I'm quite new to MongoDB and I am currently facing a situation. Below are 2 sample records from the whole database that I have :
{
"_id": 1,
"Record": 1,
"Link": [ "https://wikileaks.org/plusd/cables/1979PANAMA06344_e.html" ],
"Location": [ "USA", "PAN", "USA", "USA", "PAN" ],
"Organization": [ "GN", "SOUTHCOM", "UCMJ", "PRC" ],
"Date": [ "2016" ],
"People": [ "P.Walter" ]
}
{
"_id": 2,
"Record": 2,
"Link": [ "https://wikileaks.org/gifiles/docs/11/111533_-latam-centam-brief-110822-.html" ],
"Location": [ "NIC", "GTM", "JAM", "GTM", "PAN" ],
"Organization": [ "CENTAM", "Calibre Mining Corporation", "STRATFOR", "Alder Resources" ],
"Date": [ "2013" ],
"People": [ "Daniel Ortega", "Hugo Chavez", "Paulo Gregoire" ]
}
Basically, I'm trying to get an output like this :
{
"Country": "US",
"Years": [
{
"Year": "2016",
"Links": [ "https://wikileaks.org/gifiles/docs/11/111533_-latam-centam-brief-110822-.html",
"https://wikileaks.org/plusd/cables/1979PANAMA06344_e.html",
"https://wikileaks.org/gifiles/docs/90/9058_wax-12312008-csv-.html" ]
},
{
"Year": "2013",
"Links": [ ""https://wikileaks.org/gifiles/docs/11/111533_-latam-centam-brief-110822-.html",
"https://wikileaks.org/plusd/cables/1979PANAMA06344_e.html",
"https://wikileaks.org/gifiles/docs/90/9058_wax-12312008-csv-.html" ]
}
]
"Link_Count": 6
}
{
"Country": "UK",
"Years": [
{
"Year": "2009",
"Links": [ "https://wikileaks.org/gifiles/docs/11/111533_-latam-centam-brief-110822-.html",
"https://wikileaks.org/plusd/cables/1979PANAMA06344_e.html",
"https://wikileaks.org/gifiles/docs/90/9058_wax-12312008-csv-.html" ]
},
{
"Year": "2011",
"Links": [ ""https://wikileaks.org/gifiles/docs/11/111533_-latam-centam-brief-110822-.html",
"https://wikileaks.org/plusd/cables/1979PANAMA06344_e.html"]
}
]
"Link_Count": 5
}
I've tried to aggregate it, but I couldn't achieve what I want like I've given in the output. Here's my query :
db.test.aggregate([
{
"$unwind": "$Location"
},
{
"$group" : {
"_id": {
"Country": "$Location",
"Year": "$Date",
"Links": "$Link"
},
Loc: {
$addToSet: "$Location"
}
}
},
{
"$unwind": "$Loc"
},
{
"$group": {
"_id": "$Loc",
"Years": { "$push": {
"Year": "$_id.Year",
"Links": "$_id.Links"
}
}
}
}
]).toArray()
I used $unwind and $addToSet on $Location because there are duplicates found within $Location. I'm open to any suggestions or solution so please do tell! Thanks in advance!
You can use :
db.test.aggregate([{
"$unwind": "$Location"
}, {
"$unwind": "$Date"
}, {
"$unwind": "$Link"
}, {
"$group": {
"_id": {
"Country": "$Location",
"Year": "$Date"
},
Links: {
$addToSet: "$Link"
}
}
}, {
"$group": {
"_id": "$_id.Country",
Years: {
$push: {
"Year": "$_id.Year",
"Links": "$Links"
}
},
Link_Count: { $sum: { $size: "$Links" } }
}
}])
The idea is to $unwind all arrays to be able to $push link into a new array, and to count the grouped record with $size for the last $group stage.
Related
Given the following input:
[
{
"statuses": [
{
"status": "allowed",
"count": 3,
"events_count": [
"2001",
"1001",
"1001"
]
}
],
"date": "2022-09-10 15:00",
"_id": "2022-09-10 15:00"
}
]
I need count the number of occurrences of stauses.events_count, so the output would be:
[
{
"statuses": [
{
"status": "allowed",
"count": 3,
"events_count": [
{"type": "2001", "count": 1},
{"type": "1001", "count": 2},
]
}
],
"date": "2022-09-10 15:00",
"_id": "2022-09-10 15:00"
}
]
What I've tried
This is what I got so far:
db.collection.aggregate([
{
"$unwind": "$statuses"
},
{
"$unwind": "$statuses.events_count"
},
{
"$group": {
"_id": {
"event_count": "$statuses.events_count",
"status": "$statuses.status",
"date": "$date",
"count": "$statuses.count"
},
"occurences": {
"$sum": 1
}
}
}
])
Which produces:
[
{
"_id": {
"count": 3,
"date": "2022-09-10 15:00",
"event_count": "2001",
"status": "allowed"
},
"occurences": 1
},
{
"_id": {
"count": 3,
"date": "2022-09-10 15:00",
"event_count": "1001",
"status": "allowed"
},
"occurences": 2
}
]
I'm having difficulties grouping everything back together. I tried grouping by date and pushing back to a 'statuses' array, but it produces two items in the array (with status==allowed), rather than 1 item with status==allowed
You did 2 $unwinds, so it should be 2 $groups in reverse order:
{
"$group": {
"_id": {
"status": "$_id.status",
"count": "$_id.count",
"date": "$_id.date"
},
"event_count": {
"$push": {
"type": "$_id.event_count",
"count": "$occurences"
}
}
}
},
{
"$group": {
"_id": "$_id.date",
"date": {"$last": "$_id.date"},
"statuses": {
"$push": {
"status": "$_id.status",
"count": "$_id.count",
"event_count": "$event_count"
}
}
}
}
So I have a parent document with users, as well as an array that has users too. I want to add the DisplayName from the nested users array to the aggregation output. Any ideas?
Output I'm looking to achieve:
[
{
"user": {
"_id": "11",
"Name": "Dave",
"DocID": "1",
"DocDisplyName": "ABC"
},
{
"user": {
"_id": "33",
"Name": "Henry",
"DocID": "1",
"DocDisplyName": "ABC",
"BranchDisplayName:"BranchA"
}
}
]
And so on.. So an array of all users and for users that belong to a branch, add the branch display Name to the output.
// Doc 1
{
"_id": "1",
"DisplayName": "ABC",
"Users": [
{ "_id": "11", "Name": "Dave" },
{ "_id": "22", "Name": "Steve" }
],
"Branches": [
{
"_id": "111",
"DisplayName": "BranchA",
"Users": [
{ "_id": "33", "Name": "Henry" },
{ "_id": "44", "Name": "Josh" },
],
},
{
"_id": "222",
"DisplayName": "BranchB",
"Users": [
{ "_id": "55", "Name": "Mark" },
{ "_id": "66", "Name": "Anton" },
],
}
]
}
``Doc 2
{
"_id": "2",
"DisplayName": "DEF",
"Users": [
{ "_id": "77", "Name": "Josh" },
{ "_id": "88", "Name": "Steve" }
],
"Branches": [
{
"_id": "333",
"DisplayName": "BranchA",
"Users": [
{ "_id": "99", "Name": "Henry" },
{ "_id": "10", "Name": "Josh" },
],
},
{
"_id": "444",
"DisplayName": "BranchB",
"Users": [
{ "_id": "112", "Name": "Susan" },
{ "_id": "112", "Name": "Mary" },
],
}
]
}
Collection.aggregate([
{
$addFields: {
branchUsers: {
$reduce: {
input: "$Branches.Users",
initialValue: [],
in: {
$concatArrays: ["$$this", "$$value"],
},
},
},
},
},
{
$addFields: {
user: {
$concatArrays: ["$branchUsers", "$Users"],
},
},
},
{
$addFields: {
"user.DocID": "$_id","user.DocDisaplyName": "$DisplayName"
},
},
{
$unwind: "$user",
},
{
$project: {
_id: 0,
user: 1,
},
}
])
Thanks in advance!
OK I found a solution.
{
$addFields: {
"branchUsers.BranchDisplayName": {
$let: {
vars: {
first: {
$arrayElemAt: [ "$Branches", 0 ]
}
},
in: "$$first.DisplayName"
}
}
}
},
This creates the field only for the users that belong to the branch
Record is database:
[
{
"title": "title1",
"author": [
{
"name": "user1",
"register": true
},
{
"name": "user2",
"register": true
}
],
"tags": [
"tag1",
"tag2",
"tag3"
]
},
{
"title": "title2",
"author": [
{
"name": "user1",
"register": true
},
{
"name": "user2",
"register": true
}
],
"tags": [
"tag1",
"tag2",
"tag3"
]
},
{
"title": "title3",
"author": [
{
"name": "user1",
"register": true
},
{
"name": "user2",
"register": true
}
],
"tags": [
"tag1",
"tag2",
"tag3"
]
}
]
expected output:
{"tag":"tag1", "titles":["title1","title2","title3"], "size":3}
{"tag":"tag2", "titles":["title2","title4"], "size":2}
Can someone help with aggregate query?
You can use group
$unwind to deconstruct the array
$group to regroup the based on tags
$project to show the desired output
Here is the code,
db.collection.aggregate([
{ "$unwind": "$tags" },
{
"$group": {
"_id": "$tags",
"titles": { "$push": "$title" }
}
},
{
$project: {
tag: "$_id",
titles: 1,
size: { $size: "$titles" },
_id: "$$REMOVE"
}
}
])
Working Mongo playground
Example JSON：
{
"groups": [
{
"_id": 1,
"name": "g1"
},
{
"_id": 2,
"name": "g2"
}
],
"items": [
{
"_id": 1,
"name": "item1",
"gid": 1
},
{
"_id": 2,
"name": "item2",
"gid": 2
}
]
}
How to associate two arrays and count ？I tried to use aggregate, I didn't get the results I wanted.
Required Result:
Or can directly find all the items associated with it, perfect....
{"groups": [
{
"_id": 1,
"name": "g1",
"count": 1,
"items": [
{
"_id": 1,
"name": "item1"
}
]
},
{
"_id": 2,
"name": "g2",
"count": 1,
"items": [
{
"_id": 2,
"name": "item2"
}
]
}
]}
db.getCollection('collection').aggregate([
{$unwind:{
path:"$groups",
preserveNullAndEmptyArrays:true
}},
{$unwind:{
path:"$items",
preserveNullAndEmptyArrays:true
}},
{$redact: {$cond: [{
$eq: [
"$groups._id",
"$items.gid"
]
},
"$$KEEP",
"$$PRUNE"
]
}
},
{$project:{
_id:1,
groups_id:"$groups._id",
group_name:"$groups.name",
item_data:{
_id:"$items._id",
name:"$items.name",
}
}},
{
$group:{
_id:"$groups_id",
name:{$first:"$group_name"},
count:{$sum:1},
items:{$push:"$item_data"}
}
}
])
I have Json which have values like state_city details this contains information like which city belongs to which state -
Need to query it for particular state name which will gives me all cities that belongs to that state.
db.collection.find({
"count": 10,
"state.name": "MP"
})
[
{
"collection": "collection1",
"count": 10,
"state": [
{
"name": "MH",
"city": "Mumbai"
},
{
"name": "MH",
"city": "Pune"
},
{
"name": "UP",
"city": "Kanpur"
},
{
"name": "CG",
"city": "Raipur"
}
]
},
{
"collection": "collection2",
"count": 20,
"state": [
{
"name": "MP",
"city": "Indore"
},
{
"name": "MH",
"city": "Bhopal"
},
{
"name": "UP",
"city": "Kanpur"
},
{
"name": "CG",
"city": "Raipur"
}
]
}
]
You have to use aggregate query to get only matching elements in array :
db.collection.aggregate([{
$unwind: "$content.state"
},
{
$match: {
"content.state.name": "MH",
"count": 10
}
},
{
$group: {
_id: "$content.state.city",
}
},
{
$addFields: {
key: 1
}
},
{
$group: {
_id: "$key",
cities: {
$push: "$_id"
}
}
},
{
$project: {
_id: 0,
cities: 1
}
}
])
This query will return :
{
"cities": [
"Pune",
"Mumbai"
]
}
The following query would be the solution.
db.collection.find({ "count": 10, "state":{"name": "MP"}})
For more complex queries, $elemMatch is also available.