Please, I need a help for aggregate the status (2 and 3) count from year in a MongoDb nested document.
My Json:
[
{
"_id":1,
"name":"aaa",
"calendars":[
{
"year":2012,
"status":2
},
{
"year":2013,
"status":1
},
{
"year":2014,
"status":3
}
]
},
{
"_id":2,
"name":"bbb",
"calendars":[
{
"year":2012,
"status":1
},
{
"year":2013,
"status":1
},
{
"year":2014,
"status":2
}
]
}
]
This is my mongodb code:
db.mycol.aggregate([{"$match": {"calendars.status": {"$in": [2, 3]}}}, {"$unwind": "$calendars"},
{"$group": {_id: {"year": "$calendars.year"},
total: {"$sum": 1}
}},
{"$project": {
"year": "$_id.year",
"total": "$total", "_id": 0}},
])
And I need the result:
year total
2012 1
2013 0
2014 2
Thanks
I will first unwind the array object and match accordingly,
db.test.aggregate([
{
"$unwind": "$calendars"
},
{
"$match": {
"calendars.status": {
"$in": [
2,
3
]
}
}
},
{
"$group": {
_id: {
"year": "$calendars.year"
},
total: {
"$sum": 1
}
}
},
{
"$project": {
"year": "$_id.year",
"total": "$total",
"_id": 0
}
},
])
Related
I'm new in mongoDB.
This is one example of record from collection:
{
supplier: 1,
type: "sale",
items: [
{
"_id": ObjectId("60ee82dd2131c5032342070f"),
"itemBuySum": 10
},
{
"_id": ObjectId("60ee82dd2131c50323420710"),
"itemBuySum": 10,
},
{
"_id": ObjectId("60ee82dd2131c50323420713"),
"itemBuySum": 10
},
{
"_id": ObjectId("60ee82dd2131c50323420714"),
"itemBuySum": 20
}
]
}
I need to group by TYPE field and get the SUM. This is output I need:
{
supplier: 1,
sales: 90,
returns: 170
}
please check Mongo playground for better understand. Thank you!
$match - Filter documents.
$group - Group by type and add item into data array which leads to the result like:
[
[/* data 1 */],
[/* data 2 */]
]
$project - Decorate output document.
3.1. First $reduce is used to flatten the nested array to a single array (from Result (2)) via $concatArrays.
3.2. Second $reduce is used to aggregate $sum the itemBuySum.
db.collection.aggregate({
$match: {
supplier: 1
},
},
{
"$group": {
"_id": "$type",
"supplier": {
$first: "$supplier"
},
"data": {
"$push": "$items"
}
}
},
{
"$project": {
_id: 0,
"supplier": "$supplier",
"type": "$_id",
"returns": {
"$reduce": {
"input": {
"$reduce": {
input: "$data",
initialValue: [],
in: {
"$concatArrays": [
"$$value",
"$$this"
]
}
}
},
"initialValue": 0,
"in": {
$sum: [
"$$value",
"$$this.itemBuySum"
]
}
}
}
}
})
Sample Mongo Playground
db.collection.aggregate([
{
$match: {
supplier: 1
},
},
{
"$group": {
"_id": "$ID",
"supplier": {
"$first": "$supplier"
},
"sale": {
"$sum": {
"$cond": {
"if": {
"$eq": [
"$type",
"sale"
]
},
"then": {
"$sum": "$items.itemBuySum"
},
"else": {
"$sum": 0
}
}
}
},
"returns": {
"$sum": {
"$sum": {
"$cond": {
"if": {
"$eq": [
"$type",
"return"
]
},
"then": {
"$sum": "$items.itemBuySum"
},
"else": {
"$sum": 0
}
}
}
}
}
}
},
{
"$project": {
_id: 0,
supplier: 1,
sale: 1,
returns: 1
}
}
])
I have a user collection:
[
{"_id": 1,"name": "John", "age": 25, "valid_user": true}
{"_id": 2, "name": "Bob", "age": 40, "valid_user": false}
{"_id": 3, "name": "Jacob","age": 27,"valid_user": null}
{"_id": 4, "name": "Amelia","age": 29,"valid_user": true}
]
I run a '$facet' stage on this collection. Checkout this MongoPlayground.
I want to talk about the first output from the facet stage. The following is the response currently:
{
"user_by_valid_status": [
{
"_id": false,
"count": 1
},
{
"_id": true,
"count": 2
},
{
"_id": null,
"count": 1
}
]
}
However, I want to restructure the output in this way:
"analytics": {
"invalid_user": {
"_id": false
"count": 1
},
"valid_user": {
"_id": true
"count": 2
},
"user_with_unknown_status": {
"_id": null
"count": 1
}
}
The problem with using a '$project' stage along with 'arrayElemAt' is that the order may not be definite for me to associate an index with an attribute like 'valid_users' or others. Also, it gets further complicated because unlike the sample documents that I have shared, my collection may not always contain all the three categories of users.
Is there some way I can do this?
You can use $switch conditional operator,
$project to show value part in v with _id and count field as object, k to put $switch condition
db.collection.aggregate([
{
"$facet": {
"user_by_valid_status": [
{
"$group": {
"_id": "$valid_user",
"count": { "$sum": 1 }
}
},
{
$project: {
_id: 0,
v: { _id: "$_id", count: "$count" },
k: {
$switch: {
branches: [
{ case: { $eq: ["$_id", null] }, then: "user_with_unknown_status" },
{ case: { $eq: ["$_id", false] }, then: "invalid_user" },
{ case: { $eq: ["$_id", true] }, then: "valid_user" }
]
}
}
}
}
],
"users_above_30": [{ "$match": { "age": { "$gt": 30 } } }]
}
},
$project stage in root, convert user_by_valid_status array to object using $arrayToObject
{
$project: {
analytics: { $arrayToObject: "$user_by_valid_status" },
users_above_30: 1
}
}
])
Playground
I have collection in my db as,
[
{
"groupName" : "testName",
"participants" : [
{
"participantEmail" : "test#test.com",
"lastClearedDate" : 12223213123
},
{
"participantEmail" : "test2#test.com",
"lastClearedDate" : 1234343243423
}
],
"messages" : [
{
"message":"sdasdasdasdasdasd",
"time":22312312312,
"sender":"test#test.com"
},
{
"message":"gfdfvd dssdfdsfs",
"time":2231231237789,
"sender":"test#test.com"
}
]
}
]
This is a collection of group which contains all the participants and messages in that group.
The time field inside the message is Timestamp.
I want get all the messages inside a group which are posted after the given date and grouped by date.
I wrote the following code,
ChatGroup.aggregate([
{ $match: { group_name: groupName } },
{ $unwind: "$messages" },
{ $match: { "messages.time": { $gte: messagesFrom } } },
{
$project: {
_id: 0,
y: {
$year: {
$add: [new Date(0), { $multiply: [1000, "$messages.time"] }]
}
},
m: {
$month: {
$add: [new Date(0), { $multiply: [1000, "$messages.time"] }]
}
},
d: {
$dayOfMonth: {
$add: [new Date(0), { $multiply: [1000, "$messages.time"] }]
}
}
}
},
{
$group: {
_id: {
year: "$y",
month: "$m",
day: "$d"
},
messages: { $push: "$messages" },
count: { $sum: 1 }
}
}
]).then(
group => {
console.log("length of messages", group);
resolve(group);
},
err => {
console.log(err);
}
);
});
and I getting the following output,
[
{
"_id": {
"year": 50694,
"month": 9,
"day": 5
},
"messages": [],
"count": 3
},
{
"_id": {
"year": 50694,
"month": 8,
"day": 27
},
"messages": [],
"count": 1
},
{
"_id": {
"year": 50694,
"month": 8,
"day": 26
},
"messages": [],
"count": 10
}
]
I am not getting the messages but the count is correct.
Also the time which is displayed in the result is incorrect e.g. year, date and month.
Mongo version is 3.2.
I referred the groupby and push documentation from mongodb along with other stackoverflow questions on mongo group by.
What am I doing wrong?
Your timestamp is already in seconds. So, you don't need to convert them to millisecond by multiplying with 1000.
So your final query should be something like this
ChatGroup.aggregate([
{ "$match": {
"group_name": groupName,
"messages.time": { "$gte": messagesFrom }
}},
{ "$unwind": "$messages" },
{ "$match": { "messages.time": { "$gte": messagesFrom }}},
{ "$group": {
"_id": {
"year": { "$year": { "$add": [new Date(0), "$messages.time"] }},
"month": { "$month": { "$add": [new Date(0), "$messages.time"] }},
"day": { "$dayOfMonth": { "$add": [new Date(0), "$messages.time"] }}
},
"messages": { "$push": "$messages" },
"count": { "$sum": 1 }
}}
])
Add messages in $project
{
$project: {
_id: 0,
messages : 1,
.........
},
}
Collection exists as below:
[
{"currentLocation": "Chennai", "baseLocation": "Bengaluru"},
{"currentLocation": "Chennai", "baseLocation": "Bengaluru"},
{"currentLocation": "Delhi", "baseLocation": "Bengaluru"},
{"currentLocation": "Chennai", "baseLocation": "Chennai"}
]
Expected Output:
[
{"city": "Chennai", "currentLocationCount": 3, "baseLocationCount": 1},
{"city": "Bengaluru", "currentLocationCount": 0, "baseLocationCount": 3},
{"city": "Delhi", "currentLocationCount": 1, "baseLocationCount": 0}
]
What I have tried is:
db.getCollection('users').aggregate([{
$group: {
"_id": "$baselocation",
baseLocationCount: {
$sum: 1
}
},
}, {
$project: {
"_id": 0,
"city": "$_id",
"baseLocationCount": 1
}
}])
Got result as:
[
{"city": "Chennai", "baseLocationCount": 1},
{"city": "Bengaluru", "baseLocationCount": "3"}
]
I'm not familiar with mongo, so any help?
MongoDB Version - 3.4
Neil Lunn and myself had a lovely argument over this topic the other day which you can read all about here: Group by day with Multiple Date Fields.
Here are two solutions to your precise problem.
The first one uses the $facet stage. Bear in mind, though, that it may not be suitable for large collections because $facet produces a single (potentially huge) document that might be bigger than the current MongoDB document size limit of 16MB (which only applies to the result document and wouldn't be a problem during pipeline processing anyway):
collection.aggregate(
{
$facet:
{
"current":
[
{
$group:
{
"_id": "$currentLocation",
"currentLocationCount": { $sum: 1 }
}
}
],
"base":
[
{
$group:
{
"_id": "$baseLocation",
"baseLocationCount": { $sum: 1 }
}
}
]
}
},
{ $project: { "result": { $setUnion: [ "$current", "$base" ] } } }, // merge results into new array
{ $unwind: "$result" }, // unwind array into individual documents
{ $replaceRoot: { newRoot: "$result" } }, // get rid of the additional field level
{ $group: { "_id": "$_id", "currentLocationCount": { $sum: "$currentLocationCount" }, "baseLocationCount": { $sum: "$baseLocationCount" } } }, // group into final result)
{ $project: { "_id": 0, "city": "$_id", "currentLocationCount": 1, "baseLocationCount": 1 } } // group into final result
)
The second one works based on the $map stage instead:
collection.aggregate(
{
"$project": {
"city": {
"$map": {
"input": [ "current", "base" ],
"as": "type",
"in": {
"type": "$$type",
"name": {
"$cond": {
"if": { "$eq": [ "$$type", "current" ] },
"then": "$currentLocation",
"else": "$baseLocation"
}
}
}
}
}
}
},
{ "$unwind": "$city" },
{
"$group": {
"_id": "$city.name",
"currentLocationCount": {
"$sum": {
"$cond": {
"if": { "$eq": [ "$city.type", "current" ] },
"then": 1,
"else": 0
}
}
},
"baseLocationCount": {
"$sum": {
"$cond": {
"if": { "$eq": [ "$city.type", "base" ] },
"then": 1,
"else": 0
}
}
}
}
}
)
I'm creating a MongoDB aggregation pipeline and I'm stuck at this stage:
$group: {
_id: {checkType: "$_id.checkType", resultCode: "$_id.resultCode"},
count: { $sum: "$count" },
ctv: { $sum: "$ctv" },
perc:{$multiply:[{$divide:["$ctv","$count"]},100]},
weight: { $divide: [ "$ctv", "$count"] },
details: { $push: "$$ROOT" }
}
It gives the error "The $multiply accumulator is a unary operator". Similarly if I remove the line with $multiply I get "The $divide accumulator is a unary operator" on the subsequent line. I cannot find a description for this error on the Net. What's wrong in my sintax?
The arithmetic operators cannot be used as $group accumulators. Move them to another $project pipeline stage as:
db.collection.aggregate([
{ "$group": {
"_id": { "checkType": "$_id.checkType", "resultCode": "$_id.resultCode" },
"count": { "$sum": "$count" },
"ctv": { "$sum": "$ctv" },
"details": { "$push": "$$ROOT" }
} },
{ "$project": {
"count": 1,
"details": 1,
"ctv": 1,
"perc": { "$multiply": [ { "$divide": ["$ctv","$count"] }, 100 ] },
"weight": { "$divide": ["$ctv", "$count"] },
} }
])
or
if using MongoDB 3.4 and above, use $addFields instead of $project
db.collection.aggregate([
{ "$group": {
"_id": { "checkType": "$_id.checkType", "resultCode": "$_id.resultCode" },
"count": { "$sum": "$count" },
"ctv": { "$sum": "$ctv" },
"details": { "$push": "$$ROOT" }
} },
{ "$addFields": {
"perc": { "$multiply": [ { "$divide": ["$ctv","$count"] }, 100 ] },
"weight": { "$divide": ["$ctv", "$count"] },
} }
])