Finding/Counting Duplicate Values in Array in MongoDB - mongodb

Question

I am new to the mongo database. Using Robo3t software
I have to find out duplicate values inside an array based on channel_id.
I did a research and found that aggregation needs to be used to do grouping and find respective count.
I have developed the following query but results are not as expected.
Sample Documents:
{
"_id" : ObjectId("59b674d141b47e5401897d31"),
"subscribed_channels" : [
{
"channel_id" : "1001",
"channel_name" : "StarPlus",
"channelPrice":"100"
},
{
"channel_id" : "1002",
"channel_name" : "StarGold",
"channelPrice":"75"
},
{
"channel_id" : "1001",
"channel_name" : "StarPlus",
"channelPrice":"100"
},
{
"channel_id" : "1003",
"channel_name" : "SetMax",
"channelPrice":"80"
}
],
"viewer_account_id" : "59b6745b41b47e5401143b3d",
"public_id_type" : "PHONE_NUMBER",
"viewer_id" : "[phone]",
"role" : "CONSUMER",
"active" : true,
"date_time_created" : NumberLong(1505129681330),
"date_time_modified" : NumberLong(1569320824387)
}
{
"_id" : ObjectId("59b674d141b47e5401897d31"),
"subscribed_channels" : [
{
"channel_id" : "1001",
"channel_name" : "StarPlus",
"channelPrice":"100"
},
{
"channel_id" : "1002",
"channel_name" : "StarGold",
"channelPrice":"75"
},
{
"channel_id" : "1001",
"channel_name" : "StarPlus",
"channelPrice":"100"
},
{
"channel_id" : "1001",
"channel_name" : "StarPlus",
"channelPrice":"100"
}
],
"viewer_account_id" : "59b6745b41b47e5401143c56",
"public_id_type" : "PHONE_NUMBER",
"viewer_id" : "[phone]",
"role" : "CONSUMER",
"active" : true,
"date_time_created" : NumberLong(1505129681330),
"date_time_modified" : NumberLong(1569320824387)
}
Above are just 2 records of document viewers
Query :
db.getCollection('viewers').aggregate([
{
"$group" :
{_id:{
//viewer_id:"$consumer_id",
enterprise_id:"$subscribed_channels.channel_id",
},
"viewer_id": {
$first: "$viewer_id"
},
count:{$sum:1}
}},
{
"$match": {"count": { "$gt": 1 }}
}
])
Actual Output :
{
"_id" : {
"enterprise_id" : [
"1001",
"1001",
"1002",
"1003"
]
},
"consumer_id" : "[phone]",
"count" : 2.0
}
{
"_id" : {
"enterprise_id" : [
"1001",
"1002",
"1001",
"1001
]
},
"consumer_id" : "[phone]",
"count" : 2.0
}
Expected Output :
I want to group based on subscribed_channels.channel_id and get a count respectively
{
"_id" : {
"enterprise_id" : [
"1001",
"1001",
"1002",
"1003"
]
},
"consumer_id" : "[phone]",
"count" : 2.0
}
{
"_id" : {
"enterprise_id" : [
"1001",
"1001",
"1001",
"1002
]
},
"consumer_id" : "[phone]",
"count" : 3.0
}
Grouping is not happening based on channel_id, also the count is incorrect.
The count is not even giving me no of channel-id subscribed, also not giving duplicate channel_ids.
Please guide me in building a query that gives the correct result.

Answer 1

Try below query :
Query :
db.collection.aggregate([
/** project only needed fields & transform fields as you like */
{
$project: {
customer_id: "$viewer_id",
enterprise_id: "$subscribed_channels.channel_id",
count: {
/** Subtract size of original array & newly formed array which has unique values to get count of duplicates */
$subtract: [
{
$size: "$subscribed_channels.channel_id" // get size of original array
},
{
$size: {
$setUnion: ["$subscribed_channels.channel_id", []] // This will give you an array with unique elements & get size of it
}
}
]
}
}
}
]);
Test : MongoDB-Playground