Aggregation in elasticsearch with specific parameter - elasticsearch

Question

I have bulk documents in elasticsearch and as an example I have taken the elasticsearch documentation example as banks
{
"_index": "bank",
"_type": "account",
"_id": "25",
"_score": 1,
"_source": {
"account_number": 25,
"balance": 40540,
"firstname": "Virginia",
"lastname": "Ayala",
"age": 39,
"gender": "F",
"address": "171 Putnam Avenue",
"employer": "Filodyne",
"email": "virginiaayala#filodyne.com",
"city": "Nicholson",
"state": "PA"
}
}
,
{
"_index": "bank",
"_type": "account",
"_id": "44",
"_score": 1,
"_source": {
"account_number": 44,
"balance": 34487,
"firstname": "Aurelia",
"lastname": "Harding",
"age": 37,
"gender": "M",
"address": "502 Baycliff Terrace",
"employer": "Orbalix",
"email": "aureliaharding#orbalix.com",
"city": "Yardville",
"state": "DE"
}
}
,
{
"_index": "bank",
"_type": "account",
"_id": "99",
"_score": 1,
"_source": {
"account_number": 99,
"balance": 47159,
"firstname": "Ratliff",
"lastname": "Heath",
"age": 39,
"gender": "F",
"address": "806 Rockwell Place",
"employer": "Zappix",
"email": "ratliffheath#zappix.com",
"city": "Shaft",
"state": "ND"
}
}
,
{
"_index": "bank",
"_type": "account",
"_id": "119",
"_score": 1,
"_source": {
"account_number": 119,
"balance": 49222,
"firstname": "Laverne",
"lastname": "Johnson",
"age": 28,
"gender": "F",
"address": "302 Howard Place",
"employer": "Senmei",
"email": "lavernejohnson#senmei.com",
"city": "Herlong",
"state": "DC"
}
}
,
{
"_index": "bank",
"_type": "account",
"_id": "126",
"_score": 1,
"_source": {
"account_number": 126,
"balance": 3607,
"firstname": "Effie",
"lastname": "Gates",
"age": 39,
"gender": "F",
"address": "620 National Drive",
"employer": "Digitalus",
"email": "effiegates#digitalus.com",
"city": "Blodgett",
"state": "MD"
}
}
Now there is a field called state and price in each document. How can I write a query for which it returns only the results that contain distinct state with sort order as balance in asc order.
I was trying with terms aggregation but of no use.
UPDATE
POST _search
{
"size": 0,
"aggs": {
"states": {
"terms": {
"field": "state"
},
"aggs": {
"balances": {
"top_hits": {
"from" : 0,
"size": 1,
"sort": {"balance": "asc"}
}
}
}
}
}
}
now for this query i'll be returned with all top-hits with price sorted in that key "state". But what i want is a sorted results w.r.t balance and with unique state fields.
For the above query, i am getting response as follows
"buckets": [
{
"key": "tx",
"doc_count": 30,
"balances": {
"hits": {
"total": 30,
"max_score": null,
"hits": [
{
"_index": "bank",
"_type": "account",
"_id": "161",
"_score": null,
"_source": {
"account_number": 161,
"balance": 4659,
"firstname": "Doreen",
"lastname": "Randall",
"age": 37,
"gender": "F",
"address": "178 Court Street",
"employer": "Calcula",
"email": "doreenrandall#calcula.com",
"city": "Belmont",
"state": "TX"
},
"sort": [
4659
]
}
]
}
}
},
{
"key": "md",
"doc_count": 28,
"balances": {
"hits": {
"total": 28,
"max_score": null,
"hits": [
{
"_index": "bank",
"_type": "account",
"_id": "527",
"_score": null,
"_source": {
"account_number": 527,
"balance": 2028,
"firstname": "Carver",
"lastname": "Peters",
"age": 35,
"gender": "M",
"address": "816 Victor Road",
"employer": "Housedown",
"email": "carverpeters#housedown.com",
"city": "Nadine",
"state": "MD"
},
"sort": [
2028
]
}
]
}
}
},
{
"key": "id",
"doc_count": 27,
"balances": {
"hits": {
"total": 27,
"max_score": null,
"hits": [
{
"_index": "bank",
"_type": "account",
"_id": "402",
"_score": null,
"_source": {
"account_number": 402,
"balance": 1282,
"firstname": "Pacheco",
"lastname": "Rosales",
"age": 32,
"gender": "M",
"address": "538 Pershing Loop",
"employer": "Circum",
"email": "pachecorosales#circum.com",
"city": "Elbert",
"state": "ID"
},
"sort": [
1282
]
}
]
}
}
},
which is not in price sorted.

Answer 1

Try like this:
POST bank/_search
{
"size": 0,
"aggs": {
"states": {
"terms": {
"field": "state",
"order": {
"balances": "asc"
}
},
"aggs": {
"balances": {
"sum": {
"field": "balance"
}
}
}
}
}
}
Note: I don't see a price field, but a balance one, maybe that's the one you meant.
If you're interested in getting all documents by state sorted by price, then you can try this, too:
POST bank/_search
{
"size": 0,
"aggs": {
"states": {
"terms": {
"field": "state"
},
"aggs": {
"balances": {
"top_hits": {
"size": 5,
"sort": {"balance": "asc"}
}
}
}
}
}
}