there
My question may be confuse. Let's me explain further more.
I have document for aggregation like this.
{
"metric" : "user_act",
"stream_id" : "f00001",
"values" : {
"likes" : 57,
"comments" : 0,
"shares" : 0
}
}
{
"metric" : "user_act",
"stream_id" : "f00002",
"values" : {
"likes" : 28,
"comments" : 0,
"shares" : 1
}
}
{
"metric" : "user_act",
"stream_id" : "t00001",
"values" : {
"favorites" : 5,
"retweets" : 15
}
}
I would like to calculate engagement by sum likes, comments and shares together. So before calculating, I have to projection data before grouping. I would like to mapping values.favorites to likes, values.retweets to shares and comments if don't have any data set default to 0.
I try projection like below but does not work because value of second line of $ifNull override the first line.
{
$project: {
"stream_id" : 1,
"shares": {
$ifNull: ["$values.retweets",0],
$ifNull: ["$values.shares", 0]
} ,
"likes": {
$ifNull: ["$values.favorites",0],
$ifNull: ["$values.likes", 0]
} ,
"comments": {
$ifNull: ["$values.replys",0],
$ifNull: ["$values.comments", 0]
}
}
}
Anyone any idea? Thank you in advanced.
[Update]
I try to projection like this but not work in case: how can I check the field exists?
{
$project: {
"stream_id" : 1,
"shares": {
$switch: {
branches: [
{ case: {$ne: ["$values.retweets", 0]},
then: {$ifNull: ["$values.retweets", "$values.retweets"]}
},
{ case: {$ne: ["$values.shares", 0]},
then: {$ifNull: ["$values.shares", "$values.shares"]}
}
],
default: 0
}
}
}
}
You can try $cond projection.
db.collection.aggregate({
$project: {
"stream_id" : 1,
"shares": { $cond: [ { $eq:[ { $ifNull: [ "$values.shares", 0 ] }, 0 ] },{ $ifNull: [ "$values.retweets", 0 ] }, "$values.shares" ] },
"likes": { $cond: [ { $eq:[ { $ifNull: [ "$values.likes", 0 ] }, 0 ] }, { $ifNull: [ "$values.favorites", 0 ] }, "$values.likes" ] },
"comments": { $cond: [ { $eq:[ { $ifNull: [ "$values.comments", 0] }, 0 ] }, { $ifNull: [ "$values.replys", 0 ] }, "$values.comments" ] }
}})
Using $switch
db.collection.aggregate([{
$project: {
"stream_id" : 1,
"shares": {
$switch: {
branches: [
{ case: { $ifNull: [ "$values.shares", false ] },
then: "$values.shares"
},
{ case: { $ifNull: [ "$values.retweets", false ] },
then: "$values.retweets"
}],
default: 0
}
}
}
}])
Related
I have a collection in MongoDB that looks something like the following:
{ "_id" : 1, "type" : "start", userid: "101", placementid: 1 }
{ "_id" : 2, "type" : "start", userid: "101", placementid: 2 }
{ "_id" : 3, "type" : "start", userid: "101", placementid: 3 }
{ "_id" : 4, "type" : "end", userid: "101", placementid: 1 }
{ "_id" : 5, "type" : "end", userid: "101", placementid: 2 }
and I want to group results by userid then placementid and then count the types of "start" and "end", but only when the two counts are different. In this particular example I would want to get placementid: 3 because when grouped and counted this is the only case where the counts don't match.
I've written a query that gets the 2 counts and the grouping but I can't do the filtering when counts don't match. This is my query:
db.getCollection('mycollection').aggregate([
{
$project: {
userid: 1,
placementid: 1,
isStart: {
$cond: [ { $eq: ["$type", "start"] }, 1, 0]
},
isEnd: {
$cond: [ { $eq: ["$type", "end"] }, 1, 0]
}
}
},
{
$group: {
_id: { userid:"$userid", placementid:"$placementid" },
countStart:{ $sum: "$isStart" },
countEnd: { $sum: "$isEnd" }
}
},
{
$match: {
countStart: {$ne: "$countEnd"}
}
}
])
It seems like I'm using the match aggregation incorrectly because I'm seeing results where countStart and countEnd are the same.
{ "_id" : {"userid" : "101", "placementid" : "1"}, "countStart" : 1.0, "countEnd" : 1.0 }
{ "_id" : {"userid" : "101", "placementid" : "2"}, "countStart" : 1.0, "countEnd" : 1.0 }
{ "_id" : {"userid" : "101", "placementid" : "3"}, "countStart" : 1.0, "countEnd" : 0 }
Can anybody point into the right direction please?
To compare two fields inside $match stage you need $expr which is available in MongoDB 3.6:
db.myCollection.aggregate([
{
$project: {
userid: 1,
placementid: 1,
isStart: {
$cond: [ { $eq: ["$type", "start"] }, 1, 0]
},
isEnd: {
$cond: [ { $eq: ["$type", "end"] }, 1, 0]
}
}
},
{
$group: {
_id: { userid:"$userid", placementid:"$placementid" },
countStart:{ $sum: "$isStart" },
countEnd: { $sum: "$isEnd" }
}
},
{
$match: {
$expr: { $ne: [ "$countStart", "$countEnd" ] }
}
}
])
If you're using older version of MongoDB you can use $redact:
db.myCollection.aggregate([
{
$project: {
userid: 1,
placementid: 1,
isStart: {
$cond: [ { $eq: ["$type", "start"] }, 1, 0]
},
isEnd: {
$cond: [ { $eq: ["$type", "end"] }, 1, 0]
}
}
},
{
$group: {
_id: { userid:"$userid", placementid:"$placementid" },
countStart:{ $sum: "$isStart" },
countEnd: { $sum: "$isEnd" }
}
},
{
$redact: {
$cond: { if: { $ne: [ "$countStart", "$countEnd" ] }, then: "$$KEEP", else: "$$PRUNE" }
}
}
])
You run do the following pipeline to get this - no need to use $expr or $redact or anything special really:
db.mycollection.aggregate({
$group: {
_id: {
"userid": "$userid",
"placementid": "$placementid"
},
"sum": {
$sum: {
$cond: {
if: { $eq: [ "$type", "start" ] },
then: 1, // +1 for start
else: -1 // -1 for anything else
}
}
}
}
}, {
$match: {
"sum": { $ne: 0 } // only return the non matching-up ones
}
})
I am trying to update my mongo database which has following structure.
{
"_id" : ObjectId("5a64d076bfd103df081967ae"),
"values" : [
{
"date" : "2018-01-22",
"Price" : "1289.4075"
},
{
"date" : "2018-01-22",
"Price" : "1289.4075"
},
{
"date" : "2015-05-18",
"Price" : 1289.41
}
],
"Code" : 123456,
"schemeStatus" : "Inactive"
}
I want to compare first 2 array element's date value i.e values[0].date and values[1].date. If both matches then I want to delete values[0] so that there will be only 1 entry with that date.
You can use aggregation framework's pipeline with $out as a last stage to update your collection
db.collection.aggregate([
{
$addFields: {
sameDate: {
$let: {
vars: {
fst: { $arrayElemAt: [ "$values", 0 ] },
snd: { $arrayElemAt: [ "$values", 1 ] }
},
in: { $cond: { if: { $eq: [ "$$fst.date", "$$snd.date" ] }, then: 1, else: 0 } }
}
}
}
},
{
$project: {
_id: 1,
values : { $cond: { if: { $eq: [ "$sameDate", 0 ] }, then: "$values", else: { $slice: [ "$values", 1, { $size: "$values" } ] } } },
Code: 1,
schemeStatus: 1
}
},
{ $out: "collection" }
])
Some more important operators used here:
$cond to handle if-else logic
$let to define some helper variables
$arrayElemAt to get first and second element
$slice to pop first element
With MongoDB 3.4.10 and mongoose 4.13.6 I'm able to count sizes of two arrays on the User model:
User.aggregate()
.project({
'_id': 1,
'leftVotesCount': { '$size': '$leftVoted' },
'rightVotesCount': { '$size': '$rightVoted' }
})
where my Users are (per db.users.find())
{ "_id" : ObjectId("5a2b21e63023c6117085c240"), "rightVoted" : [ 2 ],
"leftVoted" : [ 1, 6 ] }
{ "_id" : ObjectId("5a2c0d68efde3416bc8b7020"), "rightVoted" : [ 2 ],
"leftVoted" : [ 1 ] }
Here I'm getting expected result:
[ { _id: '5a2b21e63023c6117085c240', leftVotesCount: 2, rightVotesCount: 1 },
{ _id: '5a2c0d68efde3416bc8b7020', leftVotesCount: 1, rightVotesCount: 1 } ]
Question. How can I get a cumulative value of leftVotesCount and rightVotesCount data? I tried folowing:
User.aggregate()
.project({
'_id': 1,
'leftVotesCount': { '$size': '$leftVoted' },
'rightVotesCount': { '$size': '$rightVoted' },
'votesCount': { '$add': [ '$leftVotesCount', '$rightVotesCount' ] },
'votesCount2': { '$sum': [ '$leftVotesCount', '$rightVotesCount' ] }
})
But votesCount is null and votesCount2 is 0 for both users. I'm expecting votesCount = 3 for User 1 and votesCount = 2 for User 2.
$leftVotesCount, $rightVotesCount become available only on the next stage. Try something like:
User.aggregate()
.project({
'_id': 1,
'leftVotesCount': { '$size': '$leftVoted' },
'rightVotesCount': { '$size': '$rightVoted' }
})
.project({
'_id': 1,
'leftVotesCount': 1,
'rightVotesCount': 1
'votesCount': { '$add': [ '$leftVotesCount', '$rightVotesCount' ] },
'votesCount2': { '$sum': [ '$leftVotesCount', '$rightVotesCount' ] }
})
You can't reference the project variables created in the same project stage.
You can wrap the variables in a $let expression.
User.aggregate().project({
"$let": {
"vars": {
"leftVotesCount": {
"$size": "$leftVoted"
},
"rightVotesCount": {
"$size": "$rightVoted"
}
},
"in": {
"votesCount": {
"$add": [
"$$leftVotesCount",
"$$rightVotesCount"
]
},
"leftVotesCount": "$$leftVotesCount",
"rightVotesCount": "$$rightVotesCount"
}
}
})
It turned out that $add supports nested expressions, so I was able to solve the issue by excluding intermediate variables:
User.aggregate().project({
'_id': 1,
'votesCount': { '$add': [ { '$size': '$leftVoted' }, { '$size': '$rightVoted' } ] }
});
// [ {_id: '...', votesCount: 3}, {_id: '...', votesCount: 2} ]
My collection will look like this,
{
"_id" : ObjectId("591c5971240033283736860a"),
"status" : "Done",
"createdDate" : ISODate("2017-05-17T14:09:20.653Z")
"communications" : [
{
"communicationUUID" : "df07948e-4a14-468e-beb1-db55ff72b215",
"communicationType" : "CALL",
"recipientId" : 12345,
"createdDate" : ISODate("2017-05-18T14:09:20.653Z")
"callResponse" : {
"Status" : "completed",
"id" : "dsd45554545ds92a9bd2c12e0e6436d",
}
}
]}
{
"_id" : ObjectId("45sdsd59124003345121450a"),
"status" : "ToDo",
"createdDate" : ISODate("2017-05-17T14:09:20.653Z")
"communications" : [
{
"communicationUUID" : "45sds55-4a14-468e-beb1-db55ff72b215",
"communicationType" : "CALL",
"recipientId" : 1234,
"createdDate" : ISODate("2017-05-18T14:09:20.653Z")
"callResponse" : {
"Status" : "completed",
"id" : "84fe862f1924455dsds5556436d",
}
}
]}
Currently I am writing two aggregate query to achieve my requirement and my query will be below
db.collection.aggregate(
{ $project: {
dayMonthYear: { $dateToString: { format: "%d/%m/%Y", date: "$createdDate" } },
status: 1,
}},
{ $group: {
_id: "$dayMonthYear",
Pending: { $sum: { $cond : [{ $eq : ["$status", "ToDo"]}, 1, 0]} },
InProgress: { $sum: { $cond : [{ $eq : ["$status", "InProgress"]}, 1, 0]} },
Done: { $sum: { $cond : [{ $eq : ["$status", "Done"]}, 1, 0]} },
Total: { $sum: 1 }
}}
My output will be,
{"_id" : "17/05/2017", "Pending" : 1.0, "InProgress" : 0.0, "Done" : 1.0, "Total" : 2.0 }
Using above query I can able to get count but I need to find the count based on communication Status too so I am writing one more query to achieve,
db.collection.aggregate(
{"$unwind":"$communications"},
{ $project: {
dayMonthYear: { $dateToString: { format: "%d/%m/%Y", date: "$createdDate" } },
communications: 1
}},
{ "$group": {
_id: "$dayMonthYear",
"total_call": { $sum: { $cond : [{ $or : [ { $eq: [ "$communications.callResponse.Status", "failed"] },
{ $eq: [ "$communications.callResponse.Status", "busy"] },
{ $eq: [ "$communications.callResponse.Status", "completed"] },
{ $eq: [ "$communications.callResponse.Status", "no-answer"] }
]}, 1, 0 ] }},
"engaged": { $addToSet: { $cond : [{ $eq : ["$communications.callResponse.Status", "completed"]},
"$communications.recipientId", "null" ]} },
"not_engaged": { $addToSet: { $cond: [{ $or : [ { $eq: [ "$communications.callResponse.Status", "failed"] },
{ $eq: [ "$communications.callResponse.Status", "busy"] },
{ $eq: [ "$communications.callResponse.Status", "no-answer"] } ]},
"$communications.recipientId", "null" ] }}
}},
{ "$project": {
"_id": 1,
"total_call": 1,
"engaged": { "$setDifference": [ "$ngaged", ["null"] ] },
"not_engaged": { "$setDifference": [ "$not_engaged", ["null"] ] },
}},
{ "$project": {
"total_call": 1,
"engaged": { "$size": "$engaged" },
"not_engaged": { "$size": { "$setDifference": [ "$not_engaged", "$engaged" ] }},
}})
My output will be,
{"_id" : "18/05/2017", "total_call" : 2.0, "engaged" : 2, "not_engaged" : 0}
Using above query I can able to get count but I want to achieve it in single query
I am looking for output like
{"_id":"17/05/2017", "Pending" : 1.0, "InProgress" : 0.0, "Done" : 1.0, "total_call" : 0, "engaged" : 0, "not_engaged" : 0}
{"_id":"18/05/2017", "Pending" : 0.0, "InProgress" : 0.0, "Done" : 0.0, "total_call" : 2, "engaged" : 2, "not_engaged" : 0}
Can anyone suggest or provide me good way to get above result.
You can use $concatArrays to merge the status& createdDate documents followed by $group to count the occurrences.
db.collection.aggregate([
{
"$project": {
"statusandcreateddate": {
"$concatArrays": [
[
{
"status": "$status",
"createdDate": "$createdDate"
}
],
{
"$map": {
"input": "$communications",
"as": "l",
"in": {
"status": "$$l.callResponse.Status",
"createdDate": "$$l.createdDate"
}
}
}
]
}
}
},
{
"$unwind": "$statusandcreateddate"
},
{
"$group": {
"_id": {
"$dateToString": {
"format": "%d/%m/%Y",
"date": "$statusandcreateddate.createdDate"
}
},
"total_call": {
"$sum": {
"$cond": [
{
"$or": [
{
"$eq": [
"$statusandcreateddate.status",
"failed"
]
},
{
"$eq": [
"$statusandcreateddate.status",
"busy"
]
},
{
"$eq": [
"$statusandcreateddate.status",
"completed"
]
},
{
"$eq": [
"$statusandcreateddate.status",
"no-answer"
]
}
]
},
1,
0
]
}
},
"engaged": {
"$sum": {
"$cond": [
{
"$eq": [
"$statusandcreateddate.status",
"completed"
]
},
1,
0
]
}
},
"not_engaged": {
"$sum": {
"$cond": [
{
"$or": [
{
"$eq": [
"$statusandcreateddate.status",
"failed"
]
},
{
"$eq": [
"$statusandcreateddate.status",
"busy"
]
},
{
"$eq": [
"$statusandcreateddate.status",
"no-answer"
]
}
]
},
1,
0
]
}
},
"Pending": {
"$sum": {
"$cond": [
{
"$eq": [
"$statusandcreateddate.status",
"ToDo"
]
},
1,
0
]
}
},
"InProgress": {
"$sum": {
"$cond": [
{
"$eq": [
"$statusandcreateddate.status",
"InProgress"
]
},
1,
0
]
}
},
"Done": {
"$sum": {
"$cond": [
{
"$eq": [
"$statusandcreateddate.status",
"Done"
]
},
1,
0
]
}
}
}
}
])
I'm trying to create some daily stats from a MongoDB table. The document contains messages that have a create-date, state (Warn, Error, Complete). I'd like to product a query that results in one record per - Date,Count of Warn, Count of Error, Count of Complete. I'm a newbie with Mongo and just learning the query language. I've tried aggregation with mixed results:
db.TransactionLogs.aggregate(
{ $group : {
_id : {
category: {$substr:["$startDate",0,10]},
term: "$Status",
},
total: { $sum : 2 }
}
})
results in multiple records per date by status:
"result" : [
{
"_id" : {
"category" : "2015-02-10",
"term" : "Completed",
},
"total" : 532
},
{
"_id" : {
"category" : "2015-02-10",
"term" : "Error",
},
"total" : 616
},
Message:
{ "_id" : "2ceda481-3dd3-480d-800d-95288edce6f2", "MID" : "02de5194-7a1d-4854-922c-934902840136", "Status" : "Completed", "firstName" : "Willy", "lastName" : "Wire", "allocation" : "100", "initEvent" : "Marriage", "system" : "Oracle", "startDate" : "2015-02-06T19:03:34.237Z", "stopDate" : "2015-02-06T19:23:34.237Z", "plan" : "445-A" }
I'm sure that its a lack of understanding of aggregation on my part. Any help or direction is greatly appreciated!
I figured it out. I needed to look at how to "pivot" in Mongo. This works:
db.TransactionLogs.aggregate([ { $project: { startdate: {$substr:["$startDate",0,10]},
cnt_e1: { $cond: [ { $eq: [ "$Status", "Error" ] }, "$count", 1 ] },
cnt_e2: { $cond: [ { $eq: [ "$Status", "Warning" ] }, "$count", 1 ] },
cnt_e3: { $cond: [ { $eq: [ "$Status", "Completed" ] }, "$count", 1 ] },
} },
{ $group: { _id: "$startdate", cnt_e1: { $sum: "$cnt_e1" }, cnt_e2: { $sum: "$cnt_e2" }, cnt_e3: { $sum: "$cnt_e3" } } },
{ $sort: { _id: 1 } },
Here's the code...
db.TransactionLogs.aggregate([ { $project: { startdate: {$substr:["$startDate",0,10]},
cnt_e1: { $cond: [ { $eq: [ "$Status", "Error" ] }, "$count", 1 ] },
cnt_e2: { $cond: [ { $eq: [ "$Status", "Warning" ] }, "$count", 1 ] },
cnt_e3: { $cond: [ { $eq: [ "$Status", "Completed" ] }, "$count", 1 ] },
} },
{ $group: { _id: "$startdate", cnt_e1: { $sum: "$cnt_e1" }, cnt_e2: { $sum: "$cnt_e2" }, cnt_e3: { $sum: "$cnt_e3" } } },
{ $sort: { _id: 1 } },