I need to write a MongoDB aggregation pipeline to count the objects having arrays containing two type of values:
>=10
>=20
This is my dataset:
[
{ values: [ 1, 2, 3] },
{ values: [12, 1, 3] },
{ values: [1, 21, 3] },
{ values: [1, 2, 29] },
{ values: [22, 9, 2] }
]
This would be the expected output
{
has10s: 4,
has20s: 3
}
Mongo's $in (aggregation) seems to be the tool for the job, except I can't get it to work.
This is my (non working) pipeline:
db.mytable.aggregate([
{
$project: {
"has10s" : {
"$in": [ { "$gte" : [10, "$$CURRENT"]}, "$values"]}
},
"has20s" : {
"$in": [ { "$gte" : [20, "$$CURRENT"]}, "$values"]}
}
},
{ $group: { ... sum ... } }
])
The output of $in seems to be always true. Can anyone help?
You can try something like this:
db.collection.aggregate([{
$project: {
_id: 0,
has10: {
$size: {
$filter: {
input: "$values",
as: "item",
cond: { $gte: [ "$$item", 10 ] }
}
}
},
has20: {
$size: {
$filter: {
input: "$values",
as: "item",
cond: { $gte: [ "$$item", 20 ] }
}
}
}
}
},
{
$group: {
_id: 1,
has10: { $sum: "$has10" },
has20: { $sum: "$has20" }
}
}
])
Using $project with $filter to get the actual elements and then via $size to get the array length.
See it working here
Related
get value from items.z where y=five
Sample data
[
{
"_id": 1,
"items": [
{
x: "one",
y: "two",
z: "three"
},
{
x: "four",
y: "five",
z: "six"
}
]
}]
Expected result
[{
"_id": 1,
"indexValue": "six"
}]
Tried query
db.collection.aggregate([
{
$match: {
_id: 1
}
},
{
$project: {
indexValue: {
$arrayElemAt: [
"$items",
1
]
}
}
},
{
$project: {
indexValue: "$indexValue.z"
}
}
])
Here i dont know index and it take 2 pipelines
So how to get that value and can do it in one pipeline because of performance issue?
One option is to use $filter:
db.collection.aggregate([
{$match: {_id: 1}},
{$project: {
item: {
$first: {
$filter: {
input: "$items",
cond: {$eq: ["$$this.y", "five"]}
}
}
}
}
},
{$project: {indexValue: "$item.z"}}
])
See how it works on the playground example
A: It should be output how many _ids are included by date grouped by date.
B: The number of elements in details in A.
If it has element, count 1. not 0. If the document is as follows, the value counted after excluding from A becomes B
{
_id: ObjectId
details: array //no elements
createdAt: Date
}
C: The count of B becomes C, except when there are specific details.slaesManagerIds among B.
details.salesManagerIds is provided as an array.
For examples,
[ObjecttId("612f57184205db63a3396a9e"), ObjectId("612cb021278f621a222087d7")]
I made query as follows.
https://mongoplayground.net/p/6sBxAmO_31y
It goes well until B. How can I write a query to get C ?
If you write and execute a query that can obtain C through the link above, you should get the following result.
[
{
"A": 2,
"B": 1,
"C": 1,
"_id": "2018-05-19"
},
{
"A": 3,
"B": 3,
"C": 1,
"_id": "2018-05-18"
}
]
use $filter
db.collection.aggregate([
{
$group: {
_id: {
$dateToString: {
format: "%Y-%m-%d",
date: "$createdAt"
}
},
A: {
$sum: 1
},
B: {
$sum: {
$cond: [
{
$and: [
{
$isArray: "$details"
},
{
$gt: [
{
$size: "$details"
},
0
]
}
]
},
1,
0
]
}
},
C: {
$sum: {
$cond: [
{
$and: [
{
$isArray: "$details"
},
{
$gt: [
{
$size: "$details"
},
0
]
},
{
$gt: [
{
$size: {
$filter: {
input: "$details",
as: "d",
cond: {
$and: [
{
$not: [
{
$in: [
"$$d.salesManagerId",
[
ObjectId("612f57184205db63a3396a9e"),
ObjectId("612cb021278f621a222087d7")
]
]
}
]
}
]
}
}
}
},
0
]
}
]
},
1,
0
]
}
}
}
},
{
$sort: {
_id: -1
}
}
])
mongoplayground
I want to get related data based on current item processing.
Sample:
[
{ field1: 1, field2: 2, value: 12 },
{ field1: 1, field2: 2, value: 21 },
{ field1: 1, value: 1 },
{ field2: 2, value: 2 },
{ field1: 2, field2: 3, value: 23 }
];
and result:
[
{
_id: { field1: 1, field2: 2 },
value: [12, 12],
relatedValue: [1, 2], // of item 1 and 2 because field 1 = 1 or field 2 = 2
},
];
Sample query:
db.collectionA.aggregate([
{
$match: { field1: 1 }
},
{
"$group":{
"_id":{
"field1":"$field1",
"field2":"$field2"
},
"alerts":{
"$push":{
"_id":"$_id",
"value":"$value",
"relatedData": {
"$unionWith": {
"coll": "collectionA",
"pipeline": [{
"$match": {
"$or": [
{ "field1": "$field1" },
{ "field2": "$field2" }
]
}
}]
}
}
}
}
}
}
])
I tried run this query but error, Please help me fix or give a solution
// Edited: value should be array because I want to group data by field1, field2 and push all value of group to an array
You're trying to use $unionWith within $group but it is a "pipeline stage" meaning it can't be used like that, the same way you can't use $group within a $group.
Additionally this stage is used to "union" two collections and not to populate data based on value matches ( which it seems you're trying to do here ), for this case you want to use $lookup, like so:
db.collection.aggregate([
{
$lookup: {
from: "collection",
let: {
field1: "$field1",
field2: "$field2",
docId: "$_id"
},
pipeline: [
{
$match: {
$expr: {
$and: [
{
$or: [
{
$eq: [
"$$field1",
"$field1"
]
},
{
$eq: [
"$$field2",
"$field2"
]
}
]
},
{
$ne: [
"$$docId",
"$_id"
]
}
]
}
}
},
{
$project: {
value: 1
}
}
],
as: "relatedData"
}
},
{
$group: {
_id: {
field1: "$field1",
field2: "$field2"
},
values: {
$push: "$value"
},
relatedValue: {
$push: {
$map: {
input: "$relatedData",
in: "$$this.value"
}
}
}
}
},
{
$project: {
field1: "$_id.field1",
field2: "$_id.field2",
values: 1,
relatedValues: {
"$setDifference": [
{
"$reduce": {
input: "$relatedValue",
initialValue: [],
in: {
"$setUnion": [
"$$this",
"$$value"
]
}
}
},
"$values"
]
}
}
}
])
Mongo Playground
Using mongodb, I have a collection of documents where each document has a fixed length vector of floating point values such as below:
items = [
{"id": "1", "vec": [1, 2, 0]},
{"id": "2", "vec": [6, 4, 1]},
{"id": "3", "vec": [3, 2, 2]},
]
I would like to take the row wise average of these vectors. In this example I would expect the result to return
[ (1 + 6 + 3) / 3, (2 + 4 + 2) / 3, (0 + 1 + 2) / 3 ]
This answer is very close to what I am looking for, but as far as I can tell it will only work on vectors of size 2. mongoDB - average on array values
An answer has been provided that is not very performant for large arrays. For context I am using ~700 dimension vectors.
This should work: https://mongoplayground.net/p/PKXqmmW31nW
[
{
$group: {
_id: null,
a: {
$push: {
$arrayElemAt: ["$vec", 0]
}
},
b: {
$push: {
$arrayElemAt: ["$vec", 1]
}
},
c: {
$push: {
$arrayElemAt: ["$vec", 2]
}
}
}
},
{
$project: {
a: {
$avg: "$a"
},
b: {
$avg: "$b"
},
c: {
$avg: "$c"
}
}
}
]
Which outputs:
[
{
"_id": null,
"a": 3.3333333333333335,
"b": 2.6666666666666665,
"c": 1
}
]
Here's a more efficient without $avg operator. I'll leave other answer up for reference.
https://mongoplayground.net/p/rVERc8YjKZv
db.collection.aggregate([
{
$group: {
_id: null,
a: {
$sum: {
$arrayElemAt: ["$vec", 0]
}
},
b: {
$sum: {
$arrayElemAt: ["$vec", 1]
}
},
c: {
$sum: {
$arrayElemAt: ["$vec", 2]
}
},
totalDocuments: {
$sum: 1
}
}
},
{
$project: {
a: {
$divide: ["$a", "$totalDocuments"]
},
b: {
$divide: ["$b", "$totalDocuments"]
},
c: {
$divide: ["$c", "$totalDocuments"]
}
}
}
])
You can use $unwind to get values into separate documents, the key is to keep the index of the values. Then you can use $group by the index and calculate the average using the $avg operator.
db.collection.aggregate([
{
$unwind: {
path: "$vec",
includeArrayIndex: "i" // unwind and keep index
}
},
{
$group: {
_id: "$i", // group by index
avg: { $avg: "$vec" }
}
}, // at this stage, you already get all the values you need, in separate documents. The following stages will put all the values in an array
{
$sort: { _id: 1 }
},
{
$group: {
_id: null,
avg: { $push: "$avg" }
}
}
])
Mongo Playground
I am stuck in a query scenario.
I have a json structure in Mongodb where in I will have to query the document based on the element "Index".
{"List" : {
"List1" : [11,12,13,14,15,16],
"List2" : [11,11,11,11,11,11]
},
"Values" : ["APPLE", "ORANGE", "BANANA", "MANGO", "PAPAYA", "KIWI"],
"Index" : [1,2,3,1,2,3]
}
Filter should be based on "Index" where it is ‘1’ and I wanted to be displayed as below.
{"List" : {
"List1" : [11,14],
"List2" : [11,11]
},
"Values" : ["APPLE","MANGO"],
"Index" : [1,1]
}
below is the query i executed
db.getCollection('TEST').find({"Index": 3} ,
{ "Values": 1,"List":1,"Index": 1, "Index.$": 1}
)
I get all the data except only one in the index value since I gave the positional parameter ("Index.$": 1)
With Current Mongo 3.4 version you can $zip in combination with $range to generate array of indexes and fields, $filter to match on Index field and $addFields to add to the original fields.
Last step is to $map each of the fields based on the matching index with $arrayElemAt
aggregate([{
$addFields: {
match: {
$filter: {
input: {
$zip: {
inputs: ["$Index", {
$range: [0, {
$size: "$Index"
}]
}]
}
},
as: "val",
cond: {
$eq: [{
$arrayElemAt: ["$$val", 0]
}, 1]
}
}
}
}
}, {
$project: {
"List": {
"List1": {
$map: {
input: "$match",
as: "index",
in: {
$arrayElemAt: ["$List.List1", {
$arrayElemAt: ["$$index", -1]
}]
}
}
},
"List2": {
$map: {
input: "$match",
as: "index",
in: {
$arrayElemAt: ["$List.List2", {
$arrayElemAt: ["$$index", -1]
}]
}
}
}
},
"Values": {
$map: {
input: "$match",
as: "index",
in: {
$arrayElemAt: ["$Values", {
$arrayElemAt: ["$$index", -1]
}]
}
}
},
"Index": {
$map: {
input: "$match",
as: "index",
in: {
$arrayElemAt: ["$Index", {
$arrayElemAt: ["$$index", -1]
}]
}
}
},
_id: 0
}
}]).pretty();