Is it possible to sort an array by occurrences?
For Example, given
{
"_id": {
"$oid": "60d20d342c7951852a21s53a"
},
"site": "www.xyz.ie",
"A": ["mary", "jamie", "john", "mary", "mary", "john"],
}
return
{
"_id": {
"$oid": "60d20d342c7951852a21s53a"
},
"site": "www.xyz.ie",
"A": ["mary", "jamie", "john", "mary", "mary", "john"],
"sorted_A" : ["mary","john","jamie"]
}
I am able to get it most of the way there but I cannot figure out how to join them all back together in an array.
I have been using an aggregation pipeline
Starting with $match to find the site I want
Then $unwind on with path: "$A"
Next $sortByCount on "$A"
???? I can't figure out how to group it all back together.
Here is the pipeline:
[
{
'$match': {
'site': 'www.xyz.ie'
}
}, {
'$unwind': {
'path': '$A'
}
}, {
'$sortByCount': '$A'
}, {
????
}
]
$group nu _id and A, get first site and count total elements
$sort by count in descending order
$group by only _id and get first site, and construct array of A
[
{ $match: { site: "www.xyz.ie" } },
{ $unwind: "$A" },
{
$group: {
_id: { _id: "$_id", A: "$A" },
site: { $first: "$site" },
count: { $sum: 1 }
}
},
{ $sort: { count: -1 } },
{
$group: {
_id: "$_id._id",
site: { $first: "$site" },
A: { $push: "$_id.A" }
}
}
]
Playground
Related
I have the following document structure.
{
_id: ...,
unique_id: 1234,
config_no: 1,
configs: [
{
data: "qwertyuiop" // random string
},
{
data: "asdfghjkl" // random string
}
]
}
I want to update value of data from one of the configs. The index of the config that needs to be updated is available in the config_no key.
Is there any way to update the value without querying the document.
This is what I am currently doing
doc = db.collection.findOne({"unique_id": 1234})
config_no = doc.config_no
db.collection.updateOne(
{"unique_id": 1234},
{"$set": {"configs."+config_no+".data": "zxcvbnm"}} //"configs.1.data"
)
Following is something what i would like to achive.
db.collection.updateOne(
{"unique_id": 1234},
{"$set": {"configs.${config_no}.data": "zxcvbnm"}}
)
You can $unwind with includeArrayIndex option. Use the index to perform conditional update and $merge back into the collection.
db.collection.aggregate([
{
$match: {
unique_id: 1234
}
},
{
"$unwind": {
path: "$configs",
includeArrayIndex: "idx"
}
},
{
$set: {
"configs.data": {
"$cond": {
"if": {
$eq: [
"$config_no",
"$idx"
]
},
"then": "zxcvbnm",
"else": "$configs.data"
}
}
}
},
{
$group: {
_id: "$_id",
config_no: {
$first: "$config_no"
},
configs: {
$push: "$configs"
},
unique_id: {
$first: "$unique_id"
}
}
},
{
"$merge": {
"into": "collection",
"on": "_id",
"whenMatched": "merge"
}
}
])
Mongo Playground
I was wondering if it was possible to somehow use the $match operator within the $sum function for aggregation.
{ "$unwind": "$info.avatarInfoList" },
{ "$unwind": "$info.avatarInfoList.equipList" },
{ "$unwind": "$info.avatarInfoList.equipList.flat.reliquarySubstats" },
{
"$project": {
"name" : "$name",
"character" : "$info.avatarInfoList.avatarId",
"artifact" : "$info.avatarInfoList.equipList.itemId",
"statValue" : {
"$sum": [
{"$match" : { "$info.avatarInfoList.equipList.flat.reliquarySubstats.appendPropId" : "FIGHT_PROP_CRITICAL_HURT" } },
{"$multiply": [2, {"$match" : { "$info.avatarInfoList.equipList.flat.reliquarySubstats.appendPropId" : "FIGHT_PROP_CRITICAL" } }]}
]
},
}
},
{ "$sort": { "statValue": -1 }},
{ '$limit' : 30 }
]).to_list(length=None)
print(data)
I want to be able to use the value of the $sum operator within the project fields somehow, I just don't really understand what the right approach would be for this.
Sample Input (may be too long):
https://www.toptal.com/developers/hastebin/ixamekaxoq.json
Sample Output:
( 2 * FIGHT_PROP_CRITICAL ) + FIGHT_PROP_CRITICAL_HURT sorted from highest to lowest for each item.
{name: hat, character: Slayer, artifact: 13, statValue : 25.6}
There are still a few ambiguities about how you want to aggregate your data, but using the full document from your link, here's one way to produce the output you want.
N.B.: Weapons in the "equipList" don't have "reliquarySubstats" so they show a "statValue" of null in the output.
db.collection.aggregate([
{"$unwind": "$info.avatarInfoList"},
{"$unwind": "$info.avatarInfoList.equipList"},
{
"$project": {
"_id": 0,
"name": 1,
"character": "$info.avatarInfoList.avatarId",
"artifact": "$info.avatarInfoList.equipList.itemId",
"statValue": {
"$reduce": {
"input": "$info.avatarInfoList.equipList.flat.reliquarySubstats",
"initialValue": 0,
"in": {
"$switch": {
"branches": [
{
"case": {"$eq": ["$$this.appendPropId", "FIGHT_PROP_CRITICAL"]},
"then": {
"$add": [
"$$value",
{"$multiply": [2, "$$this.statValue"]}
]
}
},
{
"case": {"$eq": ["$$this.appendPropId", "FIGHT_PROP_CRITICAL_HURT"]},
"then": {"$add": ["$$value", "$$this.statValue"]}
}
],
"default": "$$value"
}
}
}
}
}
},
{"$sort": {"statValue": -1}}
])
Try it on mongoplayground.net.
It's not quite clear what you want to achieve, but as mentioned you want to be using $cond here.
like so:
{
"$project": {
"statValue": {
"$sum": [
{
$cond: [
{ // if this condition is true (prop id = prop critical hurt )
$eq: [
"$info.avatarInfoList.equipList.flat.reliquarySubstats.appendPropId",
"FIGHT_PROP_CRITICAL_HURT"
]
},
{ // then use this value for the "$sum"
"$multiply": [
2,
"$info.avatarInfoList.equipList.flat.reliquarySubstats.statValue"
]
},
0 // otherwise use this value for the sum.
]
}
]
}
}
Mongo Playground
I have a database collection that has objects like this:
{
"_id": ObjectId("something"),
"name_lower": "total",
"name": "Total",
"mounts": [
[
"mount1",
"instance1"
],
[
"mount2",
"instance1"
],
[
"mount1",
"instance2"
],
[
"mount2",
"instance2"
]
]
}
Say I want to remove every mount that has the instance instance2, How would I go about doing that? I have been searching for quite a while.
You can do something like this
[
{
$unwind: "$mounts"
},
{
$match: {
"mounts": {
$ne: "instance2"
}
}
},
{
$group: {
_id: "$_id",
name: {
$first: "$name"
},
mounts: {
$push: "$mounts"
}
}
}
]
Working Mongo playground
This answer is based on #varman answer but more pythonic and efficient.
The first stage should be a $match condition to filter out documents that don't need to be updated.
Since the mounts key consists of a nested array, we have to $unwind it, so that we can remove array elements that need to be removed.
We have to apply the $match condition again to filter out the element that has to be removed.
Finally, we have to $group the pipeline by _id key, so that the documents which got $unwind in the previous stage will be groupped into a single document.
from pymongo import MongoClient
client = MongoClient("<URI-String>")
col = client["<DB-Name"]["<Collection-Name>"]
count = 0
for cursor in col.aggregate([
{
"$match": {
"mounts": {"$ne": "instance2"}
}
},
{
"$unwind": "$mounts"
},
{
"$match": {
"mounts": {"$ne": "instance2"}
}
},
{
"$group": {
"_id": "$_id",
"newMounts": {
"$push": "$mounts"
}
}
},
]):
# print(cursor)
col.update_one({
"_id": cursor["_id"]
}, {
"$set": {
"mounts": cursor["newMounts"]
}
})
count += 1
print("\r", count, end="")
print("\n\nDone!!!")
generate unique id in nested document - Pymongo
my database looks like this...
{
"_id":"5ea661d6213894a6082af6d1",
"blog_id":"blog_one",
"comments": [
{
"user_id":"1",
"comment":"comment for blog one this is good"
},
{
"user_id":"2",
"comment":"other for blog one"
},
]
}
I want to add unique id in each and every comment,
I want it to output like this,
{
"_id":"5ea661d6213894a6082af6d1",
"blog_id":"blog_one",
"comments": [
{
"id" : "something" (auto generate unique),
"user_id":"1",
"comment":"comment for blog one this is good"
},
{
"id" : "something" (auto generate unique),
"user_id":"2",
"comment":"other for blog one"
},
]
}
I'm using PyMongo, is there a way to update this kind of document?
it's possible or not?
This update will add an unique id value to each of the comments array with nested documents. The id value is calculated based upon the present time as milliseconds. This value is incremented for each array element to get the new id value for the nested documents of the array.
The code runs with MongoDB version 4.2 and PyMongo 3.10.
pipeline = [
{
"$set": {
"comments": {
"$map": {
"input": { "$range": [ 0, { "$size": "$comments" } ] },
"in": {
"$mergeObjects": [
{ "id": { "$add": [ { "$toLong" : datetime.datetime.now() }, "$$this" ] } },
{ "$arrayElemAt": [ "$comments", "$$this" ] }
]
}
}
}
}
}
]
collection.update_one( { }, pipeline )
The updated document:
{
"_id" : "5ea661d6213894a6082af6d1",
"blog_id" : "blog_one",
"comments" : [
{
"id" : NumberLong("1588179349566"),
"user_id" : "1",
"comment" : "comment for blog one this is good"
},
{
"id" : NumberLong("1588179349567"),
"user_id" : "2",
"comment" : "other for blog one"
}
]
}
[ EDIT ADD ]
The following works from mongo shell. It adds unique id for the comments array's nested documents - unique across the documents.
db.collection.aggregate( [
{
"$unwind": "$comments" },
{
"$group": {
"_id": null,
"count": { "$sum": 1 },
"docs": { "$push": "$$ROOT" },
"now": { $first: "$$NOW" }
}
},
{
"$addFields": {
"docs": {
"$map": {
"input": { "$range": [ 0, "$count" ] },
"in": {
"$mergeObjects": [
{ "comments_id": { "$add": [ { "$toLong" : "$now" }, "$$this" ] } },
{ "$arrayElemAt": [ "$docs", "$$this" ] }
]
}
}
}
}
},
{
"$unwind": "$docs"
},
{
"$addFields": {
"docs.comments.comments_id": "$docs.comments_id"
}
},
{
"$replaceRoot": { "newRoot": "$docs" }
},
{
"$group": {
"_id": { "_id": "$_id", "blog_id": "$blog_id" },
"comments": { "$push": "$comments" }
}
},
{
$project: {
"_id": 0,
"_id": "$_id._id",
"blog_id": "$_id.blog_id",
"comments": 1
}
}
] ).forEach(doc => db.blogs.updateOne( { _id: doc._id }, { $set: { comments: doc.comments } } ) )
You can use ObjectId constructor to create the ids and place them in your nested documents.
I have a MongoDB document structure like following:
Structure
{
"stores": [
{
"items": [
{
"feedback": [],
"item_category": "101",
"item_id": "10"
},
{
"feedback": [],
"item_category": "101",
"item_id": "11"
}
]
},
{
"items": [
{
"feedback": [],
"item_category": "101",
"item_id": "10"
},
{
"feedback": ["A feedback"],
"item_category": "101",
"item_id": "11"
},
{
"feedback": [],
"item_category": "101",
"item_id": "12"
},
{
"feedback": [],
"item_category": "102",
"item_id": "13"
},
{
"feedback": [],
"item_category": "102",
"item_id": "14"
}
],
"store_id": 500
}
]
}
This is a single document in a collection. Some field are deleted to produce minimal representation of the data.
What I want is to get items only if the feedback field in the items array is not empty. The expected result is:
Expected result
{
"stores": [
{
"items": [
{
"feedback": ["A feedback"],
"item_category": "101",
"item_id": "11"
}
],
"store_id": 500
}
]
}
This is what I tried based on examples in this, which I think pretty same situation, but it didn't work. What's wrong with my query, isn't it the same situation in zipcode search example in the link? It returns everything like in the first JSON code, Structure:
What I tried
query = {
'date': {'$gte': since, '$lte': until},
'stores.items': {"$elemMatch": {"feedback": {"$ne": []}}}
}
Thanks.
Please try this :
db.yourCollectionName.aggregate([
{ $match: { 'date': { '$gte': since, '$lte': until }, 'stores.items': { "$elemMatch": { "feedback": { "$ne": [] } } } } },
{ $unwind: '$stores' },
{ $match: { 'stores.items': { "$elemMatch": { "feedback": { "$ne": [] } } } } },
{ $unwind: '$stores.items' },
{ $match: { 'stores.items.feedback': { "$ne": [] } } },
{ $group: { _id: { _id: '$_id', store_id: '$stores.store_id' }, items: { $push: '$stores.items' } } },
{ $project: { _id: '$_id._id', store_id: '$_id.store_id', items: 1 } },
{ $group: { _id: '$_id', stores: { $push: '$$ROOT' } } },
{ $project: { 'stores._id': 0 } }
])
We've all these stages as you need to operate on an array of arrays, this query is written assuming you're dealing with a large set of data, Since you're filtering on dates just in case if your documents size is way less after first $match then you can avoid following $match stage which is in between two $unwind's.
Ref 's :
$match,
$unwind,
$project,
$group
This aggregate query gets the needed result (using the provided sample document and run from the mongo shell):
db.stores.aggregate( [
{ $unwind: "$stores" },
{ $unwind: "$stores.items" },
{ $addFields: { feedbackExists: { $gt: [ { $size: "$stores.items.feedback" }, 0 ] } } },
{ $match: { feedbackExists: true } },
{ $project: { _id: 0, feedbackExists: 0 } }
] )