I am tring to make a query where use the value and try to interpolate a string in a new field.
Mongo Database:
[
{
"state": "1",
"events": {
"1": [
{
"date": 123.2,
"msg": "msg1"
},
{
"date": 124.2,
"msg": "msg2"
}
],
"2": [
{
"date": 125.2,
"msg": "msg3"
},
{
"date": 126.2,
"msg": "msg4"
}
],
}
},
{
"state": "2",
"events": {
"1": [
{
"date": 123.2,
"msg": "msg1"
},
{
"date": 124.2,
"msg": "msg2"
}
],
"2": [
{
"date": 125.2,
"msg": "msg3"
},
{
"date": 126.2,
"msg": "msg4"
}
],
}
}
]
Aggregate query:
db.collection.aggregate({
"$match": {
"state": {
"$in": [
"1",
"2"
]
}
}
},
{
"$group": {
"_id": {
"state": "$state"
},
"this_path": {
"$first": {
"$concat": [
"events.",
"$state",
".0.date"
]
}
}
}
})
"this_path" gets "events.1.0.date", but how to use this value, in another query(line), I would like to do like a string interpolation. Some thing like
...
"date": {
"$first": { `\$${this_path}`}
...
so it become the "events.1.date" then "$events.1.0.date" then "123.2"
you can define it by let just for example a fragment from pipeline:
$lookup: {
from: contentCollectionName,
as: 'content',
let: {
parentId: '$id',
},
The id is taken from above matched documents, but it can be anything
Related
I have the following collection in MongoDB
[
{
"acronym": "front",
"references": [
{
"date": "2020-03-04",
"value": "5.6"
},
{
"date": "2020-03-05",
"value": "6.3"
}
]
}
]
I want to use the function $addToSet in order to add new document into references. I know that it can be done with the following code:
db.collection.update({
"acronym": "front"
},
{
$addToSet: {
"references": {
"date": "2020-03-06",
"value": "6"
}
}
})
And it will add the new document to the array references, so the result is the following:
[
{
"acronym": "front",
"references": [
{
"date": "2020-03-04",
"value": "5.6"
},
{
"date": "2020-03-05",
"value": "6.3"
},
{
"date": "2020-03-06",
"value": "6"
}
]
}
]
QUESTION: What I want to obtain is that in the case of adding a date that is already in the array, the update will no be produced.
Here is the playground: https://mongoplayground.net/p/DPER2RuROEs
Thanks!
You can add another qualifier to the update to prevent duplicated dates
db.collection.update({
"acronym": "front",
"references.date": {
$ne: "2020-03-04"
}
},
{
$addToSet: {
"references": {
"date": "2020-03-04",
"value": "6"
}
}
})
I got the solution from here
I'm trying to query my dataset for two purposes:
Match a term (resellable = true)
Order the results by their price
lowest to highest
Data set/doc is:
"data" : {
"resellable" : true,
"startingPrice" : 0,
"id" : "4emEe_r_x5DRCc5",
"buyNowPrice" : 0.006493, //Changes per object
"sub_title" : "test 1",
"title" : "test 1",
"category" : "Education",
}
//THREE OBJECTS WITH THE VALUES OF 0.006, 0.7, 1.05 FOR BUYNOWPRICE
I have three objects of these with different buyNowPrice
Query with agg is:
{
"query": {
"bool": {
"must": [
{
"term": {
"data.resellable": true
}
}
]
}
},
"from": 0,
"size": 5,
"aggs": {
"lowestPrice": {
"terms": {
"field": "data.buyNowPrice",
"order": {
"lowest_price": "desc"
}
},
"aggs": {
"lowest_price": {
"min": {
"field": "data.buyNowPrice"
}
},
"lowest_price_top_hits": {
"top_hits": {
"size": 5,
"sort": [
{
"data.buyNowPrice": {
"order": "desc"
}
}
]
}
}
}
}
}
}
The query works fine, and the results are 3 objects that have resellable = true
The issue is, the agg is not organizing the results based off the lowest buy now price.
Each result, the order of buyNowPrice is: 1.06, 0.006, 0.7 - which is not ordered properly.
Switching to desc has no affect, so I don't believe the agg is running at all?
EDIT:
Using the suggestion below my query now looks like:
{
"query": {
"bool": {
"must": [
{
"term": {
"data.resellable": true
}
}
]
}
},
"from": 0,
"size": 5,
"aggs": {
"lowestPrice": {
"terms": {
"field": "data.buyNowPrice",
"order": {
"lowest_price": "asc"
}
},
"aggs": {
"lowest_price": {
"min": {
"field": "data.buyNowPrice"
}
},
"lowest_price_top_hits": {
"top_hits": {
"size": 5
}
}
}
}
}
}
With the results of the query being:
total: { value: 3, relation: 'eq' },
max_score: 0.2876821,
hits: [
{
_index: 'education',
_type: 'listing',
_id: '4emEe_r_x5DRCc5', <--- buyNowPrice of 0.006
_score: 0.2876821,
_source: [Object]
},
{
_index: 'education',
_type: 'listing',
_id: '4ee_r_x5DRCc5', <--- buyNowPrice of 1.006
_score: 0.18232156,
_source: [Object]
},
{
_index: 'education',
_type: 'listing',
_id: '4444_r_x5DRCc5', <--- buyNowPrice of 0.7
_score: 0.18232156,
_source: [Object]
}
]
}
EDIT 2:
Removing the query for resellable = true the aggregation will sort properly and return the items in the proper order. But with the query for resellable included, it does not.
I'm assuming this has to do with the _score property overriding the sorting from agg? How would this be fixed
You can use a bucket sort aggregation that is a parent pipeline
aggregation which sorts the buckets of its parent multi-bucket
aggregation. Zero or more sort fields may be specified together with
the corresponding sort order.
Adding a working example (using the same index data as given in the question), search query, and search result
Search Query:
{
"query": {
"bool": {
"must": [
{
"term": {
"data.resellable": true
}
}
]
}
},
"from": 0,
"size": 5,
"aggs": {
"source": {
"terms": {
"field": "data.buyNowPrice"
},
"aggs": {
"latest": {
"top_hits": {
"_source": {
"includes": [
"data.buyNowPrice",
"data.id"
]
}
}
},
"highest_price": {
"max": {
"field": "data.buyNowPrice"
}
},
"bucket_sort_order": {
"bucket_sort": {
"sort": {
"highest_price": {
"order": "desc"
}
}
}
}
}
}
}
}
Search Result:
"buckets": [
{
"key": 1.0499999523162842,
"doc_count": 1,
"highest_price": {
"value": 1.0499999523162842
},
"latest": {
"hits": {
"total": {
"value": 1,
"relation": "eq"
},
"max_score": 0.08701137,
"hits": [
{
"_index": "stof_64364468",
"_type": "_doc",
"_id": "3",
"_score": 0.08701137,
"_source": {
"data": {
"id": "4emEe_r_x5DRCc5",
"buyNowPrice": 1.05 <-- note this
}
}
}
]
}
}
},
{
"key": 0.699999988079071,
"doc_count": 1,
"highest_price": {
"value": 0.699999988079071
},
"latest": {
"hits": {
"total": {
"value": 1,
"relation": "eq"
},
"max_score": 0.08701137,
"hits": [
{
"_index": "stof_64364468",
"_type": "_doc",
"_id": "2",
"_score": 0.08701137,
"_source": {
"data": {
"id": "4emEe_r_x5DRCc5",
"buyNowPrice": 0.7 <-- note this
}
}
}
]
}
}
},
{
"key": 0.006000000052154064,
"doc_count": 1,
"highest_price": {
"value": 0.006000000052154064
},
"latest": {
"hits": {
"total": {
"value": 1,
"relation": "eq"
},
"max_score": 0.08701137,
"hits": [
{
"_index": "stof_64364468",
"_type": "_doc",
"_id": "1",
"_score": 0.08701137,
"_source": {
"data": {
"id": "4emEe_r_x5DRCc5",
"buyNowPrice": 0.006 <-- note this
}
}
}
]
}
}
}
]
Update 1:
If you modify your search query as :
{
"query": {
"bool": {
"must": [
{
"term": {
"data.resellable": true
}
}
]
}
},
"aggs": {
"lowestPrice": {
"terms": {
"field": "data.buyNowPrice",
"order": {
"lowest_price": "asc" <-- change the order here
}
},
"aggs": {
"lowest_price": {
"min": {
"field": "data.buyNowPrice"
}
},
"lowest_price_top_hits": {
"top_hits": {
"size": 5
}
}
}
}
}
}
Running the above search query also, you will get your required results.
I'm converting MongoDB Query to Elasticsearch in NodeJS platform. While developing I'm facing some difficulties with grouping and filtering data (getting nested objects like hits.hits._source) within Elasticsearch Query like we doing in MongoDB Query.
Example:-
UserModel.aggregate([
{
$match: {
uId: req.body.uId, timestamp: { $gte: req.body.date, $lte: new Date() }
},
},
{
$group: {
_id: "$eId",
location: {
$push: {
time: "$timestamp", lat: "$lat"
}
},
timestamp: {
$push: "$timestamp"
},
testId: { $first: "$testId" },
}
},
{
$project: {
eId: 1, location: 1, testId: 1, max: { $max: "$timestamp" }
}
},
{ $unwind: { path: "$location", preserveNullAndEmptyArrays: true } },
{
$redact: {
$cond: {
if: { $eq: ["$location.time", "$max"] },
then: "$$DESCEND",
else: "$$PRUNE"
}
}
},
{
$project: {
eId: 1, latitude: "$location.lat", testId: 1
}
},
]).exec(function (err, result) {
console.log(result)
});
What will be the equivalent query in Elasticsearch?
I'm looking for solution with grouping, unwinding and projecting (MongoDB concepts to Elasticsearch) required data with minimal nested response.
Thanks in Advance.
EDIT:-
Adding Elasticsearch Document:-
{
"timestamp": "2019-10-08T:02:50:15.54Z",
"status" : 1,
"eId": "5d5d7ce0c89852e7bad4a407",
"location": [
2.000,
34.5664111801
],
"zId": "5d5d7ce0c89852e7bad4a4ef"
},
{
"timestamp": "2019-10-09T:02:50:15.54Z",
"status" : 1,
"eId": "5d5d7ce0c89852e7bad4a408",
"location": [
2.100,
35.5664111801
],
"zId": "5d5d7ce0c89852e7bad4a4ef"
},
{
"timestamp": "2019-10-09T:03:50:15.54Z",
"status" : 1,
"eId": "5d5d7ce0c89852e7bad4a407",
"location": [
4.100,
35.5664111801
],
"zId": "5d5d7ce0c89852e7bad4a4ef"
},
{
"timestamp": "2019-10-09T:03:40:15.54Z",
"status" : 1,
"eId": "5d5d7ce0c89852e7bad4a407",
"location": [
2.100,
35.5664111801
],
"zId": "5d5d7ce0c89852e7bad4a4e1"
},
{
"timestamp": "2019-10-10T:03:40:15.54Z",
"status" : 1,
"eId": "5d5d7ce0c89852e7bad4a407",
"location": [
3.100,
35.5664111801
],
"zId": "5d5d7ce0c89852e7bad4a4e1"
}
Match with status =1, and Group By eId
With that results, group by timestamp and get max timestamp value
Expected Result:-
[
{
"_id": "5d5d7ce0c89852e7bad4a407",
"max": "2019-10-10T:03:40:15.54Z", // max timestamp
"zId": [
"5d5d7ce0c89852e7bad4a4e1",
"5d5d7ce0c89852e7bad4a4ef"
]
},
{
"_id": "5d5d7ce0c89852e7bad4a408",
"max": "2019-10-09T:02:50:15.54Z",
"zId": [
"5d5d7ce0c89852e7bad4a4ef"
]
}, // ...etc
]
Thanks for the documents. Sadly, I do not know any way to retrieve only the documents having the max timestamp field value.
The following query will allow you to filter by status and group by eId then get the max timestamp value, but it will not return the documents having the max timestamp value.
{
"size": 0,
"query": {
"term": {
"status": 1
}
},
"aggregations": {
"eId_group": {
"terms": {
"field": "eId"
},
"aggregations": {
"max_timestamp": {
"max": {
"field": "timestamp"
}
}
}
}
}
}
This second query use a top_hits aggregation to retrieve the documents grouped by eId. The returned documents are sorted by decreasing timestamp value so the documents having the max timestamp will be firsts, but you may also get documents with different timestamps.
{
"size": 0,
"query": {
"term": {
"status": 1
}
},
"aggregations": {
"eId_group": {
"terms": {
"field": "eId"
},
"aggregations": {
"max_timestamp": {
"max": {
"field": "timestamp"
}
},
"top_documents": {
"top_hits": {
"size": 20,
"sort": { "timestamp": "desc"}
}
}
}
}
}
}
I used the following mapping for the index
PUT /test_index
{
"mappings": {
"properties": {
"timestamp": {
"type": "date"
},
"eId": {
"type": "keyword"
},
"zId": {
"type": "keyword"
},
"status": {
"type": "keyword"
}
}
}
}
would like to know how to use MongoDB's aggregation to collectively summarize a count of each reason_id:
I would like to get known that there are 2 counts for having "reason_id = KW7Kcsv7835YZeE3n", and 1 count for having "reason_id = KNcKQCjhFzha3oLfE".
Here is my data:
[
{
"_id": "2DLQFJLbZScBXpSam",
"toilet_id": "bJsyfh3TCvpTzE2mJ",
"reason_ids": [
"KNcKQCjhFzha3oLfE",
"KW7Kcsv7835YZeE3n"
],
"score_id": null,
"toilet": {
"_id": "bJsyfh3TCvpTzE2mJ",
"name": "Toilet_M_1",
"gender": "m",
"mac_address": "11:11:11:11:11:11"
}
},
{
"_id": "akjsbcjascklsacas",
"toilet_id": "bJsyfh3TCvpTzE2mJ",
"reason_ids": [
"KW7Kcsv7835YZeE3n"
],
"score_id": null,
"toilet": {
"_id": "fsgndgklndsdsdsd",
"name": "Toilet_F_1",
"gender": "f",
"mac_address": "11:11:11:11:11:11"
}
},
]
You can try this
db.collection.aggregate([
{
"$unwind": "$reason_ids"
},
{
"$group": {
"_id": "$reason_ids",
"count": {
"$sum": 1
}
}
}
])
Output
[
{
"_id": "KW7Kcsv7835YZeE3n",
"count": 2
},
{
"_id": "KNcKQCjhFzha3oLfE",
"count": 1
}
]
Try it here
I have been reading some posts which are related to my question, whereas I have not been able to find a proper solution for what I'm trying to do hear.
I have this JSON file that I am obtaining directly from my database via a sql query:
[
{
"scenario": "scenario-483d742c-4492-4a4f-95fa-7ccceac8bb18",
"data": [
{
"date": "2018-05-21",
"price": 14.173041264216105
}
]
},
{
"scenario": "scenario-483d742c-4492-4a4f-95fa-7ccceac8bb18",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
},
{
"scenario": "scenario-c705069f-fa53-4ff3-9f07-3fcbf9dc8d15",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
},
{
"scenario": "scenario-c705069f-fa53-4ff3-9f07-3fcbf9dc8d15",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
},
{
"scenario": "scenario-d58bb001-d7ed-4744-8f6c-8377519c7a99",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
},
{
"scenario": "scenario-d58bb001-d7ed-4744-8f6c-8377519c7a99",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
}
]
My objectif is to be able to sort/transform this json object to a new json object which is classified by the scenario, so, something that looks like:
[
{
"scenario": "scenario-483d742c-4492-4a4f-95fa-7ccceac8bb18",
"data": [
{
"date": "2018-05-21",
"price": 14.173041264216105
},
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
},
{
"scenario": "scenario-c705069f-fa53-4ff3-9f07-3fcbf9dc8d15",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
},
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
},
{
"scenario": "scenario-d58bb001-d7ed-4744-8f6c-8377519c7a99",
"data": [
{
"date": "2018-05-22",
"price": 42.94691197077433
},
{
"date": "2018-05-22",
"price": 42.94691197077433
}
]
I have been trying some javascript selfmade functions but I have not obtainend the desired result.
This is the last thing I've tried:
let estructura = [];
for (var j =0; j<obj.length; j++){
for (var i=0; i<estructura.length; i++){
if(obj[j]['scenario'] == estructura[i]['scenario']){
estructura[i]['data'].push(obj[j]['data'])
} else {
console.log("no match, we add the scenario to estructura")
estructura.push(
{
scenario:obj[j]['scenario'],
data: []
})
}
}
}
Thank you
You can achieve this easily with built-in functions like reduce. Iterate over the input, grouping into an object indexed by scenario, creating a object with a data array if the scenario doesn't exist yet, and push to that array:
const input=[{"scenario":"scenario-483d742c-4492-4a4f-95fa-7ccceac8bb18","data":[{"date":"2018-05-21","price":14.173041264216105}]},{"scenario":"scenario-483d742c-4492-4a4f-95fa-7ccceac8bb18","data":[{"date":"2018-05-22","price":42.94691197077433}]},{"scenario":"scenario-c705069f-fa53-4ff3-9f07-3fcbf9dc8d15","data":[{"date":"2018-05-22","price":42.94691197077433}]},{"scenario":"scenario-c705069f-fa53-4ff3-9f07-3fcbf9dc8d15","data":[{"date":"2018-05-22","price":42.94691197077433}]},{"scenario":"scenario-d58bb001-d7ed-4744-8f6c-8377519c7a99","data":[{"date":"2018-05-22","price":42.94691197077433}]},{"scenario":"scenario-d58bb001-d7ed-4744-8f6c-8377519c7a99","data":[{"date":"2018-05-22","price":42.94691197077433}]}]
console.log(
Object.values(input.reduce((a, { scenario, data }) => {
if (!a[scenario]) a[scenario] = { scenario, data: [] };
a[scenario].data.push(data[0]);
return a;
}, {}))
);