I have data in worksheets collection like below:
/* 1 */
{
"_id" : ObjectId("5c21d780f82aa31334ab6506"),
"isBilling" : true,
"hours" : 6,
"userId" : ObjectId("5c1f38a1d7537d1444738467"),
"projectId": ObjectId("5c1f38a1d7537d1444731234");
}
/* 2 */
{
"_id" : ObjectId("5c21d780f82aa31334ab6507"),
"isBilling" : true,
"hours" : 4,
"userId" : ObjectId("5c1f38a1d7537d1444738493"),
"projectId": ObjectId("5c1f38a1d7537d1444734567");
}
/* 3 */
{
"_id" : ObjectId("5c21e10fae07cc1204a5b647"),
"isBilling" : false,
"hours" : 8,
"userId" : ObjectId("5c1f388fd7537d1444738492"),
"projectId": ObjectId("5c1f38a1d7537d1444731234");
}
I am using below aggregate query to get total count of fields:
Worksheet.aggregate([
{
$match: conditions
},
{
"$group": {
"_id": null,
"billingHours": {
"$sum": {
"$cond": [{ "$eq": ["$isBilling", true] }, "$hours", 0]
}
},
"fixContract": {
"$sum": {
"$cond": [{ "$eq": ["$isBilling", true] }, 0, "$hours"]
}
}
}
}
])
Now i want the sum of unique projectId field. It above case it is 2. I tried it by applying two $group in above implemented query. But it is not working. I want to get the result like below:
[
{
"_id": null,
"billingHours": 0,
"fixContract": 8,
"totalProjects": 2
}
]
Use $addToSet accumulator and then $size operator to count the number of unique projectId
Worksheet.aggregate([
{ $match: conditions },
{ "$group": {
"_id": null,
"billingHours": {
"$sum": {
"$cond": [{ "$eq": ["$isBilling", true] }, "$hours", 0]
}
},
"fixContract": {
"$sum": {
"$cond": [{ "$eq": ["$isBilling", true] }, 0, "$hours"]
}
},
"projectIds": { "$addToSet": "$projectId" }
}},
{ "$addFields": { "projectIds": { "$size": "$projectIds" }}}
])
Related
I have some documents in a collection which looks like this
{
"_id" : "5a2e50b32d43ba00010041e5",
account_id:"23232323"
status:"accepted",
keyname:"java"
},
{
"_id" : "5a2e54332d43ba00010041e5",
account_id:"2323233"
status:"pending",
keyname:"java"
},
{
"_id" : "5a2e54332d43ba00010041e5",
account_id:"23232sdsd3"
status:"pending",
keyname:"Nodejs"
}
I need to get the counts of the pending and accepted status for each keyname for a particular account_id
eg: should give a result like this.
{
keyname:"java",
pending:10,
accepted:10
}
This is the code that I have tried out
db.getCollection("programs").aggregate([
{ "$match": { "account_id": "1" } },
{ "$group": { "_id": "$keyname", "count": { "$sum": 1 } } },
{ "$match": { "_id": { "$ne": null } } }
])
which gives a result like this
{
"_id" : "java",
"count" : 3.0
},
{
"_id" : "nodejs",
"count" : 3.0
},
{
"_id" : "C#",
"count" : 3.0
}
You can use below aggregation
db.collection.aggregate([
{ "$match": { "account_id": "1" } },
{ "$group": {
"_id": "$keyname",
"accepted": {
"$sum": {
"$cond": [
{ "$eq": ["$status", "accepted"] },
0,
1
]
}
},
"pending": {
"$sum": {
"$cond": [
{ "$eq": ["$status", "pending"] },
0,
1
]
}
}
}}
])
I have a mongo db collection like below,
{
"id": ObjectId("132456"),
reading :[
{
"weight" : {
"measurement" : 82.0,
"unit" : "kg"
}
}
],
"date" : ISODate("2018-09-12T11:45:08.174Z")
},
{
"id": ObjectId("132457"),
reading :[
{
"weight" : {
"measurement" : 80.0,
"unit" : "kg"
}
}
],
"date" : ISODate("2018-09-12T10:45:08.174Z")
},
{
"id": ObjectId("132458"),
reading :[
{
"weight" : {
"measurement" : 85.0,
"unit" : "kg"
}
}
],
"date" : ISODate("2018-09-11T09:45:08.174Z")
}
I need a mongo db query that will give me the current weight and the weight difference between the current and next record.
Example output below,
{
"id": ObjectId("132456"),
"currentWeight": 75.0,
"weightDifference": 2.0,
"date" : ISODate("2018-09-12T11:45:08.174Z")
},
{
"id": ObjectId("132457"),
"currentWeight": 80.0,
"weightDifference": -5.0,
"date" : ISODate("2018-09-12T10:45:08.174Z")
}
I was not able to get the weight from next document to subtract the weight from current document.
Thanks in advance for your help
My try for the above problem,
db.measurementCollection.aggregate([
{
$match : { "date" : { $gte : new ISODate("2018-09-01T00:00:00.000Z") , $lte : new ISODate("2018-09-12T23:59:59.000Z") } }
},
{
$project : { "date" : 1 ,
"currentWeight" : {$arrayElemAt: [ "$reading.weight.measurement", 0 ]}
},
{ $sort: {"date":-1} },
{
$addFields : {
"weigtDifference" :
{
{
$limit: 2
},
{
$group: {
_id: null,
'count1': {$first: '$currentWeight'},
'count2': {$last: '$currentWeight'}
}
},
{
$subtract: ['$count1', '$count2']
}
}
}
}
])
You can try below aggregation but I will not recommend you to use this with the large data set.
db.collection.aggregate([
{ "$match": {
"date" : {
"$gte": new ISODate("2018-09-01T00:00:00.000Z"),
"$lte": new ISODate("2018-09-12T23:59:59.000Z")
}
}},
{ "$unwind": "$reading" },
{ "$sort": { "date": -1 }},
{ "$group": { "_id": null, "data": { "$push": "$$ROOT" }}},
{ "$project": {
"data": {
"$filter": {
"input": {
"$map": {
"input": { "$range": [0, { "$size": "$data" }] },
"as": "tt",
"in": {
"$let": {
"vars": {
"first": { "$arrayElemAt": ["$data", "$$tt"] },
"second": { "$arrayElemAt": ["$data", { "$add": ["$$tt", 1] }] }
},
"in": {
"currentWeight": "$$first.reading.weight.measurement",
"weightDifference": { "$subtract": ["$$second.reading.weight.measurement", "$$first.reading.weight.measurement"] },
"_id": "$$first._id",
"date": "$$first.date"
}
}
}
}
},
"cond": { "$ne": ["$$this.weightDifference", null] }
}
}
}
},
{ "$unwind": "$data" },
{ "$replaceRoot": { "newRoot": "$data" }}
])
I have a 3 Collections Assignments, Status, Assignee.
Assignments Fields : [_id, status, Assignee]
Assignee and Status Fields : [_id, name].
There can be many assignments associated with various Status and Assignee collections(linked via _id field), There is no nesting or complex data.
I need a query for all assignments ids where Assignees are the row, Status are the Columns, there combined cell is the count with Total counts at the end.
To help you visualize, I am attaching below image. I am new to complex Mongo DB Aggregate framework, kindly guide me to achieve query.
Note: Data in Status and Assignee collection will be dynamic. Nothing is predetermined in the Query. So, the Rows and Columns are going to grow dynamically in future, If the query is given pagination, then it would be of great help. I cannot write a query with hard coded status names like 'pending', 'completed' etc. As data shall grow and existing data may change like 'pending task', 'completed work'.
Below is my query
db.getCollection('Assignments').aggregate([
{
"$group": {
"_id": {
"assignee": "$assignee",
"statusId": "$statusId"
},
"statusCount": { "$sum": 1 }
}
},
{
"$group": {
"_id": "$_id.assignee",
"statuses": {
"$push": {
"statusId": "$_id.statusId",
"count": "$statusCount"
},
},
"count": { "$sum": "$statusCount" }
}
},
]);
Below is the output format:
{
"_id" : "John",
"statuses" : {
"statusId" : "Pending",
"count" : 3.0
},
"count" : 3.0
}
{
"_id" : "Katrina",
"statuses" : [{
"statusId" : "Pending",
"count" : 1.0
},
{
"statusId" : "Completed",
"count" : 1.0
},
{
"statusId" : "Assigned",
"count" : 1.0
}],
"count" : 3.0
}
{
"_id" : "Collins",
"statuses" : {
"statusId" : "Pending",
"count" : 4.0
},
"count" : 4.0
}
Expected Output is:
{
"_id" : "Katrina",
"Pending" : 1.0,
"Completed" : 1.0,
"Assigned" : 1.0,
"totalCount" : 3.0
}
Any Idea on how to many various statusId for different assignee as keys and not values in single document.
You need another $group stage after $unwind to count number of status based on statusId string value:
{
"$group": {
"_id": "$_id",
"Pending" : {
"$sum": {
"$cond": [
{ "$eq": [
"$statuses.statusId",
"Pending"
]},
"$statuses.count",
0
]
}
},
"Completed" : {
"$sum": {
"$cond": [
{ "$eq": [
"$statuses.statusId",
"Completed"
]},
"$statuses.count",
0
]
}
},
"Assigned" : {
"$sum": {
"$cond": [
{ "$eq": [
"$statuses.statusId",
"Assigned"
]},
"$statuses.count",
0
]
}
},
"totalCount": { "$sum": 1 }
}
}
The final aggregate command:
db.getCollection('Assignments').aggregate([
{
"$group": {
"_id": {
"assignee": "$assignee",
"statusId": "$statusId"
},
"statusCount": { "$sum": 1 }
}
},
{
"$group": {
"_id": "$_id.assignee",
"statuses": {
"$push": {
"statusId": "$_id.statusId",
"count": "$statusCount"
},
},
"count": { "$sum": "$statusCount" }
}
},
{ "$unwind": "$statuses" },
{
"$group": {
"_id": "$_id",
"Pending" : {
"$sum": {
"$cond": [
{ "$eq": [
"$statuses.statusId",
"Pending"
]},
"$statuses.count",
0
]
}
},
"Completed" : {
"$sum": {
"$cond": [
{ "$eq": [
"$statuses.statusId",
"Completed"
]},
"$statuses.count",
0
]
}
},
"Assigned" : {
"$sum": {
"$cond": [
{ "$eq": [
"$statuses.statusId",
"Assigned"
]},
"$statuses.count",
0
]
}
},
"totalCount": { "$sum": 1 }
}
}
]);
Why not just keep statuses as an object so each status is a key/val pair. If that works you do the following
db.getCollection('Assignments').aggregate([
[
{
"$group": {
"_id": {
"assignee": "$assignee",
"statusId": "$statusId"
},
"statusCount": { "$sum": 1 }
},
},
{
"$group" : {
"_id" : "$_id.assignee",
"statuses" : {
"$push" : {
"k" : "$_id.statusId", // <- "k" as key value important for $arrayToObject Function
"v" : "$statusCount" // <- "v" as key value important for $arrayToObject Function
}
},
"count" : {
"$sum" : "$statusCount"
}
}
},
{
"$project" : {
"_id" : 1.0,
"statuses" : {
"$arrayToObject" : "$statuses"
},
"totalCount" : "$count"
}
}
],
{
"allowDiskUse" : false
}
);
This gives you:
{
"_id" : "Katrina",
"statuses": {
"Pending" : 1.0,
"Completed" : 1.0,
"Assigned" : 1.0,
},
"totalCount" : 3.0
}
A compromise having it one layer deeper but still the shape of statuses you wanted and dynamic with each new statusId added.
I have these collections in my database:
Items:
{ "IdUser" : "1", "IdItem" : "1" },
{ "IdUser" : "1", "IdItem" : "2" },
{ "IdUser" : "1", "IdItem" : "3" },
{ "IdUser" : "2", "IdItem" : "4" },
{ "IdUser" : "2", "IdItem" : "5" },
{ "IdUser" : "4", "IdItem" : "6" },
{ "IdUser" : "5", "IdItem" : "7" }
Users
{ "_id" : "1", "DateRegister" : ISODate("2016-03-29T22:00:38.764+0000") },
{ "_id" : "2", "DateRegister" : ISODate("2014-03-29T22:00:38.764+0000") },
{ "_id" : "2", "DateRegister" : ISODate("2015-02-29T22:00:38.764+0000") },
{ "_id" : "4", "DateRegister" : ISODate("2013-01-29T22:00:38.764+0000") },
{ "_id" : "5", "DateRegister" : ISODate("2016-04-29T22:00:38.764+0000") }
How can I obtain this result but FILTERED with users registered after 2015:
Users with one item: 2
Users with two items: 1
Users with three items: 1
I have tried with that, but I don't know how to filter... Thanks!
db.collection.aggregate([
{
"$group": {
"_id": "$IdUser",
"count": {
"$sum": { "$cond": [{ "$gt": [ "$IdItem", null ] }, 1, 0 ] }
}
}
},
{
"$group": {
"_id": "$count",
"users": { "$push": "$_id" }
}
},
{
"$project": {
"_id": 0,
"number_of_items": "$_id",
"number_of_users": { "$size": "$users" }
}
}
])
You may want to utilize the $lookup operator to perform a join of the items collection with the users collection and then do a $match filter on the DateRegistered field before piping the main grouping operations.
Following this example + the links herein to the documentation will give you an idea:
db.items.aggregate([
{
"$lookup": {
"from": "users",
"localField": "IdUser",
"foreignField": "_id",
"as": "user"
}
},
{ "$match": { "user.DateRegister": { "$gt": new Date(2015, 11, 31) } } },
{
"$group": {
"_id": "$IdUser",
"count": {
"$sum": { "$cond": [{ "$gt": [ "$IdItem", null ] }, 1, 0 ] }
}
}
},
{
"$group": {
"_id": "$count",
"users": { "$push": "$_id" }
}
},
{
"$project": {
"_id": 0,
"number_of_items": "$_id",
"number_of_users": { "$size": "$users" }
}
}
])
In the event that your MongoDB server does not support the $lookup operator, you will then need a workaround where you split the operations on the different collections i.e.
get a list of user id's that match the given date range criteria, this could be done with the distinct() method on the users collection with the date query option.
use that list in the items collection aggregation pipeline within the $match operator initial step.
The following demonstrates this:
// use distinct to get the user id's list
var userIds = db.users.distinct("_id", { "DateRegister": { "$gt": new Date(2015, 11, 31) } })
// perform your aggregation with a filtered collection using the list from the above operations
db.items.aggregate([
{ "$match": { "IdUser": { "$in": userIds } } },
{
"$group": {
"_id": "$IdUser",
"count": {
"$sum": { "$cond": [{ "$gt": [ "$IdItem", null ] }, 1, 0 ] }
}
}
},
{
"$group": {
"_id": "$count",
"users": { "$push": "$_id" }
}
},
{
"$project": {
"_id": 0,
"number_of_items": "$_id",
"number_of_users": { "$size": "$users" }
}
}
])
My collection will look this,
{
"_id" : ObjectId("55c8bd1d85b83e06dc54c0eb"),
"name" : "xxx",
"salary" : 10000,
"type" : "type1"
}
{
"_id" : ObjectId("55c8bd1d85b83e06dc54c0eb"),
"name" : "aaa",
"salary" : 10000,
"type" : "type2"
}
{
"_id" : ObjectId("55c8bd1d85b83e06dc54c0eb"),
"name" : "ccc",
"salary" : 10000,
"type" : "type2"
}
My query params will be coming as,
{salary=10000, type=type2}
so based on the query I need to fetch the count of above query params
The result should be something like this,
{ category: 'type1', count: 500 } { category: 'type2', count: 200 } { category: 'name', count: 100 }
Now I am getting count by hitting three different queries and constructing the result (or) server side iteration I can get the result.
Can anyone suggest or provide me good way to get above result
Your quesstion is not very clearly presented, but what it seems you wanted to do here was count the occurances of the data in the fields, optionally filtering those fields by the values that matches the criteria.
Here the $cond operator allows you to tranform a logical condition into a value:
db.collection.aggregate([
{ "$group": {
"_id": null,
"name": { "$sum": 1 },
"salary": {
"$sum": {
"$cond": [
{ "$gte": [ "$salary", 1000 ] },
1,
0
]
}
},
"type": {
"$sum": {
"$cond": [
{ "$eq": [ "$type", "type2" ] },
1,
0
]
}
}
}}
])
All values are in the same document, and it does not really make any sense to split them up here as this is additional work in the pipeline.
{ "_id" : null, "name" : 3, "salary" : 3, "type" : 2 }
Otherwise in the long form, which is not very performant due to needing to make a copy of each document for every key looks like this:
db.collection.aggregate([
{ "$project": {
"name": 1,
"salary": 1,
"type": 1,
"category": { "$literal": ["name","salary","type"] }
}},
{ "$unwind": "$category" },
{ "$group": {
"_id": "$category",
"count": {
"$sum": {
"$cond": [
{ "$and": [
{ "$eq": [ "$category", "name"] },
{ "$ifNull": [ "$name", false ] }
]},
1,
{ "$cond": [
{ "$and": [
{ "$eq": [ "$category", "salary" ] },
{ "$gte": [ "$salary", 1000 ] }
]},
1,
{ "$cond": [
{ "$and": [
{ "$eq": [ "$category", "type" ] },
{ "$eq": [ "$type", "type2" ] }
]},
1,
0
]}
]}
]
}
}
}}
])
And it's output:
{ "_id" : "type", "count" : 2 }
{ "_id" : "salary", "count" : 3 }
{ "_id" : "name", "count" : 3 }
If your documents do not have uniform key names or otherwise cannot specify each key in your pipeline condition, then apply with mapReduce instead:
db.collection.mapReduce(
function() {
var doc = this;
delete doc._id;
Object.keys(this).forEach(function(key) {
var value = (( key == "salary") && ( doc[key] < 1000 ))
? 0
: (( key == "type" ) && ( doc[key] != "type2" ))
? 0
: 1;
emit(key,value);
});
},
function(key,values) {
return Array.sum(values);
},
{
"out": { "inline": 1 }
}
);
And it's output:
"results" : [
{
"_id" : "name",
"value" : 3
},
{
"_id" : "salary",
"value" : 3
},
{
"_id" : "type",
"value" : 2
}
]
Which is basically the same thing with a conditional count, except that you only specify the "reverse" of the conditions you want and only for the fields you want to filter conditions on. And of course this output format is simple to emit as separate documents.
The same approach applies where to test the condition is met on the fields you want conditions for and return 1 where the condition is met or 0 where it is not for the summing the count.
You can use aggregation as following query:
db.collection.aggregate({
$match: {
salary: 10000,
//add any other condition here
}
}, {
$group: {
_id: "$type",
"count": {
$sum: 1
}
}
}, {
$project: {
"category": "$_id",
"count": 1,
_id: 0
}
}