Using Go driver for Mongo, I have a simple collection, each document is my last visit to the city. How to find all documents, most recent visit to field destination.
Field _id is auto-generated and incrementing chronologically.
[
{
"_id": "62e0d290fd1a769bb8ad13ba",
"destination": "NY"
"airline": "Delta"
},
{
"_id": "62e0d2defd1a769bb8ad13bb",
"destination": "DC"
"airline": "Southwest"
},
{
"_id": "62e0d2defd1a769bb8ad13bc",
"destination": "DC"
"airline": "American"
{
"_id": "62e0d2defd1a769bb8ad13bd",
"destination": "NY"
"airline": "JetBlue"
}
]
Expected output (most recent inserted document for visit to each city)
[
{
"_id": "62e0d2defd1a769bb8ad13bc",
"destination": "DC"
"airline": "American"
{
"_id": "62e0d2defd1a769bb8ad13bd",
"destination": "NY"
"airline": "JetBlue"
}
]
Hope this answer will help to you
db.collection.aggregate([
{
"$group": {
"_id": "$destination",
"airline": {
"$last": "$airline"
},
"destination": {
"$last": "$destination"
},
"id": {
"$last": "$_id"
}
}
},
{
"$project": {
_id: "$id",
destination: 1,
airline: 1
}
},
{
"$sort": {
_id: 1,
}
}
])
Related
I would like to get the unique elements of all arrays in a collection. Consider the following collection
[
{
"collection": "collection",
"myArray": [
{
"name": "ABC",
"code": "AB"
},
{
"name": "DEF",
"code": "DE"
}
]
},
{
"collection": "collection",
"myArray": [
{
"name": "GHI",
"code": "GH"
},
{
"name": "DEF",
"code": "DE"
}
]
}
]
I can achieve this by using $unwind and $group like this:
db.collection.aggregate([
{
$unwind: "$myArray"
},
{
$group: {
_id: null,
data: {
$addToSet: "$myArray"
}
}
}
])
And get the output:
[
{
"_id": null,
"data": [
{
"code": "GH",
"name": "GHI"
},
{
"code": "DE",
"name": "DEF"
},
{
"code": "AB",
"name": "ABC"
}
]
}
]
However, the array "myArray" will have a lot of elements (about 6) and the number of documents passed into this stage of the pipeline will be about 600. So unwinding the array would give me a total of 3600 documents being processed. I would like to know if there's a way for me to achieve the same result without unwinding
You can use below aggregation
db.collection.aggregate([
{ "$group": {
"_id": null,
"data": { "$push": "$myArray" }
}},
{ "$project": {
"data": {
"$reduce": {
"input": "$data",
"initialValue": [],
"in": { "$setUnion": ["$$this", "$$value"] }
}
}
}}
])
Output
[
{
"_id": null,
"data": [
{
"code": "AB",
"name": "ABC"
},
{
"code": "DE",
"name": "DEF"
},
{
"code": "GH",
"name": "GHI"
}
]
}
]
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.
I have a dataset in MongoDB that looks like this:
{ "name": "Tom's", "category": "coffee shop" },
{ "name": "Red Lobster", "category": "restaurant" },
{ "name": "Tom's", "category": "coffee shop" },
{ "name": "Starbucks", "category": "coffee shop" },
{ "name": "Central Park", "category": "park" },
{ "name": "Office", "category": "office" },
{ "name": "Red Lobster", "category": "restaurant" },
{ "name": "Home", "category": "home" },
{ ... } // and so on
How can I find the most common value for specific categories? For example, the most common occurring value for coffee shop and restaurant should be Tom's and Red Lobster, respectively.
My current $aggregate query only seems to list the most common occurring value among ALL of the dataset:
db.collection.aggregate(
{ "$group": { "_id": { "name": "$name" }, "count": { "$sum":1 } }},
{ "$group": { "_id": "$_id.name", "count": { "$sum": "$count" } }},
{ "$sort": { "count":-1 }}
)
You can try the below query.
$group on category and name to get the count for each category and name combination.
$sort the input documents by category and count desc.
$group on category with $first to pick the document with most occurrences.
db.collection_name.aggregate([
{
"$group": {
"_id": {
"category": "$category",
"name": "$name"
},
"count": {
"$sum": 1
}
}
},
{
"$sort": {
"_id.category": 1,
"count": -1
}
},
{
"$group": {
"_id": {
"category": "$_id.category"
},
"name": {
"$first": "$_id.name"
},
"count": {
"$first": "$count"
}
}
}
])
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.
I've got collection that looks like:
[{
"org": "A",
"type": "simple",
"payFor": 3,
"price": 100
},
{
"org": "A",
"type": "custom",
"payFor": 2,
"price": 115
},
{
"org": "B",
"type": "simple",
"payFor": 1,
"price": 110
},
{
"org": "B",
"type": "custom",
"payFor": 2,
"price": 200
},
{
"org": "B",
"type": "custom",
"payFor": 4,
"price": 220
}]
And need to produce result with query to perform group by "org" where payments appears for only first "payFor" prices in "type".
I'm trying to use expression result by $slice operator in $add but this is not works.
pipeline:
[{
"$group": {
"_id": {
"org": "$org",
"type": "$type"
},
"payFor": {
"$max": "$payFor"
},
"count": {
"$sum": 1
},
"prices": {
"$push": "$price"
}
}
},
{
"$group": {
"_id": "$_id.org",
"payments": {
"$push": {
"type": "$_id.type",
"forFirst": "$payFor",
"sum": {
"$cond": [
{
"$gte": [
"$payFor",
"$count"
]
},
{
"$add": {
"$prices": {
"$slice": "$count"
}
}
},
{
"$add": "$prices"
}
]
}
}
}
}
}]
I know that it is possible to traverse unwinded prices and pick only "payFor" count of them. but result collections are more rich than in example above and this operation will produce some unecessary overheads.
Need some advice from community. Please. Thanks.