For each student in a collection, I have an array of absences. I want to summarize the data by displaying the number of absences for each day of the week.
Given the following input:
{
"_id" : 9373,
"absences" : [
{
"code" : "U",
"date" : ISODate("2021-01-17T00:00:00.000+0000"),
"full_day" : false,
"remote" : false,
"dayNumber" : 1,
"dayName" : "Sunday"
}
]
}
{
"_id" : 9406,
"absences" : [
{
"code" : "E",
"date" : ISODate("2020-12-09T00:00:00.000+0000"),
"full_day" : false,
"remote" : false,
"dayNumber" : 4,
"dayName" : "Wednesday"
},
{
"code" : "U",
"date" : ISODate("2021-05-27T00:00:00.000+0000"),
"full_day" : false,
"remote" : false,
"dayNumber" : 5,
"dayName" : "Thursday"
}
]
}
How can I achieve the following output:
[
{
"_id": 9373,
"days": [
{
"dayNumber": 1,
"dayName": "Sunday",
"count": 1
}
]
},
{
"_id": 9406,
"days": [
{
"dayNumber": 4,
"dayName": "Wednesday",
"count": 1
},
{
"dayNumber": 5,
"dayName": "Thursday",
"count": 1
}
]
}
]
I've pushed all the required fields to this stage of the pipeline. I'm just not clear how to roll up the data in the nested absences array.
$unwind deconstruct absences array
$group by _id and dayNumber, and get count of grouped documents
$group by _id and reconstruct days array
db.collection.aggregate([
{ $unwind: "$absences" },
{
$group: {
_id: {
_id: "$_id",
dayNumber: "$absences.dayNumber"
},
dayName: { $first: "$absences.dayName" },
count: { $sum: 1 }
}
},
{
$group: {
_id: "$_id._id",
days: {
$push: {
dayName: "$dayName",
dayNumber: "$_id.dayNumber",
count: "$count"
}
}
}
}
])
Playground
Related
//8. isbn numbers of books that sold at least X copies (you decide the value for X).
Book example
{
isbn: "0001",
title: "Book1",
pages: NumberInt("150"),
price: NumberDecimal("321.2"),
copies: NumberInt("3"),
language: "english",
author: ["Author1"],
category: ["Space Opera"],
genre: ["Genre-1", "Genre-2"],
character: ["Character-1", "Character-2"],
},
Order example
{
orderNo: "3",
customerNo: "0003",
date: {
day: NumberInt("25"),
month: NumberInt("02"),
year: NumberInt("2021"),
},
orderLine: [
{
isbn: "0006",
price: NumberDecimal("341.0"),
amount: NumberInt("2"),
},
{
isbn: "0007",
price: NumberDecimal("170.5"),
amount: NumberInt("1"),
},
],
},
My try
I believe I have a mistake inside the pipeline at the group stage. For now I need at least to have isbn along with the copies sold in one object.
db.books.aggregate([ // editing this
{ $match : {} },
{
$lookup :
{
from : "orders",
pipeline : [
{
$group :
{
_id: null,
amount_total : { $sum : "$orderLine.amount" }
}
},
{ $project : { _id : 0, amount_total : 1} }
],
as : "amount"
}
},
{ $project : { _id : 0, isbn : 1, amount : 1} }
])
No idea why all are 0's, I was expecting at least some different numbers.
{
"isbn": "0001",
"amount": [
{
"amount_total": 0
}
]
},
{
"isbn": "0002",
"amount": [
{
"amount_total": 0
}
]
},
{
"isbn": "0003",
"amount": [
{
"amount_total": 0
}
]
},// and so on
Apparently, this does what I wanted.
db.books.aggregate([
{
$lookup: {
from: "orders",
let: { isbn: "$isbn" }, // Pass this variable to pipeline for Joining condition.
pipeline: [
{ $unwind: "$orderLine" },
{
$match: {
// Join condition.
$expr: { $eq: ["$orderLine.isbn", "$$isbn"] }
}
},
{
$project: { _id: 0 , orderNo : 1, "orderLine.amount": 1}
}
],
as: "amount"
}
}, { $project : { _id : 0, isbn : 1, amount_total : { $sum : "$amount.orderLine.amount" } } }
])
In your query $lookup is performing a join operation without any condition instead try this query:
db.books.aggregate([
{
$lookup: {
from: "orders",
let: { isbn: "$isbn" },
pipeline: [
{ $unwind: "$orderLine" },
{
$match: {
$expr: { $eq: ["$orderLine.isbn", "$$isbn"] }
}
}
],
as: "amount"
}
},
{
$project: {
_id: 0,
isbn: 1,
amount_total: { $sum: "$amount.orderLine.amount" }
}
}
]);
Test data:
books collection:
/* 1 createdAt:3/12/2021, 10:41:13 AM*/
{
"_id" : ObjectId("604af7f14b5860176c2254b7"),
"isbn" : "0001",
"title" : "Book1"
},
/* 2 createdAt:3/12/2021, 10:41:13 AM*/
{
"_id" : ObjectId("604af7f14b5860176c2254b8"),
"isbn" : "0002",
"title" : "Book2"
}
orders collection:
/* 1 createdAt:3/12/2021, 11:10:51 AM*/
{
"_id" : ObjectId("604afee34b5860176c2254ce"),
"orderNo" : "1",
"customerNo" : "0001",
"orderLine" : [
{
"isbn" : "0001",
"price" : 341,
"amount" : 2
},
{
"isbn" : "0002",
"price" : 170.5,
"amount" : 1
},
{
"isbn" : "0003",
"price" : 190.5,
"amount" : 3
}
]
},
/* 2 createdAt:3/12/2021, 11:10:51 AM*/
{
"_id" : ObjectId("604afee34b5860176c2254cf"),
"orderNo" : "3",
"customerNo" : "0003",
"orderLine" : [
{
"isbn" : "0001",
"price" : 341,
"amount" : 2
},
{
"isbn" : "0002",
"price" : 170.5,
"amount" : 1
},
{
"isbn" : "0003",
"price" : 190.5,
"amount" : 3
}
]
}
Output:
/* 1 */
{
"isbn" : "0001",
"amount_total" : 4
},
/* 2 */
{
"isbn" : "0002",
"amount_total" : 2
}
The $sum inside $group stage will sum root and grouped fields but here orderLine field is an array, you need to sum that array of numbers before applying $sum, it means nested $sum operation,
{
$group: {
_id: null,
amount_total: {
$sum: {
$sum: "$orderLine.amount"
}
}
}
}
Playground
Try the final solution,
$match isbn array in orderLine.isbn using $in condition
$filter to iterate look of orderLine array, and match isbn, it will return filtered documents
$let declare a orders variable to hold above filtered documents of orderLine, sum the amount from filtered array using $sum
$project to show required fields, and get total sum of amount_total array
db.books.aggregate([
{
$lookup: {
from: "orders",
let: { isbn: "$isbn" },
pipeline: [
{ $match: { $expr: { $in: ["$$isbn", "$orderLine.isbn"] } } },
{
$project: {
_id: 0,
amount_total: {
$let: {
vars: {
orders: {
$filter: {
input: "$orderLine",
cond: { $eq: ["$$this.isbn", "$$isbn"] }
}
}
},
in: { $sum: "$$orders.amount" }
}
}
}
}
],
as: "amount"
}
},
{
$project: {
_id: 0,
isbn: 1,
amount_total: { $sum: "$amount.amount_total" }
}
}
])
Playground
I have a dataset in mongodb collection named visitorsSession like
{ip : 192.2.1.1,country : 'US', type : 'Visitors',date : '2019-12-15T00:00:00.359Z'},
{ip : 192.3.1.8,country : 'UK', type : 'Visitors',date : '2019-12-15T00:00:00.359Z'},
{ip : 192.5.1.4,country : 'UK', type : 'Visitors',date : '2019-12-15T00:00:00.359Z'},
{ip : 192.8.1.7,country : 'US', type : 'Visitors',date : '2019-12-15T00:00:00.359Z'},
{ip : 192.1.1.3,country : 'US', type : 'Visitors',date : '2019-12-15T00:00:00.359Z'}
I am using this mongodb aggregation
[{$match: {
nsp : "/hrm.sbtjapan.com",
creationDate : {
$gte: "2019-12-15T00:00:00.359Z",
$lte: "2019-12-20T23:00:00.359Z"
},
type : "Visitors"
}}, {$group: {
_id : "$country",
totalSessions : {
$sum: 1
}
}}, {$project: {
_id : 0,
country : "$_id",
totalSessions : 1
}}, {$sort: {
country: -1
}}]
using above aggregation i am getting results like this
[{country : 'US',totalSessions : 3},{country : 'UK',totalSessions : 2}]
But i also total visitors also along with result like totalVisitors : 5
How can i do this in mongodb aggregation ?
You can use $facet aggregation stage to calculate total visitors as well as visitors by country in a single pass:
db.visitorsSession.aggregate( [
{
$match: {
nsp : "/hrm.sbtjapan.com",
creationDate : {
$gte: "2019-12-15T00:00:00.359Z",
$lte: "2019-12-20T23:00:00.359Z"
},
type : "Visitors"
}
},
{
$facet: {
totalVisitors: [
{
$count: "count"
}
],
countrySessions: [
{
$group: {
_id : "$country",
sessions : { $sum: 1 }
}
},
{
$project: {
country: "$_id",
_id: 0,
sessions: 1
}
}
],
}
},
{
$addFields: {
totalVisitors: { $arrayElemAt: [ "$totalVisitors.count" , 0 ] },
}
}
] )
The output:
{
"totalVisitors" : 5,
"countrySessions" : [
{
"sessions" : 2,
"country" : "UK"
},
{
"sessions" : 3,
"country" : "US"
}
]
}
You could be better off with two queries to do this.
To save the two db round trips following aggregation can be used which IMO is kinda verbose (and might be little expensive if documents are very large) to just count the documents.
Idea: Is to have a $group at the top to count documents and preserve the original documents using $push and $$ROOT. And then before other matches/filter ops $unwind the created array of original docs.
db.collection.aggregate([
{
$group: {
_id: null,
docsCount: {
$sum: 1
},
originals: {
$push: "$$ROOT"
}
}
},
{
$unwind: "$originals"
},
{ $match: "..." }, //and other stages on `originals` which contains the source documents
{
$group: {
_id: "$originals.country",
totalSessions: {
$sum: 1
},
totalVisitors: {
$first: "$docsCount"
}
}
}
]);
Sample O/P: Playground Link
[
{
"_id": "UK",
"totalSessions": 2,
"totalVisitors": 5
},
{
"_id": "US",
"totalSessions": 3,
"totalVisitors": 5
}
]
My MongoDB database have a structure
{
"_id" : ObjectId("5c1ccc20fc0f60769227d455"),
"type" : 0,
"id" : "hwJyzAHyfjXUlrGhblT7txWd",
"userowner" : 1.0,
"campid" : "9548",
"date" : 1545391136,
"useragent" : "mozilla/5.0 (windows nt 10.0; win64; x64; rv:65.0) gecko/20100101 firefox/65.0",
"domain" : "",
"referer" : "",
"country" : "en",
"language" : "en-US",
"languages" : [
"en-US",
"en"
],
"screenres" : [
"1920*1080"
],
"avscreenres" : [
"1080*1858"
],
"webgl" : "angle (nvidia geforce gtx 1060 6gb direct3d11 vs_5_0 ps_5_0)",
"hash" : 123,
"timezone" : -180,
"result" : true,
"resultreason" : "learning",
"remoteip" : "0.0.0.0"
}
Every a document have a vield "result" with a bool value.
I make aggregation selection:
db.getCollection('clicks').aggregate([
{ $match: {userowner: 1, date:{$gte: 0, $lte: 9545392055}} },
{ $group : {_id : "$campid",
number: {$sum: 1}}}
])
and get a Result:
/* 1 */
{
"_id" : "4587",
"number" : 2.0
}
/* 2 */
{
"_id" : "9548",
"number" : 1346.0
}
How can count the amount of value "true" and "false" in a field "result" and get a result like this:
/* 1 */
{
"_id" : "4587",
"number" : 2.0,
"passed":100,
"blocked":120
}
/* 2 */
{
"_id" : "9548",
"number" : 1346.0,
"passed":100,
"blocked":120
}
I hope this works as per your requirement.
db.getCollection('clicks').aggregate(
[
{
$match: {
userowner: 1, date: {
$gte: 0, $lte: 9545392055
}
}
},
{
$group: {
_id: "$campid", passed: {
$sum: {
$cond:
[
{ $eq: ["$result", true] },
1, 0
]
}
},
blocked: {
$sum: {
$cond:
[
{
$eq: ["$result", false]
}
, 1, 0]
}
},
number: { $sum: 1 }
}
},
{
$project: {
_id: 0,
campid: "$_id",
number: 1,
passed: 1,
blocked: 1
}
}
])
Output:-
{
"passed" : 3,
"blocked" : 2,
"number" : 5,
"campid" : "4587"
}
{
"passed" : 2,
"blocked" : 1,
"number" : 3,
"campid" : "9548"
}
Refer $group, $cond, and $eq for more info.
With MongoDb 3.6 and newer, you can leverage the use of $arrayToObject operator within a $replaceRoot pipeline to get the desired result.
You would need to group the documents intially by the campid and the result field, aggregate the sum and pass the results to yet another group pipeline stage. This group stage will prepare the documents in a way that $arrayToObject operator will give you the desired object by creating a key-value array using $push.
The result from this is then fed to the $replaceRoot pipeline to bring the passed and blocked fields to the root of the document.
The following aggregate pipeline describes the above:
db.getCollection('clicks').aggregate([
{ "$match": { "userowner": 1, "date": { "$gte": 0, "$lte": 9545392055 } } },
{ "$group": {
"_id": {
"campid": "$campid",
"result": { "$cond": [ "$result", "passed", "blocked" ] }
},
"count": { "$sum": 1 }
} },
{ "$group": {
"_id": "$_id.campid",
"number": { "$sum": "$count" },
"counts": {
"$push": {
"k": "$_id.result",
"v": "$count"
}
}
} },
{ "$replaceRoot": {
"newRoot": {
"$mergeObjects": [
{ "$arrayToObject": "$counts" },
"$$ROOT"
]
}
} },
{ "$project": { "counts": 0 } }
])
This question already has an answer here:
Promote subfields to top level in projection without listing all keys
(1 answer)
Closed 4 years ago.
Currently I am running this query to calculate averages and to return the data in a specific format:
db.metrics.aggregate([
{
$unwind:"$data"
},
{
$group:{
_id:"$data.configName",
avg:{
$avg:"$data.linesCount"
},
data:{
$last:"$data"
},
date:{
$last:"$date"
}
}
}
]).pretty()
On a collection which contains objects in this format:
{
"_id" : {
"date" : 1526569274000,
}
"date" : "20150220",
"data" : [
{
"configName" : "aaa",
"linesCount" : 500,
"insertedLinesCount" : 658,
}
],
"applicationName" : "loader"
}
Which returns this result:
{
"_id" : "aaa",
"avg" : 500,
"data" : {
"configName" : "aaa",
"linesCount" : 500,
"insertedLinesCount" : 658,
"succeeded" : true
},
"date" : "20150220"
}
The details are correct but I'd like to change the format. Is there any way to take what is in the data object and return it so that the final result is a list of 1-1 mappings, like so:
{
"_id" : "aaa",
"avg" : 500,
"configName" : "aaa",
"linesCount" : 500,
"insertedLinesCount" : 658,
"fileFormat" : "",
"date" : "20150220"
}
You need to use the $project stage at the end of the result
db.collection.aggregate([
{
$unwind: "$data"
},
{
$group: {
_id: "$data.configName",
avg: {
$avg: "$data.linesCount"
},
data: {
$last: "$data"
},
date: {
$last: "$date"
}
}
},
{
$project: {
configName: "$data.configName",
insertedLinesCount: "$data.insertedLinesCount",
linesCount: "$data.linesCount",
succeeded: "$data.succeeded",
_id: 1,
avg: 1,
date: 1
}
}
])
above query gives you the following result... check it here
[
{
"_id": "aaa",
"avg": 500,
"configName": "aaa",
"date": "20150220",
"insertedLinesCount": 658,
"linesCount": 500,
"succeeded": true
}
]
Add a $replaceRoot stage after $group
{
$replaceRoot: {
newRoot: {
_id: "$_id",
avg: "$avg",
configName: "$data.configName"
...
}
}
}
I want to get data to each month. in my table data is stored like this:-
"patient" : [
{
"status" : 'arrived',
start_time: '2017-08-17T09:17:00.000Z
},
{
"status" : 'arraived',
start_time: '2017-08-16T07:17:00.000Z
},
{
"status" : 'arrived',
start_time: '2017-07-12T09:17:00.000Z
},
{
"status" : 'arraived',
start_time: '2017-07-05T08:10:00.000Z
},
{
"status" : 'arrived',
start_time: '2017-06-02T09:17:00.000Z
},
{
"status" : 'arraived',
start_time: '2017-05-05T08:16:00.000Z
}
]
etc,
and I want to sum of patient of each month (jan to des), like this :-
{
"month" : 8,
"count" : 2
}and like this month 1 to 12
I assume, patient array is associated with a customer and the date is stored in mongo ISO format.
So, the actual document would look like :
{
name: "stackOverflow",
"patient" : [
{
"status" : 'arrived',
"start_time": ISODate("2017-08-17T09:17:00.000Z")
},
{
"status" : 'arraived',
"start_time": ISODate("2017-08-16T07:17:00.000Z")
},
{
"status" : 'arrived',
"start_time": ISODate("2017-07-12T09:17:00.000Z")
},
{
"status" : 'arraived',
"start_time": ISODate("2017-07-05T08:10:00.000Z")
},
{
"status" : 'arrived',
"start_time": ISODate("2017-06-02T09:17:00.000Z")
},
{
"status" : 'arraived',
"start_time": ISODate("2017-05-05T08:16:00.000Z")
}
]
}
here is a sample query which you can try -
db.test.aggregate([
{$unwind: "$patient"},
{ $group: {
_id: {name: "$name", month: {$month: "$patient.start_time"}},
count: { $sum: 1}
}},
{$group: {
_id: "$_id.name",
patient: {$push: {month: "$_id.month", count: "$count"}}
}}
])
Sample output:
{
"_id" : "stackOverflow",
"patient" : [
{
"month" : 5,
"count" : 1
},
{
"month" : 6,
"count" : 1
},
{
"month" : 7,
"count" : 2
},
{
"month" : 8,
"count" : 2
}
]
}
You can change query according to your use-case. hope this will help you!
This is my code:-
db.appointments.aggregate( [
{
$project:
{
"patient_id": 1,
"start_time": 1,
"status": 1
}
},
{
$match: {
'start_time' : { $gte: startdate.toISOString() },
'status': { $eq: 'arrived' }
} ,
},
{ $group: {
_id: {id: "$_id", start_time: {$month: "$appointments.start_time"}},
count: { $sum: 1}
}}
])
When I used this :-
{ $group: {
_id: {id: "$_id", start_time: {$month: "$start_time"}},
count: { $sum: 1}
}
}
its showing error message:-
{"name":"MongoError","message":"can't convert from BSON type missing to Date","ok":0,"errmsg":"can't convert from BSON type missing to Date","code":16006,"codeName":"Location16006"}
And when I comment this its showing this :-
Out Put here:-
:[{"count":{"_id":"595b6f95ab43ec1f6c92b898","patient_id":"595649904dbe9525c0e036ef","start_time":"2017-07-04T10:35:00.000Z","status":"arrived"}},
{"count":{"_id":"595dff870960d425d4f14633","patient_id":"5956478b4dbe9525c0e036ea","start_time":"2017-03-08T09:14:00.000Z","status":"arrived"}},{"count":{"_id":"595dffaa0960d425d4f14634","patient_id":"595649904dbe9525c0e036ef","start_time":"2017-03-17T09:15:00.000Z","status":"arrived"}},{"count":{"_id":"595dffcf0960d425d4f14635","patient_id":"595648394dbe9525c0e036ec","start_time":"2017-06-08T09:15:00.000Z","status":"arrived"}},{"count":{"_id":"595dfffb0960d425d4f14636","patient_id":"5956478b4dbe9525c0e036ea","start_time":"2017-06-20T09:16:00.000Z","status":"arrived"}},{"count":{"_id":"595e00160960d425d4f14637","patient_id":"5959ea7f80388b19e0b57817","start_time":"2017-08-17T09:17:00.000Z","status":"arrived"}}]}
const group = {
$group: {
_id: { month: { $month: "$createdAt" } },
count: { $sum: 1 },
},
};
const groups = {
$group: {
_id: null,
patient: { $push: { month: '$_id.month', count: '$count' } },
},
};
return db.Patient.aggregate([group, groups]);