I am new to mongodb aggregation, i have a collection
{
"_id":60ab3312623b0108338a9601,
"items":[{"type":"Tshirt","price":300,"quantity":2}],
"orderId":"ORD189",
"from":"abc",
"to":"xyz",
"createdAt":2021-05-24T05:01:06.960Z,
"__v":0,
"tracking":null
}
I want to find the count of orders per day and totalPrice of items like
{_id: {date:24, month:05, year:2021}, count: 1, totalPrice: 600}
I used aggregations like below
db.getCollection("orders").aggregate(
[
{
"$group" : {
"_id" : {
"date" : {
"$dayOfMonth" : "$createdAt"
},
"month" : {
"$month" : "$createdAt"
},
"year" : {
"$year" : "$createdAt"
}
},
"count" : { $sum : 1},
"totalPrice" : {
$sum: {
$map: {
"input" :"$items",
"as":"item",
"in":{
$multiply: ["$item.price", "$item.quantity"]
}
}
}
}
}
}
]
);
It is giving me the following result
{
"_id" : {
"date" : NumberInt(24),
"month" : NumberInt(5),
"year" : NumberInt(2021)
},
"count" : 1.0,
"totalPrice" : NumberInt(0)
}
If I use unwind am not able to get the proper count.
You just need to correct totalPrice calculation,
$map to iterate loop of items and do multiplication of price and quantity, this will return array of total
$sum to get total of above total
"totalPrice": {
$sum: {
$sum: {
$map: {
input: "$items",
in: {
$multiply: ["$$this.price", "$$this.quantity"]
}
}
}
}
}
Playground
Related
How to get percentage total of data with group by date in MongoDB ?
Link example : https://mongoplayground.net/p/aNND4EPQhcb
I have some collection structure like this
{
"_id" : ObjectId("5ccbb96706d1d47a4b2ced4b"),
"date" : "2019-05-03T10:39:53.108Z",
"id" : 166,
"update_at" : "2019-05-03T10:45:36.208Z",
"type" : "image"
}
{
"_id" : ObjectId("5ccbb96706d1d47a4b2ced4c"),
"date" : "2019-05-03T10:39:53.133Z",
"id" : 166,
"update_at" : "2019-05-03T10:45:36.208Z",
"type" : "image"
}
{
"_id" : ObjectId("5ccbb96706d1d47a4b2ced4d"),
"date" : "2019-05-03T10:39:53.180Z",
"id" : 166,
"update_at" : "2019-05-03T10:45:36.208Z",
"type" : "image"
}
{
"_id" : ObjectId("5ccbb96706d1d47a4b2ced4e"),
"date" : "2019-05-03T10:39:53.218Z",
"id" : 166,
"update_at" : "2019-05-03T10:45:36.208Z",
"type" : "image"
}
And I have query in mongodb to get data of collection, how to get percentage of total data. in bellow example query to get data :
db.name_collection.aggregate(
[
{ "$match": {
"update_at": { "$gte": "2019-11-04T00:00:00.0Z", "$lt": "2019-11-06T00:00:00.0Z"},
"id": { "$in": [166] }
} },
{
"$group" : {
"_id": {
$substr: [ '$update_at', 0, 10 ]
},
"count" : {
"$sum" : 1
}
}
},
{
"$project" : {
"_id" : 0,
"date" : "$_id",
"count" : "$count"
}
},
{
"$sort" : {
"date" : 1
}
}
]
)
and this response :
{
"date" : "2019-11-04",
"count" : 39
},
{
"date" : "2019-11-05",
"count" : 135
}
how to get percentage data total from key count ? example response to this :
{
"date" : "2019-11-04",
"count" : 39,
"percentage" : "22%"
},
{
"date" : "2019-11-05",
"count" : 135,
"percentage" : "78%"
}
You have to group by null to get total count and then use $map to calculate the percentage. $round will be a useful operator in such case. Finally you can $unwind and $replaceRoot to get back the same number of documents:
db.collection.aggregate([
// previous aggregation steps
{
$group: {
_id: null,
total: { $sum: "$count" },
docs: { $push: "$$ROOT" }
}
},
{
$project: {
docs: {
$map: {
input: "$docs",
in: {
date: "$$this.date",
count: "$$this.count",
percentage: { $concat: [ { $toString: { $round: { $multiply: [ { $divide: [ "$$this.count", "$total" ] }, 100 ] } } }, '%' ] }
}
}
}
}
},
{
$unwind: "$docs"
},
{
$replaceRoot: { newRoot: "$docs" }
}
])
Mongo Playground
I am new to mongo and trying to perform aggregation query to calculate min/max of timestamps for a given document.
Sample documents are below -
{
"_id" : ObjectId("5c9cd93adddca9ebb2b3fcba"),
"frequency" : 5,
"s_id" : "30081993",
"timestamp" : NumberLong(1546300800000),
"date" : ISODate("2019-01-01T00:00:00.000Z"),
"values" : {
"1547439900000" : {
"number_of_values" : 3,
"min_value" : 32.13,
"max_value" : 81.42
},
"1547440200000" : {
"number_of_values" : 3,
"min_value" : 48.08,
"max_value" : 84.52
},
"1547440500000" : {
"number_of_values" : 2,
"min_value" : 27.39,
"max_value" : 94.64
}
}
}
{
"_id" : ObjectId("5c9cd851dddca9ebb2b3f2ac"),
"frequency" : 5,
"s_id" : "27061995",
"timestamp" : NumberLong(1546300800000),
"date" : ISODate("2019-01-01T00:00:00.000Z"),
"values" : {
"1547539900000" : {
"number_of_values" : 31,
"min_value" : 322.13,
"max_value" : 831.42
},
"1547540200000" : {
"number_of_values" : 3,
"min_value" : 418.08,
"max_value" : 8114.52
},
"1547740500000" : {
"number_of_values" : 2,
"min_value" : 207.39,
"max_value" : 940.64
}
}
}
I have come up with the following query which works for a single document.
db.testdb.aggregate([
{
$match: {
"s_id": "30081993",
"frequency": 5,
}
},
{
$project: {
_id: 1,
valuesarray: {
$objectToArray: "$values"
}
}
},
{
$unwind: "$valuesarray"
},
{
$group: {
"_id": "",
"min_timestamp": {
$min: "$valuesarray.k"
},
"max_timestamp": {
$max: "$valuesarray.k"
}
}
}
]);
The output is below
{
"_id" : "",
"min_timestamp" : "1547439900000",
"max_timestamp" : "1547440500000"
}
I want an aggregation query which can calculate the max/min of timestamps but for multiple documents i.e I want to use a $in operator during the $match stage and get min/max of all s_id. Is this possible?
Expected :
{
"_id" : "30081993",
"min_timestamp" : "1547439900000",
"max_timestamp" : "1547440500000"
}
{
"_id" : "27061995",
"min_timestamp" : "1547539900000",
"max_timestamp" : "1547740500000"
}
Yes, only small changes are required to make this work for multiple documents.
In $match stage, specify your $in query:
$match: {
"s_id": { $in : [ "30081993", "27061995" ] },
"frequency": 5,
}
In $project stage, rename s_id to _id, to ensure we keep the s_id associated with each document:
$project: {
_id: "$s_id",
valuesarray: {
$objectToArray: "$values"
}
}
In $group stage, group by _id (originally s_id), to ensure we correctly group the timestamps together before calculating $min/$max:
$group: {
"_id": "$_id",
"min_timestamp": {
$min: "$valuesarray.k"
},
"max_timestamp": {
$max: "$valuesarray.k"
}
}
Whole pipeline:
db.testdb.aggregate([
{
$match: {
"s_id": { $in : [ "30081993", "27061995" ] },
"frequency": 5,
}
},
{
$project: {
_id: "$s_id",
valuesarray: {
$objectToArray: "$values"
}
}
},
{
$unwind: "$valuesarray"
},
{
$group: {
"_id": "$_id",
"min_timestamp": {
$min: "$valuesarray.k"
},
"max_timestamp": {
$max: "$valuesarray.k"
}
}
}
]);
I want to count correct, incorrect and unattempted question count. I am getting zero values.
Query -
db.studentreports.aggregate([
{ $match: { 'groupId': 314 } },
{ $unwind: '$questions' },
{ $group:
{
_id: {
dateTimeStamp: '$dateTimeStamp',
customerId: '$customerId'
},
questions : { $push: '$questions' },
unttempted : { $sum : { $eq: ['$questions.status',0]}},
correct : { $sum : { $eq: ['$questions.status',1]}},
incorrect : { $sum : { $eq: ['$questions.status',2]}},
Total: { $sum: 1 }
}
}
])
Schema structure -
{
"_id" : ObjectId("59fb46ed560e1a2fd5b6fbf4"),
"customerId" : 2863318,
"groupId" : 309,
"questions" : [
{
"questionId" : 567,
"status" : 0,
"_id" : ObjectId("59fb46ee560e1a2fd5b700a4"),
},
{
"questionId" : 711,
"status" : 0,
"_id" : ObjectId("59fb46ee560e1a2fd5b700a3")
},
....
values unttempted, correct and incorrect are getting wrong -
"unttempted" : 0,
"correct" : 0,
"incorrect" : 0,
"Total" : 7558.0
Group by is required based on datetime and customerId.
Can some one correct query ?
Thanks.
You want to sum these fields only if a certain condition is met.
You just have to rewrite your group statement like this:
{ $group:
{
_id: {
dateTimeStamp: '$dateTimeStamp',
customerId: '$customerId'
},
questions : { $push: '$questions' },
unttempted : { $sum : {$cond:[{ $eq: ['$questions.status',0]}, 1, 0]}},
correct : { $sum : {$cond:[{ $eq: ['$questions.status',1]}, 1, 0]}},
incorrect : { $sum : {$cond:[{ $eq: ['$questions.status',2]}, 1, 0]}},
Total: { $sum: 1 }
}
}
Check out the documentation $eq. $eq compares and returns true or false. So then your $sum cannot do anything with that result
My collection looks like this:
{
"_id":ObjectId("5744b6cd9c408cea15964d18"),
"uuid":"bbde4bba-062b-4024-9bb0-8b12656afa7e",
"version":1,
"categories":["sport"]
},
{
"_id":ObjectId("5745d2bab047379469e10e27"),
"uuid":"bbde4bba-062b-4024-9bb0-8b12656afa7e",
"version":2,
"categories":["sport", "shopping"]
},
{
"_id":ObjectId("5744b6359c408cea15964d15"),
"uuid":"561c3705-ba6d-432b-98fb-254483fcbefa",
"version":1,
"categories":["politics"]
}
I want to count the number of documents for every category. To do this, I unwind the categories array:
db.collection.aggregate(
{$unwind: '$categories'},
{$group: {_id: '$categories', count: {$sum: 1}} }
)
Result:
{ "_id" : "sport", "count" : 2 }
{ "_id" : "shopping", "count" : 1 }
{ "_id" : "politics", "count" : 1 }
Now I want to count the number of documents for every category, but where document version is the latest version.
This is where I am stuck.
It's ugly but I think this gives you what you're after:
db.collection.aggregate(
{ $unwind : "$categories" },
{ $group :
{ "_id" : { "uuid" : "$uuid" },
"doc" : { $push : { "version" : "$version", "category" : "$categories" } },
"maxVersion" : { $max : "$version" }
}
},
{ $unwind : "$doc" },
{ $project : { "_id" : 0, "uuid" : "$id.uuid", "category" : "$doc.category", "isCurrentVersion" : { $eq : [ "$doc.version", "$maxVersion" ] } } },
{ $match : { "isCurrentVersion" : true }},
{ $group : { "_id" : "$category", "count" : { $sum : 1 } } }
)
You can do this by first grouping the denormalized documents (from the $unwind operator step) by two keys, i.e. the categories and version fields. This is necessary for the preceding pipeline step which orders the grouped documents and their accumulated counts by the version (desc) and categories (asc) keys respectively using the $sort operator.
Another grouping will be required to get the top documents in each categories group after ordering using the $first operator. The following shows this
db.collection.aggregate(
{ "$unwind": "$categories" },
{
"$group": {
"_id": {
'categories': '$categories',
'version': '$version'
},
"count": { "$sum": 1 }
}
},
{ "$sort": { "_id.version": -1, "_id.categories": 1 } },
{
"$group": {
"_id": "$_id.categories",
"count": { "$first": "$count" },
"version": { "$first": "$_id.version" }
}
}
)
Sample Output
{ "_id" : "shopping", "count" : 1, "version" : 2 }
{ "_id" : "sport", "count" : 1, "version" : 2 }
{ "_id" : "politics", "count" : 1, "version" : 1 }
I am new in MongoDB world.
I've following data in my collection
{
"_id" : ObjectId("5735d8d4d147aa34e440988f"),
"DeviceLogId" : "26962",
"DeviceId" : "10",
"UserId" : "78",
"LogDateTime" : ISODate("2016-05-12T07:52:44.000+0000")
}
{
"_id" : ObjectId("5735d8d4d147aa34e4409890"),
"DeviceLogId" : "26963",
"DeviceId" : "10",
"UserId" : "342",
"LogDateTime" : ISODate("2016-05-12T07:54:09.000+0000")
}
{
"_id" : ObjectId("5735d8d4d147aa34e4409891"),
"DeviceLogId" : "26964",
"DeviceId" : "10",
"UserId" : "342",
"LogDateTime" : ISODate("2016-05-12T07:54:10.000+0000")
}
{
"_id" : ObjectId("5735d8d4d147aa34e4409892"),
"DeviceLogId" : "26965",
"DeviceId" : "10",
"UserId" : "78",
"LogDateTime" : ISODate("2016-05-12T07:54:27.000+0000")
}
I want to query DeviceId of each user with maximum LogDateTime using group by.
I've written group by query like below but have no idea how would I get DeviceLogId for each record.
collectionName.aggregate(
[{
$match: { LogDateTime: { $gt: todaysDateStart, $lt: todayDateEnd } }
}, {
$group: {
_id: "$UserId",
maxPunchTime: { $max: { $add: [ "$LogDateTime", 330*60000 ] } },
}
}])
In MSSQL, I could easily do it with nested query but I've no idea how would I achieve that in MongoDB.
Thanks in advance.
Use the $addToSet Group Accumulator:
collectionName.aggregate(
[{
$match: { LogDateTime: { $gt: todaysDateStart, $lt: todayDateEnd } }
}
, {
$group: {
_id: "$UserId",
maxPunchTime: { $max: { $add: [ "$LogDateTime", 330*60000 ] } },
deviceLogIds:{$addToSet: "$DeviceLogId"} //<----
}
} ,
{ $sort: {"maxPunchTime" : -1} } , {$limit : 1} //Sort Descending + Limit to 1
])
Add deviceid to an array in group phase,
Device:{$addToSet:deviceId}