Elasticsearch include field in result set of aggregation - elasticsearch

How can field of type string be included in the result set of an aggregation?
For example given the following mapping:
{
"sport": {
"mappings": {
"runners": {
"properties": {
"name": {
"type": "string"
},
"city": {
"type": "string"
},
"region": {
"type": "string"
},
"sport": {
"type": "string"
}
}
}
}
}
}
Sample data:
curl -XPOST "http://localhost:9200/sport/_bulk" -d'
{"index":{"_index":"sport","_type":"runner"}}
{"name":"Gary", "city":"New York","region":"A","sport":"Soccer"}
{"index":{"_index":"sport","_type":"runner"}}
{"name":"Bob", "city":"New York","region":"A","sport":"Tennis"}
{"index":{"_index":"sport","_type":"runner"}}
{"name":"Mike", "city":"Atlanta","region":"B","sport":"Soccer"}
'
How can the field name be included in result set of the aggregation:
{
"size": 0,
"aggregations": {
"agg": {
"terms": {
"field": "city"}
}
}
}

This seems to do what you want, if I'm understanding you correctly:
POST /sport/_search
{
"size": 0,
"aggregations": {
"city_terms": {
"terms": {
"field": "city"
},
"aggs": {
"name_terms": {
"terms": {
"field": "name"
}
}
}
}
}
}
With the data you provided, it returns:
{
"took": 43,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 3,
"max_score": 0,
"hits": []
},
"aggregations": {
"city_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "new",
"doc_count": 2,
"name_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "bob",
"doc_count": 1
},
{
"key": "gary",
"doc_count": 1
}
]
}
},
{
"key": "york",
"doc_count": 2,
"name_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "bob",
"doc_count": 1
},
{
"key": "gary",
"doc_count": 1
}
]
}
},
{
"key": "atlanta",
"doc_count": 1,
"name_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "mike",
"doc_count": 1
}
]
}
}
]
}
}
}
(You may want to add "index":"not_analyzed" to one or both fields in your mapping, if these results are not what you were expecting.)
Here's the code I used to test it:
http://sense.qbox.io/gist/07735aadc082c1c60409931c279f3fd85a340dbb

Related

Elasticsearch - Count number of occurrence perd field per document

Is it possible to calculate the number of occurence of distinct values in a list field.
For example, let the following data:
[
{
"page":1,
"colors":[
{
"color": red
},
{
"color": white
},
{
"color": red
}
]
},
{
"page":2,
"colors":[
{
"color": yellow
},
{
"color": yellow
}
]
}
]
Is it possible to get a result as the follwing:
{
"page":1,
"colors_count":[
{
"Key": red,
"Count": 2
},
{
"Key": white,
"Count": 1
},
]
},
{
"page":2,
"colors_count":[
{
"Key": yellow,
"Count": 2
}
]
}
I tried using term aggregation but I got the number of distinct values, so for page:1 i got red:1 and white:1.
Yes, you can do it. you will have to use nested_field type and nested_Agg
Mapping:
PUT colors
{
"mappings": {
"properties": {
"page" : { "type": "keyword" },
"colors": {
"type": "nested",
"properties": {
"color": {
"type": "keyword"
}
}
}
}
}
}
Insert Documents:
PUT colors/_doc/1
{
"page": 1,
"colors": [
{
"color": "red"
},
{
"color": "white"
},
{
"color": "red"
}
]
}
PUT colors/_doc/2
{
"page": 2,
"colors": [
{
"color": "yellow"
},
{
"color": "yellow"
}
]
}
Query:
GET colors/_search
{
"size" :0,
"aggs": {
"groupByPage": {
"terms": {
"field": "page"
},
"aggs": {
"colors": {
"nested": {
"path": "colors"
},
"aggs": {
"genres": {
"terms": {
"field": "colors.color"
}
}
}
}
}
}
}
}
Output:
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 2,
"relation": "eq"
},
"max_score": null,
"hits": []
},
"aggregations": {
"groupByPage": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "1", // page field value
"doc_count": 1,
"colors": {
"doc_count": 3,
"genres": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "red",
"doc_count": 2
},
{
"key": "white",
"doc_count": 1
}
]
}
}
},
{
"key": "2", // page field value
"doc_count": 1,
"colors": {
"doc_count": 2,
"genres": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "yellow",
"doc_count": 2
}
]
}
}
}
]
}
}
}

Buckets size filter in Elasticsearch

Here is my query result
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 502,
"max_score": 0,
"hits": []
},
"aggregations": {
"HIGH_RISK_USERS": {
"doc_count": 1004,
"USERS_COUNT": {
"doc_count_error_upper_bound": 5,
"sum_other_doc_count": 437,
"buckets": [
{
"key": "49",
"doc_count": 502,
"NAME": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": []
}
},
{
"key": "02122219455#53.205.223.157",
"doc_count": 44,
"NAME": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "caller",
"doc_count": 42
},
{
"key": "CallFrom",
"doc_count": 2
}
]
}
},
{
"key": "+02129916178#53.205.223.157",
"doc_count": 2,
"NAME": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "caller",
"doc_count": 2
}
]
}
}
]
}
}
}
}
Here is my query
{
"size": 0,
"query": {
"bool": {
"filter": [
{
"nested": {
"path": "x_nova_extensions.entities",
"query": {
"bool": {
"filter": [
{
"match": {
"x_nova_extensions.entities.text": "49"
}
},
{
"terms": {
"x_nova_extensions.entities.type": [
"sourceCountryCode",
"CallerIPCountryCode",
"CallerIPCountryName",
"CallerIPCountryCode",
"CallerPhoneCountryName"
]
}
}
]
}
}
}
}
]
}
},
"aggs": {
"HIGH_RISK_USERS": {
"nested": {
"path": "x_nova_extensions.entities"
},
"aggs": {
"USERS_COUNT": {
"terms": {
"field": "x_nova_extensions.entities.text",
"size": 10,
"order": {
"_count": "desc"
}
},
"aggs": {
"NAME": {
"terms": {
"field": "x_nova_extensions.entities.type",
"include": [
"caller",
"callee",
"CallFrom",
"CallTo"
]
}
}
}
}
}
}
}
}
I want my query to return only bucket[].size > 0
I searched on the internet and I couldn't find any specific keyword or something else. Even I am not sure if Elasticsearch supports this or not. I want to sure that Elasticsearch supports this
Are there any keyword or how can I handle it ?
Thanks
I think the thing that you are looking for is Aggregation Pipeline
By that way, you can reach the bucket size and filter the result accordingly.
"min_bucket_selector": {
"bucket_selector": {
"buckets_path": {
"nameCount": "NAME._bucket_count"
},
"script": {
"source": "params.nameCount != 0"
}
}
}
}
}
But please pay attention to the elasticsearch version. The way how it is applied can be different according to the version.

In elasticsearch, how to group by value inside nested array

Say, I have following documents:
1st doc:
{
productName: "product1",
tags: [
{
"name":"key1",
"value":"value1"
},
{
"name":"key2",
"value":"value2"
}
]
}
2nd doc:
{
productName: "product2",
tags: [
{
"name":"key1",
"value":"value1"
},
{
"name":"key2",
"value":"value3"
}
]
}
I know if I want to group by productName, I could use a terms aggregation
"terms": {
"field": "productName"
}
which will give me two buckets with two different keys "product1", "product2".
However, what should the query be if I would like to group by tag key? i.e. I would like to group by tag with name==key1, then I am expecting one bucket with key="value1"; while if I group by tag with name==key2, I am expecting the result to be two buckets with keys "value2", "value3".
What should the query look like if I would like to group by the 'value' inside a nested array but not group by the 'key'? Any suggestion?
It sounds like a nested terms aggregation is what you're looking for.
With the two documents you posted, this query:
POST /test_index/_search
{
"size": 0,
"aggs": {
"product_name_terms": {
"terms": {
"field": "product_name"
}
},
"nested_tags": {
"nested": {
"path": "tags"
},
"aggs": {
"tags_name_terms": {
"terms": {
"field": "tags.name"
}
},
"tags_value_terms": {
"terms": {
"field": "tags.value"
}
}
}
}
}
}
returns this:
{
"took": 67,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 2,
"max_score": 0,
"hits": []
},
"aggregations": {
"product_name_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": []
},
"nested_tags": {
"doc_count": 4,
"tags_name_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "key1",
"doc_count": 2
},
{
"key": "key2",
"doc_count": 2
}
]
},
"tags_value_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "value1",
"doc_count": 2
},
{
"key": "value2",
"doc_count": 1
},
{
"key": "value3",
"doc_count": 1
}
]
}
}
}
}
Here is some code I used to test it:
http://sense.qbox.io/gist/a9a172f41dbd520d5e61063a9686055681110522
EDIT: Filter by Nested Value
As per your comment, if you want to filter the nested results by a value (of the nested results), you can add another "layer" of aggregation making use of the filter aggregation as follows:
POST /test_index/_search
{
"size": 0,
"aggs": {
"nested_tags": {
"nested": {
"path": "tags"
},
"aggs": {
"filter_tag_name": {
"filter": {
"term": {
"tags.name": "key1"
}
},
"aggs": {
"tags_name_terms": {
"terms": {
"field": "tags.name"
}
},
"tags_value_terms": {
"terms": {
"field": "tags.value"
}
}
}
}
}
}
}
}
which returns:
{
"took": 10,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 2,
"max_score": 0,
"hits": []
},
"aggregations": {
"nested_tags": {
"doc_count": 4,
"filter_tag_name": {
"doc_count": 2,
"tags_name_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "key1",
"doc_count": 2
}
]
},
"tags_value_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "value1",
"doc_count": 2
}
]
}
}
}
}
}
Here's the updated code:
http://sense.qbox.io/gist/507c3aabf36b8f6ed8bb076c8c1b8552097c5458

query for elasticsearch returning count

I am struggling to create the query/rule that will help me create an alerting script. I want to query the elasticsearch API for counts on a specific index so that I can get alerted when the count reaches a certain threshold.
The following query is an attempt as I have no experience with this:
{
"query": {
"filtered": {
"query": {
"query_string": {
"analyze_wildcard": true,
"query": "*"
}
},
"filter": {
"bool": {
"must": [
{
"query": {
"match": {
"PStream": {
"query": "*",
"type": "phrase"
}
}
}
},
{
"range": {
"#timestamp": {
"gte": 1447789445320,
"lte": 1447793045320
}
}
}
],
"must_not": []
}
}
}
},
"highlight": {
"pre_tags": [
"#kibana-highlighted-field#"
],
"post_tags": [
"#/kibana-highlighted-field#"
],
"fields": {
"*": {}
},
"fragment_size": 2147483647
},
"size": 500,
"sort": [
{
"#timestamp": {
"order": "desc",
"unmapped_type": "boolean"
}
}
],
"aggs": {
"2": {
"date_histogram": {
"field": "#timestamp",
"interval": "1m",
"pre_zone": "-05:00",
"pre_zone_adjust_large_interval": true,
"min_doc_count": 0,
"extended_bounds": {
"min": 1447789445317,
"max": 1447793045317
}
}
}
},
The field PStream is the field that I am focused on
EDIT:
An example of the data going to the index:
{
"_index": "logstash-2015.11.17",
"_type": "logs",
"_id": "AVEXMKu2YVnF1NOjr9YT",
"_score": null,
"_source": {
"authorUrl": "",
"postUrl": "",
"pubDate": "2015-11-17T15:18:24",
"scrapeDate": "2015-11-17T15:44:03",
"clientId": "136902834",
"query": "Jenny Balatsinou",
"PType": "post",
"tLatency": 1539,
"PLang": "en",
"PStream": "864321",
"PName": "xStackOverflow",
"#version": "1",
"#timestamp": "2015-11-17T20:44:03.400Z"
},
"fields": {
"#timestamp": [
1447793043400
],
"pubDate": [
1447773504000
],
"scrapeDate": [
1447775043000
]
},
"sort": [
1447793043400
]
there are about 20 million of these messages getting indexed daily into Elasticsearch. I have created a dashboard in Kibana where I view this data and stats. I would like to write the proper query that I can use in a java program that periodically runs and checks this index using this query. It should return the hourly total count grouped by the PStream variable which has multiple values. So anytime the value is 0 it will send an alert.
Eg. Output:
"result": {
"total": 74,
"successful": 63,
"failed": 11,
{
{
"index": "logstash-2015.11.08",
"PStream": "37647338933",
"Count": 1234532
},
{
"index": "logstash-2015.11.08",
"PStream": "45345343566",
"Count": 156532
},
As a quick example (per comments above), I just set up a trivial index:
DELETE /test_index
PUT /test_index
added some (simplified) data:
PUT /test_index/doc/_bulk
{"index":{"_id":1}}
{"PStream": "864321","#timestamp": "2015-11-17T20:44:03.400Z"}
{"index":{"_id":2}}
{"PStream": "864321","#timestamp": "2015-11-17T21:44:03.400Z"}
{"index":{"_id":3}}
{"PStream": "864321","#timestamp": "2015-11-17T20:44:03.400Z"}
{"index":{"_id":4}}
{"PStream": "864322","#timestamp": "2015-11-17T21:44:03.400Z"}
And now I can get the "PStream" terms inside an hour histogram:
POST /test_index/_search
{
"size": 0,
"aggs" : {
"timestamp_histogram" : {
"date_histogram" : {
"field" : "#timestamp",
"interval" : "hour"
},
"aggs": {
"pstream_terms": {
"terms": {
"field": "PStream"
}
}
}
}
}
}
...
{
"took": 6,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 4,
"max_score": 0,
"hits": []
},
"aggregations": {
"timestamp_histogram": {
"buckets": [
{
"key_as_string": "2015-11-17T20:00:00.000Z",
"key": 1447790400000,
"doc_count": 2,
"pstream_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "864321",
"doc_count": 2
}
]
}
},
{
"key_as_string": "2015-11-17T21:00:00.000Z",
"key": 1447794000000,
"doc_count": 2,
"pstream_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "864321",
"doc_count": 1
},
{
"key": "864322",
"doc_count": 1
}
]
}
}
]
}
}
}
or the other way around:
POST /test_index/_search
{
"size": 0,
"aggs": {
"pstream_terms": {
"terms": {
"field": "PStream"
},
"aggs": {
"timestamp_histogram": {
"date_histogram": {
"field": "#timestamp",
"interval": "hour"
}
}
}
}
}
}
...
{
"took": 5,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 4,
"max_score": 0,
"hits": []
},
"aggregations": {
"pstream_terms": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "864321",
"doc_count": 3,
"timestamp_histogram": {
"buckets": [
{
"key_as_string": "2015-11-17T20:00:00.000Z",
"key": 1447790400000,
"doc_count": 2
},
{
"key_as_string": "2015-11-17T21:00:00.000Z",
"key": 1447794000000,
"doc_count": 1
}
]
}
},
{
"key": "864322",
"doc_count": 1,
"timestamp_histogram": {
"buckets": [
{
"key_as_string": "2015-11-17T21:00:00.000Z",
"key": 1447794000000,
"doc_count": 1
}
]
}
}
]
}
}
}
Here's the code I used:
http://sense.qbox.io/gist/6c0c30db1cf0fb8529bcfec21c0ce5c02a5ae94c

How to use elasticsearch facet query to groupby the result

I have a json data in the below format
{
"ID": { "Color": "Black", "Product": "Car" },
"ID": { "Color": "Black", "Product": "Car" },
"ID": { "Color": "Black", "Product": "Van" },
"ID": { "Color": "Black", "Product": "Van" },
"ID": { "Color": "Ash", "Product": "Bike" }
}
I want to calculate the count of car and the corresponding color. I am using elasticsearch facet to do this.
My query
$http.post('http://localhost:9200/product/productinfoinfo/_search?size=5', { "aggregations": { "ProductInfo": { "terms": { "field": "product" } } }, "facets": { "ProductColor": { "terms": { "field": "Color", "size": 10 } } } })
I am getting the output like below
"facets": { "ProductColor": { "_type": "terms", "missing": 0, "total": 7115, "other": 1448, "terms": [ { "term": "Black", "count": 4 }, { "term": "Ash","count":1} },
"aggregations": { "ProductInfo": { "doc_count_error_upper_bound": 94, "sum_other_doc_count": 11414, "buckets": [ { "key": "Car", "doc_count": 2 }, { "key": "Van", "doc_count": 2 }, { "key": "Bike", "doc_count": 1 } ] } } }
What I actually want is,
[ { "key": "Car", "doc_count": 2, "Color":"Black", "count":2 }, { "key": "Van", "doc_count": 2,"Color":"Black", "count":2 }, { "key": "Bike", "doc_count": 1,"Color":"Ash", "count":1 } ]
I would like to groupby the result . Is it possible to do it in elasticsearch query.
Thanks in advance
This is because you're using both aggregations and facets, which, if they are similar, are not meant to be used together.
Facets are deprecated and will be soon removed from ElasticSearch.
Aggregations are the way to go to make "group by"-like queries.
You just have to nest another terms aggregation in the first one, like this :
{
"aggs": {
"By_type": {
"terms": {
"field": "Product"
},
"aggs": {
"By_color": {
"terms": {
"field": "Color"
}
}
}
}
}
}
And the result will be close to what you want :
"aggregations": {
"By_type": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "bike",
"doc_count": 2,
"By_color": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "ash",
"doc_count": 1
},
{
"key": "black",
"doc_count": 1
}
]
}
},
{
"key": "car",
"doc_count": 2,
"By_color": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "black",
"doc_count": 2
}
]
}
},
{
"key": "van",
"doc_count": 1,
"By_color": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "black",
"doc_count": 1
}
]
}
}
]
}
}

Resources