mongodb aggregation find min value and other fields in nested array - mongodb

Is it possible to find in a nested array the max date and show its price then show the parent field like the actual price.
The result I want it to show like this :
{
"_id" : ObjectId("5547e45c97d8b2c816c994c8"),
"actualPrice":19500,
"lastModifDate" :ISODate("2015-05-04T22:53:50.583Z"),
"price":"16000"
}
The data :
db.adds.findOne()
{
"_id" : ObjectId("5547e45c97d8b2c816c994c8"),
"addTitle" : "Clio pack luxe",
"actualPrice" : 19500,
"fistModificationDate" : ISODate("2015-05-03T22:00:00Z"),
"addID" : "1746540",
"history" : [
{
"price" : 18000,
"modifDate" : ISODate("2015-05-04T22:01:47.272Z"),
"_id" : ObjectId("5547ec4bfeb20b0414e8e51b")
},
{
"price" : 16000,
"modifDate" : ISODate("2015-05-04T22:53:50.583Z"),
"_id" : ObjectId("5547f87e83a1dae00bc033fa")
},
{
"price" : 19000,
"modifDate" : ISODate("2015-04-04T22:53:50.583Z"),
"_id" : ObjectId("5547f87e83a1dae00bc033fe")
}
],
"__v" : 1
}
my query
db.adds.aggregate(
[
{ $match:{addID:"1746540"}},
{ $unwind:"$history"},
{ $group:{
_id:0,
lastModifDate:{$max:"$historique.modifDate"}
}
}
])
I dont know how to include other fields I used $project but I get errors
thanks for helping

You could try the following aggregation pipeline which does not need to make use of the $group operator stage as the $project operator takes care of the fields projection:
db.adds.aggregate([
{
"$match": {"addID": "1746540"}
},
{
"$unwind": "$history"
},
{
"$project": {
"actualPrice": 1,
"lastModifDate": "$history.modifDate",
"price": "$history.price"
}
},
{
"$sort": { "lastModifDate": -1 }
},
{
"$limit": 1
}
])
Output
/* 1 */
{
"result" : [
{
"_id" : ObjectId("5547e45c97d8b2c816c994c8"),
"actualPrice" : 19500,
"lastModifDate" : ISODate("2015-05-04T22:53:50.583Z"),
"price" : 16000
}
],
"ok" : 1
}

Related

Mongodb Query to get the nth document

I need to create a query in mongodb that needs to return the SECOND TO THE LAST document. I am planning to use $group for this query but i dont know what aggregation function to use. I only know $first and $last.
I have an example collection below and also include the expected output. Thank you!
"_id" : ObjectId("60dc27ac54b7c46bfa1b84b4"),
"auditlogs" : [
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84be"),
"userid" : ObjectId("5ffe702d59a9205db81fcb69"),
"action" : "ADDTRANSACTION"
},
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84bd"),
"userid" : ObjectId("5ffe644f9493e05db9245192"),
"action" : "EDITPROFILE"
},
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84bc"),
"userid" : ObjectId("5ffe64949493e05db9245197"),
"action" : "DELETETRANSACTION"
} ]
"_id" : ObjectId("60dc27ac54b7c46bfa1b75ge2"),
"auditlogs" : [
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84bb"),
"userid" : ObjectId("5ffe64b69493e05db924519b"),
"action" : "ADDTRANSACTION"
},
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84ba"),
"userid" : ObjectId("5ffe65419493e05db92451d4"),
"action" : "ADDTRANSACTION"
},
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84b9"),
"userid" : ObjectId("5ffe65689493e05db92451d9"),
"action" : "CHANGEACCESS"
},
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84b8"),
"userid" : ObjectId("5ffe65819493e05db92451dd"),
"action" : "DELETETRANSACTION"
},
{
"_id" : ObjectId("60dc27ac54b7c46bfa1b84b7"),
"userid" : ObjectId("5ffe65df9493e05db92451f3"),
"action" : "EDITPROFILE",
]
OUTPUT:
{"_id" : ObjectId("60dc27ac54b7c46bfa1b84b4"),"_id" : ObjectId("60dc27ac54b7c46bfa1b84bd"),"userid" : ObjectId("5ffe644f9493e05db9245192"),"action" : "EDITPROFILE"},
{"_id" : ObjectId("60dc27ac54b7c46bfa1b75ge2"),"_id" : ObjectId("60dc27ac54b7c46bfa1b84b8"),"userid" : ObjectId("5ffe65819493e05db92451dd"),"action" : "DELETETRANSACTION"}
You can't have two _id keys in one single object.
I've made the parent object's id to _parentId you can give it's a name anything you want except _id
Aggregation:
db.collection.aggregate([
{
$unwind: "$auditlogs"
},
{
"$project": {
"_parentId": "$_id",
"_id": "$auditlogs._id",
"action": "$auditlogs.action",
"userid": "$auditlogs.userid",
}
}
])
Playground
You can slice the array by -2 to get the last two item, then by 1 to get first one. Therefore, the array will be left the second to the last. Finally, unwind auditlogs so it can be changed from array to object which is structure that you want.
db.collection.aggregate([
{
$project: { auditlogs : { $slice: [ "$auditlogs", -2 ] } }
},
{
$project: { auditlogs : { $slice: [ "$auditlogs", 1 ] } }
},
{
$unwind: "$auditlogs"
}
])

mongodb aggregation $max and corresponding timestamp

I'm being challenged by the $group $max in an aggregation with MongoDB on Nodes Express app. Here is the a sample of the collection;
{"_id":"5b7e78cf022be03c35776bec",
"humidity":60,
"pressure":1014.18,
"temperature":26.8,
"light":2464,
"timestampiso":"2018-08-23T09:05:19.112Z",
"timestamp":1535015119112
},
{
"_id":"5b7e7892022be03c35776bea",
"humidity":60.4,
"pressure":1014.14,
"temperature":26.7,
"light":2422,
"timestampiso":"2018-08-23T09:04:18.115Z",
"timestamp":1535015058115
},
{
"_id":"5b7e7855022be03c35776be8",
"humidity":60.6,
"pressure":1014.2,
"temperature":26.6,
"light":2409,
"timestampiso":"2018-08-23T09:03:17.113Z",
"timestamp":1535014997113
}]
What I'm trying to do is to query the collection, by first retrieving the entries of the last hour based on the timestamp and then looking for highest pressure of the sample (should be 60 entries as there is one entry per minute)
What I can de is find this value. What I'm stuggling on to have the timestamp related to that max value.
When I run
db.collection("ArduinoSensorMkr1000").
aggregate([{ "$match" : {"timestamp" : {"$gte" : (Date.now()-60*60*1000)}}},
{ "$group" : {"_id" : null, maxpressure : {"$max" : "$pressure"}
}
},
{
"$project" : { "_id" : 0 }
}
])
Fine, the output is correct and I get the maxpressure as so
[{"maxpressure":1014.87}]
but what I'm trying to output is the maxpressure field but with it, its corresponding timestamp. The output should look as so
[{"maxpressure":1014.87,"timestamp":1535015058115}]
Any hints on how I get this timestamp value to show?
Thank you for your support
You can try this first need to sort your data using $sort and you can pick max value by using $first
QUERY
db.col.aggregate([
{ "$match": { "timestamp": { "$gte": (Date.now() - 60 * 60 * 1000) } } },
{ "$sort": { "pressure": -1 } },
{
"$group": {
"_id": null, "maxpressure": { "$first": "$pressure" },
"timestamp": { "$first": "$timestamp" }
}
},
{
"$project": { "_id": 0 }
}
])
DATA
[{
"_id" : "5b7e78cf022be03c35776bec",
"humidity" : 60.0,
"pressure" : 1014.18,
"temperature" : 26.8,
"light" : 2464.0,
"timestampiso" : "2018-08-23T09:05:19.112Z",
"timestamp" : 1535015119112.0
},
{
"_id" : "5b7e7892022be03c35776bea",
"humidity" : 60.4,
"pressure" : 1014.14,
"temperature" : 26.7,
"light" : 2422.0,
"timestampiso" : "2018-08-23T09:04:18.115Z",
"timestamp" : 1535015058115.0
},
{
"_id" : "5b7e7855022be03c35776be8",
"humidity" : 60.6,
"pressure" : 1014.2,
"temperature" : 26.6,
"light" : 2409.0,
"timestampiso" : "2018-08-23T09:03:17.113Z",
"timestamp" : 1535014997113.0
}]
THE OUTPUT
{
"maxpressure" : 1014.87,
"timestamp" : 1535015058115.0
}
My suggestion is to use sort/limit instead of grouping. By this way you can get entire document before project only interesting fields :
db['ArduinoSensorMkr1000'].aggregate(
[{ "$match" : {"timestamp" : {"$gte" : (Date.now()-5*60*60*1000)}}},
{$sort:{pressure:-1}},
{$limit:1},{
"$project" : { "_id" : 0,"timestamp":1,"pressure":1 }}
])

Mongo $filter with date comparison

I have the following aggregation which has a date comparison where I only want to grab documents that have the $$item.date less than the current time.
[
{ $match : { "_id" : "57b4c5f0291ebb13110b888e" } },
{ $project : {
"fulfillments" : {
$filter : {
"input" : "$fulfillments",
"as" : "item",
"cond" : { "$gte" : ["$$item.date","new Date()"]}
}
}
}
},
...
...
]
The important part that I have a question about above is the following:
"cond" : { "$gte" : ["$$item.date","new Date()"]}
This doesn't seem to be working as I can change the new Date() to 1 or 0 or pretty much any value and it still returns all documents. I need it to only return documents that have the date greater than or equal to the current date.
For example, given the following document
{
"_id": "57b4c5f0291ebb13110b888e",
"fulfillments": [
{
"_id": "582deb33bb117300010a2ae5",
"date": new Date("2016-11-23T17:00:00-0700"),
},
{
"_id": "582deb33bdf17300010a2ae5",
"date": new Date("2017-11-23T17:00:00-0700"),
}
}
Only the following fulfillment should be returned because it is 2017-11-23
{
"_id": "582deb33bdf17300010a2ae5",
"date": new Date("2017-11-23T17:00:00-0700"),
}
Update
There is question if I am giving an accurate document strucutre, so I included a screenshot below to validate this.
If you just want the current time on the machine just remove the " from the query, see below for my example
> db.test.find().pretty()
{
"_id" : "57b4c5f0291ebb13110b888e",
"fulfillments" : [
{
"_id" : "582deb33bb117300010a2ae5",
"date" : ISODate("2016-11-24T00:00:00Z")
},
{
"_id" : "582deb33bdf17300010a2ae5",
"date" : ISODate("2017-11-24T00:00:00Z")
}
]
}
>
> db.test.aggregate([
... { $match : { "_id" : "57b4c5f0291ebb13110b888e" } },
... { $project : {
... "fulfillments" : {
... $filter : {
... "input" : "$fulfillments",
... "as" : "item",
... "cond" : { "$gte" : ["$$item.date",new Date()]}
... }
... }
... }
... }
... ]).pretty()
{
"_id" : "57b4c5f0291ebb13110b888e",
"fulfillments" : [
{
"_id" : "582deb33bdf17300010a2ae5",
"date" : ISODate("2017-11-24T00:00:00Z")
}
]
}
>

MongoDB filtering out subdocuments with lookup aggregation

Our project database has a capped collection called values which gets updated every few minutes with new data from sensors. These sensors all belong to a single sensor node, and I would like to query the last data from these nodes in a single aggregation. The problem I am having is filtering out just the last of ALL the types of sensors while still having only one (efficient) query. I looked around and found the $group argument, but I can't seem to figure out how to use it correctly in this case.
The database is structured as follows:
nodes:
{
"_id": 681
"sensors": [
{
"type": "foo"
},
{
"type": "bar"
}
]
}
values:
{
"_id" : ObjectId("570cc8b6ac55850d5740784e"),
"timestamp" : ISODate("2016-04-12T12:06:46.344Z"),
"type" : "foo",
"nodeid" : 681,
"value" : 10
}
{
"_id" : ObjectId("190ac8b6ac55850d5740776e"),
"timestamp" : ISODate("2016-04-12T12:06:46.344Z"),
"type" : "bar",
"nodeid" : 681,
"value" : 20
}
{
"_id" : ObjectId("167bc997bb66750d5740665e"),
"timestamp" : ISODate("2016-04-12T12:06:46.344Z"),
"type" : "bar",
"nodeid" : 200,
"value" : 20
}
{
"_id" : ObjectId("110cc9c6ac55850d5740784e"),
"timestamp" : ISODate("2016-04-09T12:06:46.344Z"),
"type" : "foo",
"nodeid" : 681,
"value" : 12
}
so let's imagine I want the data from node 681, I would want a structure like this:
nodes:
{
"_id": 681
"sensors": [
{
"_id" : ObjectId("570cc8b6ac55850d5740784e"),
"timestamp" : ISODate("2016-04-12T12:06:46.344Z"),
"type" : "foo",
"nodeid" : 681,
"value" : 10
},
{
"_id" : ObjectId("190ac8b6ac55850d5740776e"),
"timestamp" : ISODate("2016-04-12T12:06:46.344Z"),
"type" : "bar",
"nodeid" : 681,
"value" : 20
}
]
}
Notice how one value of foo is not queried, because I want to only get the latest value possible if there are more than one value (which is always going to be the case). The ordering of the collection is already according to the timestamp because the collection is capped.
I have this query, but it just gets all the values from the database (which is waaay too much to do in a lifetime, let alone one request of the web app), so I was wondering how I would filter it before it gets aggregated.
query:
db.nodes.aggregate(
[
{
$unwind: "$sensors"
},
{
$match:{
nodeid: 681
}
},
{
$lookup:{
from: "values", localField: "sensors.type", foreignField: "type", as: "sensors"
}
}
}
]
)
Try this
// Pipeline
[
// Stage 1 - sort the data collection if not already done (optional)
{
$sort: {
"timestamp":1
}
},
// Stage 2 - group by type & nodeid then get first item found in each group
{
$group: {
"_id":{type:"$type",nodeid:"$nodeid"},
"sensors": {"$first":"$$CURRENT"} //consider using $last if your collection is on reverse
}
},
// Stage 3 - project the fields in desired
{
$project: {
"_id":"$sensors._id",
"timestamp":"$sensors.timestamp",
"type":"$sensors.type",
"nodeid":"$sensors.nodeid",
"value":"$sensors.value"
}
},
// Stage 4 - group and push it to array sensors
{
$group: {
"_id":{nodeid:"$nodeid"},
"sensors": {"$addToSet":"$$CURRENT"}
}
}
]
as far as I got document structure, there is no need to use $lookup as all data is in readings(values) collection.
Please see proposed solution:
db.readings.aggregate([{
$match : {
nodeid : 681
}
},
{
$group : {
_id : {
type : "$type",
nodeid : "$nodeid"
},
readings : {
$push : {
timestamp : "$timestamp",
value : "$value",
id : "$_id"
}
}
}
}, {
$project : {
_id : "$_id",
readings : {
$slice : ["$readings", -1]
}
}
}, {
$unwind : "$readings"
}, {
$project : {
_id : "$readings.id",
type : "$_id.type",
nodeid : "$_id.nodeid",
timestamp : "$readings.timestamp",
value : "$readings.value",
}
}, {
$group : {
_id : "$nodeid",
sensors : {
$push : {
_id : "$_id",
timestamp : "$timestamp",
value : "$value",
type:"$type"
}
}
}
}
])
and output:
{
"_id" : 681,
"sensors" : [
{
"_id" : ObjectId("110cc9c6ac55850d5740784e"),
"timestamp" : ISODate("2016-04-09T12:06:46.344Z"),
"value" : 12,
"type" : "foo"
},
{
"_id" : ObjectId("190ac8b6ac55850d5740776e"),
"timestamp" : ISODate("2016-04-12T12:06:46.344Z"),
"value" : 20,
"type" : "bar"
}
]
}
Any comments welcome!

MongoDB $sum and $avg of sub documents

I need to get $sum and $avg of subdocuments, i would like to get $sum and $avg of Channels[0].. and other channels as well.
my data structure looks like this
{
_id : ... Location : 1,
Channels : [
{ _id: ...,
Value: 25
},
{
_id: ... ,
Value: 39
},
{
_id: ..,
Value: 12
}
]
}
In order to get the sum and average of the Channels.Value elements for each document in your collection you will need to use mongodb's Aggregation processing. Further, since Channels is an array you will need to use the $unwind operator to deconstruct the array.
Assuming that your collection is called example, here's how you could get both the document sum and average of the Channels.Values:
db.example.aggregate( [
{
"$unwind" : "$Channels"
},
{
"$group" : {
"_id" : "$_id",
"documentSum" : { "$sum" : "$Channels.Value" },
"documentAvg" : { "$avg" : "$Channels.Value" }
}
}
] )
The output from your post's data would be:
{
"_id" : SomeObjectIdValue,
"documentSum" : 76,
"documentAvg" : 25.333333333333332
}
If you have more than one document in your collection then you will see a result row for each document containing a Channels array.
Solution 1: Using two groups based this example:
previous question
db.records.aggregate(
[
{ $unwind: "$Channels" },
{ $group: {
_id: {
"loc" : "$Location",
"cId" : "$Channels.Id"
},
"value" : {$sum : "$Channels.Value" },
"average" : {$avg : "$Channels.Value"},
"maximun" : {$max : "$Channels.Value"},
"minimum" : {$min : "$Channels.Value"}
}},
{ $group: {
_id : "$_id.loc",
"ChannelsSumary" : { $push :
{ "channelId" : '$_id.cId',
"value" :'$value',
"average" : '$average',
"maximun" : '$maximun',
"minimum" : '$minimum'
}}
}
}
]
)
Solution 2:
there is property i didn't show on my original question that might of help "Channels.Id" independent from "Channels._Id"
db.records.aggregate( [
{
"$unwind" : "$Channels"
},
{
"$group" : {
"_id" : "$Channels.Id",
"documentSum" : { "$sum" : "$Channels.Value" },
"documentAvg" : { "$avg" : "$Channels.Value" }
}
}
] )