{
_id: "$departure.name",
departureCount: {$sum: 1}
}
}
])
But I haven't figured out how to merge the arrival and departure name into one document along with counts for both. Any suggestions on how to accomplish this?
You should use a $map to split your doc into 2, then $unwind and $group..
[
{
$project: {
dep: '$departure.name',
arr: '$arrival.name'
}
},
{
$project: {
f: {
$map: {
input: {
$literal: ['dep', 'arr']
},
as: 'el',
in : {
type: '$$el',
name: {
$cond: [{
$eq: ['$$el', 'dep']
}, '$dep', '$arr']
}
}
}
}
}
},
{
$unwind: '$f'
}, {
$group: {
_id: {
'name': '$f.name'
},
departureCount: {
$sum: {
$cond: [{
$eq: ['$f.type', 'dep']
}, 1, 0]
}
},
arrivalCount: {
$sum: {
$cond: [{
$eq: ['$f.type', 'arr']
}, 1, 0]
}
}
}
}, {
$project: {
_id: 0,
name: '$_id.name',
departureCount: 1,
arrivalCount: 1
}
}
]