I want to write a group by query to written active user and total count(both active and inactive) grouped by a date column in mongodb. I am able to run them as two separate scripts but how to retrieve the same information in one script
db.user.aggregate(
{
"$match": { 'phoneInfo.verifiedFlag': true}
},
{
"$project": {
yearMonthDayUTC: { $dateToString: { format: "%Y-%m-%d", date: "$createdOn" } }
}
},
{
"$group": {
"_id": {day: "$yearMonthDayUTC"},
count: {
"$sum": 1
}
}
},
{
$sort: {
"_id.day": 1,
}
})
You can use the $cond operator in your group to create a conditional count as follows (assuming the inactive/active values are in a field called status):
db.user.aggregate([
{ "$match": { 'phoneInfo.verifiedFlag': true} },
{
"$group": {
"_id": { "$dateToString": { "format": "%Y-%m-%d", "date": "$createdOn" } },
"total": { "$sum": 1 },
"active_count": {
"$sum": {
"$cond": [ { "$eq": [ "$status", "active" ] }, 1, 0 ]
}
},
"inactive_count": {
"$sum": {
"$cond": [ { "$eq": [ "$status", "inactive" ] }, 1, 0 ]
}
}
}
},
{ "$sort": { "_id": 1 } }
])
For different values you can adapt the following pipeline:
db.user.aggregate([
{ "$match": { 'phoneInfo.verifiedFlag': true} },
{
"$group": {
"_id": {
"day": {
"$dateToString": {
"format": "%Y-%m-%d",
"date": "$createdOn"
}
},
"status": { "$toLower": "$status" }
},
"count": { "$sum": 1 }
}
},
{
"$group": {
"_id": "$_id.day",
"counts": {
"$push": {
"status": "$_id.status",
"count": "$count"
}
}
}
},
{ "$sort": { "_id": 1 } }
])
Related
I am currently using the following query but hitting a small issue - It's really slow.
Is there any way that mongooseJS can either:
a) split this into smaller queries and run it in segments
b) a better way to query this data.
My query
[
{
$project: {
"location": 1,
"year": { "$year": "$timestamp" }
}
},
{
$match: { "year": 2020 }
},
{
$group: {
"_id": "$location.coordinates",
"count": { "$sum": 1 }
}
},
{
$project: {
"_id": 0,
"count": 1,
"location.coordinates": {
"$map": {
"input": "$_id",
"in": { "$toString": "$$this" }
}
}
}
},
{
$sort: { count: -1 }
}
])
in NodeJS I am querying it like I have M10 atlas so no issue running the query it works in Mongodb compass
router.get('/pastlocation', (req, res) =>{
const pastlocation = require('mongoose').model('pastlistenerslocation');
pastlocation.aggregate([
{
$project: {
"location": 1,
"year": { "$year": "$timestamp" }
}
},
{
$match: { "year": 2020 }
},
{
$group: {
"_id": "$location.coordinates",
"count": { "$sum": 1 }
}
},
{
$project: {
"_id": 0,
"count": 1,
"location.coordinates": {
"$map": {
"input": "$_id",
"in": { "$toString": "$$this" }
}
}
}
},
{ $sort: { count: -1 } }
])).allowDiskUse(true).exec(function(err,result) {
if(err){console.log(err)}
res.json(result);
});
});
Data looks like this:
{
"UUID": "9B3640AC-3AA9-4313-94DB-9DFFEC7362E1",
"location": {
"coordinates": [115.8802288492358, -31.92553401927643],
"type": "Point"
},
"timestamp": {
"$date": "2020-11-04T13:20:58.224Z"
},
"__v": 0
}
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 collection with documents that look similar to this:
[
{
"_id": ObjectId("..."),
"date": ISODate("..."),
"type": "TypeA",
"color": "ColorA",
"soldFor": 12.15
},
{
"_id": ObjectId("..."),
"date": ISODate("..."),
"type": "TypeA",
"color": "ColorB",
"soldFor": 13.15
},
{
"_id": ObjectId("..."),
"date": ISODate("..."),
"type": "TypeB",
"color": "ColorA",
"soldFor": 12.15
},
{
"_id": ObjectId("..."),
"date": ISODate("..."),
"type": "TypeB",
"color": "ColorB",
"soldFor": 12.15
}
]
I know that this is not a good way to store such information, but unfortunately I have no influence in that.
What I need to get out of the collection is something like this:
[
2017: {
typeA: {
colorA: {
sum: 125.00
},
colorB: {
sum: 110.00
}
},
typeB: {
colorA: {
sum: 125.000
}
}
},
2016: {
typeA: {
colorB: {
sum: 125.000
}
}
}
]
At the moment I have two group stages that give me everything grouped by year, but I have no clue how to get the two other sub-groups. Building the sum would be a nice to have, but I am certain that I can figure out how that would be done in a group.
So far my pipeline looks like this:
[
{
$group: {
_id: { type: '$type', color: '$color', year: { $year: '$date' } },
docs: {
$push: '$$ROOT'
}
}
},
{
$group: {
_id: { year: '$_id.year' },
docs: {
$push: '$$ROOT'
}
}
}
]
which results in something like this:
[
{
"_id": {
"year": 2006
},
"docs": {
"_id": {
"type": "typeA",
"color": "colorA",
"year": 2006
},
"docs": [
{
... root document
}
]
}
},
{
"_id": {
"year": 2016
},
"docs": [
{
"_id": {
"type": "typeA",
"color": "colorB",
"year": 2016
},
"docs": [
{
... root document
}
]
}
... more docs with three keys in id
]
}
]
Help is much appreciated!
Using a cohort of operators found in MongoDB 3.4.4 and newer, i.e. $addFields, $arrayToObject and $replaceRoot, you can compose a pipeline like the following to get the desired result:
[
{ "$group": {
"_id": {
"year": { "$year": "$date" },
"type": "$type",
"color": "$color"
},
"count": { "$sum": "$soldFor" }
} },
{ "$group": {
"_id": {
"year": "$_id.year",
"type": "$_id.type"
},
"counts": {
"$push": {
"k": "$_id.color",
"v": { "sum": "$count" }
}
}
} },
{ "$addFields": {
"counts": { "$arrayToObject": "$counts" }
} },
{ "$group": {
"_id": "$_id.year",
"counts": {
"$push": {
"k": "$_id.type",
"v": "$counts"
}
}
} },
{ "$addFields": {
"counts": { "$arrayToObject": "$counts" }
} },
{ "$group": {
"_id": null,
"counts": {
"$push": {
"k": { "$substr": ["$_id", 0, -1 ]},
"v": "$counts"
}
}
} },
{ "$replaceRoot": {
"newRoot": {
"$mergeObjects": [
{ "$arrayToObject": "$counts" },
"$$ROOT"
]
}
} },
{ "$project": { "counts": 0 } }
]
I have documents like:
{
"platform":"android",
"install_date":20151029
}
platform - can have one value from [android|ios|kindle|facebook ] .
install_date - there are many install_dates
There are also many fields.
Aim : I am calculating installs per platform on particular date.
So I am using group by in aggregation framework and make counts by platform. Document should look like like:
{
"install_date":20151029,
"platform" : {
"android":1000,
"ios": 2000,
"facebook":1500
}
}
I have done like:
db.collection.aggregate([
{
$group: {
_id: { platform: "$platform",install_date:"$install_date"},
count: { "$sum": 1 }
}
},
{
$group: {
_id: { install_date:"$_id.install_date"},
platform: { $push : {platform :"$_id.platform", count:"$count" } }
}
},
{
$project : { _id: 0, install_date: "$_id.install_date", platform: 1 }
}
])
which Gives document like:
{
"platform": [
{
"platform": "facebook",
"count": 1500
},
{
"platform": "ios",
"count": 2000
},
{
"platform": "android",
"count": 1000
}
],
"install_date": 20151027
}
Problem:
Projecting array to single object as "platform"
With MongoDb 3.4 and newer, you can leverage the use of $arrayToObject operator to get the desired result. You would need to run the following aggregate pipeline:
db.collection.aggregate([
{ "$group": {
"_id": {
"date": "$install_date",
"platform": { "$toLower": "$platform" }
},
"count": { "$sum": 1 }
} },
{ "$group": {
"_id": "$_id.date",
"counts": {
"$push": {
"k": "$_id.platform",
"v": "$count"
}
}
} },
{ "$addFields": {
"install_date": "$_id",
"platform": { "$arrayToObject": "$counts" }
} },
{ "$project": { "counts": 0, "_id": 0 } }
])
For older versions, take advantage of the $cond operator in the $group pipeline step to evaluate the counts based on the platform field value, something like the following:
db.collection.aggregate([
{ "$group": {
"_id": "$install_date",
"android_count": {
"$sum": {
"$cond": [ { "$eq": [ "$platform", "android" ] }, 1, 0 ]
}
},
"ios_count": {
"$sum": {
"$cond": [ { "$eq": [ "$platform", "ios" ] }, 1, 0 ]
}
},
"facebook_count": {
"$sum": {
"$cond": [ { "$eq": [ "$platform", "facebook" ] }, 1, 0 ]
}
},
"kindle_count": {
"$sum": {
"$cond": [ { "$eq": [ "$platform", "kindle" ] }, 1, 0 ]
}
}
} },
{ "$project": {
"_id": 0, "install_date": "$_id",
"platform": {
"android": "$android_count",
"ios": "$ios_count",
"facebook": "$facebook_count",
"kindle": "$kindle_count"
}
} }
])
In the above, $cond takes a logical condition as it's first argument (if) and then returns the second argument where the evaluation is true (then) or the third argument where false (else). This makes true/false returns into 1 and 0 to feed to $sum respectively.
So for example, if { "$eq": [ "$platform", "facebook" ] }, is true then the expression will evaluate to { $sum: 1 } else it will be { $sum: 0 }
[
{ "$match": {
"created":{
"$gte": ISODate("2015-07-19T07:26:49.045Z")
},
"created":{
"$lte": ISODate("2015-07-20T07:37:56.045Z")
}
}},
{ "$group:{
"_id":{
"ln":"$l.ln",
"cid":"$cid"
},
"appCount":{ "$sum": 1 }
}},
{ "$group": {
"_id": { "ln":"$_id.ln" },
"cusappCount": { "$sum": 1 }
}},
{ "$sort":{ "_id.ln":1 } }
]
In above mongo db query I am not able to display the appcount in result.. I am able to display cusappCount. Could anyone please help me on this
The $match is wrong to start with and does not do what you think. It is only selecting the "second" statement:
"created":{
"$lte": ISODate("2015-07-20T07:37:56.045Z")
}
So your selections are incorrect to start with.
That and other corrections below:
[
{ "$match": {
"created": {
"$gte": ISODate("2015-07-19T07:26:49.045Z"),
"$lte": ISODate("2015-07-20T07:37:56.045Z")
}
}},
{ "$group":{
"_id": {
"ln":"$l.ln",
"cid":"$cid"
},
"appCount":{ "$sum": 1 }
}},
{ "$group": {
"_id": "$_id.ln",
"cusappCount": { "$sum": "$appCount" },
"distinctCustCount": { "$sum": 1 }
}},
{ "$sort":{ "_id": 1 } }
]
Which seems to be what you are trying to do.
So your earier "count" is then passed to $sum when grouping at a "broader" level. The "second" count is just for the "distinct" items in the earlier key.
If you are trying to "retain" the values of "appCount", then the problem here is that your "grouping" is "taking away" the detail level that appears at. So for what it is woth, then this is where you use "arrays" in an output structure:
[
{ "$match": {
"created": {
"$gte": ISODate("2015-07-19T07:26:49.045Z"),
"$lte": ISODate("2015-07-20T07:37:56.045Z")
}
}},
{ "$group":{
"_id": {
"ln":"$l.ln",
"cid":"$cid"
},
"appCount":{ "$sum": 1 }
}},
{ "$group": {
"_id": "$_id.ln",
"cusappCount": { "$sum": 1 },
"custs": { "$push": {
"cid": "$_id.cid", "appCount": "$appCount"
}}
}},
{ "$sort":{ "_id": 1 } }
]