How to use cumulative_sum with a previous aggregation? - elasticsearch

I would like to plot a cumulative sum of some events, per day. The cumulative sum aggregation seems to be the way to go so I tried to reuse the example given in the docs.
The first aggregation works fine, the following query
{
"aggs": {
"vulns_day" : {
"date_histogram" :{
"field": "HOST_START_iso",
"interval": "day"
}
}
}
}
gives replies such as
(...)
{
"key_as_string": "2016-09-08T00:00:00.000Z",
"key": 1473292800000,
"doc_count": 76330
},
{
"key_as_string": "2016-09-09T00:00:00.000Z",
"key": 1473379200000,
"doc_count": 37712
},
(...)
I then wanted to query the cumulative sum of doc_count above via
{
"aggs": {
"vulns_day" : {
"date_histogram" :{
"field": "HOST_START_iso",
"interval": "day"
}
},
"aggs": {
"vulns_cumulated": {
"cumulative_sum": {
"buckets_path": "doc_count"
}
}
}
}
}
but it gives an error:
"reason": {
"type": "search_parse_exception",
"reason": "Could not find aggregator type [vulns_cumulated] in [aggs]",
I see that bucket_path should point to the elements to be summed and the example for cumulative aggregations created a specific intermediate sum but I do not have anything to sum (beside doc_count).

I guess, you should change your query like this:
{
"aggs": {
"vulns_day": {
"date_histogram": {
"field": "HOST_START_iso",
"interval": "day"
},
"aggs": {
"document_count": {
"value_count": {
"field": "HOST_START_iso"
}
},
"vulns_cumulated": {
"cumulative_sum": {
"buckets_path": "document_count"
}
}
}
}
}
}

I found the solution. Since doc_count did not seem to be available, I tried to retrieve stats for the time parameter, and use its count value. It worked:
{
"size": 0,
"aggs": {
"vulns_day": {
"date_histogram": {
"field": "HOST_START_iso",
"interval": "day"
},
"aggs": {
"dates_stats": {
"stats": {
"field": "HOST_START_iso"
}
},
"vulns_cumulated": {
"cumulative_sum": {
"buckets_path": "dates_stats.count"
}
}
}
}
}
}

Related

Elasticsearch: How set 'doc_count' of a FILTER-Aggregation in relation to total 'doc_count'

A seemingly very trivial problem prompted me today to read the Elasticsearch documentation again diligently. So far, however, I have not come across the solution....
Question:
is ther's a simple way to set the doc_count of a filter aggregation in relation to the total doc_count?
Here's a snippet from my search-request-json.
In the feature_occurrences aggregation I filtered documents.
Now I want to calculate the ratio filtered/all Docs in each time bucket.
GET my_index/_search
{
"aggs": {
"time_buckets": {
"date_histogram": {
"field": "date",
"calendar_interval": "1d",
"min_doc_count": 0
},
"aggs": {
"feature_occurrences": {
"filter": {
"term": {
"x": "y"
}
}
},
"feature_occurrences_per_doc" : {
// feature_occurences.doc_count / doc_count
}
Any Ideas ?
You can use bucket_script to calc the ratio:
{
"aggs": {
"date": {
"date_histogram": {
"field": "#timestamp",
"interval": "hour"
},
"aggs": {
"feature_occurrences": {
"filter": {
"term": {
"cloud.region": "westeurope"
}
}
},
"ratio": {
"bucket_script": {
"buckets_path": {
"doc_count": "_count",
"features_count": "feature_occurrences._count"
},
"script": "params.features_count / params.doc_count"
}
}
}
}
}
}
Elastic bucket script doc:
https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-pipeline-bucket-script-aggregation.html

How to define percentage of result items with specific field in Elasticsearch query?

I have a search query that returns all items matching users that have type manager or lead.
{
"from": 0,
"size": 20,
"query": {
"bool": {
"should": [
{
"terms": {
"type": ["manager", "lead"]
}
}
]
}
}
}
Is there a way to define what percentage of the results should be of type "manager"?
In other words, I want the results to have 80% of users with type manager and 20% with type lead.
I want to make a suggestion to use bucket_path aggregation. As I know this aggregation needs to be run in sub-aggs of a histogram aggregation. As you have such field in your mapping so I think this query should work for you:
{
"size": 0,
"aggs": {
"NAME": {
"date_histogram": {
"field": "my_datetime",
"interval": "month"
},
"aggs": {
"role_type": {
"terms": {
"field": "type",
"size": 10
},
"aggs": {
"count": {
"value_count": {
"field": "_id"
}
}
}
},
"role_1_ratio": {
"bucket_script": {
"buckets_path": {
"role_1": "role_type['manager']>count",
"role_2": "role_type['lead']>count"
},
"script": "params.role_1 / (params.role_1+params.role_2)*100"
}
},
"role_2_ratio": {
"bucket_script": {
"buckets_path": {
"role_1": "role_type['manager']>count",
"role_2": "role_type['lead']>count"
},
"script": "params.role_2 / (params.role_1+params.role_2)*100"
}
}
}
}
}
}
Please let me know if it didn't work well for you.

ElasticSearch: Nested buckets aggregation

I'm new to ElasticSearch, so this question could be quite trivial for you, but here I go:
I'm using kibana_sample_data_ecommerce, which documents have a mapping like this
{
...
"order_date" : <datetime>
"taxful_total_price" : <double>
...
}
I want to get a basic daily behavior of the data:
Expecting documents like this:
[
{
"qtime" : "00:00",
"mean" : 20,
"std" : 40
},
{
"qtime" : "01:00",
"mean" : 150,
"std" : 64
},
...
]
So, the process I think that I need to do is:
Group by day all records ->
Group by time window for each day ->
Sum all record in each time window ->
Cumulative Sum for each sum by time window, thus, I get behavior of a day ->
Extended_stats by the same time window across all days
And that can be expressed like this:
But I can't unwrap those buckets to process those statistics. May you give me some advice to do that operation and get that result?
Here is my current query(kibana developer tools):
POST kibana_sample_data_ecommerce/_search
{
"size": 0,
"query": {
"bool": {
"must": [
{
"range": {
"order_date": {
"gt": "now-1M",
"lte": "now"
}
}
}
]
}
},
"aggs": {
"day_histo": {
"date_histogram": {
"field": "order_date",
"calendar_interval": "day"
},
"aggs": {
"qmin_histo": {
"date_histogram": {
"field": "order_date",
"calendar_interval": "hour"
},
"aggs": {
"qminute_sum": {
"sum": {
"field": "taxful_total_price"
}
},
"cumulative_qminute_sum": {
"cumulative_sum": {
"buckets_path": "qminute_sum"
}
}
}
}
}
}
}
}
Here's how you pull off the extended stats:
{
"size": 0,
"query": {
"bool": {
"must": [
{
"range": {
"order_date": {
"gt": "now-4M",
"lte": "now"
}
}
}
]
}
},
"aggs": {
"by_day": {
"date_histogram": {
"field": "order_date",
"calendar_interval": "day"
},
"aggs": {
"by_hour": {
"date_histogram": {
"field": "order_date",
"calendar_interval": "hour"
},
"aggs": {
"by_taxful_total_price": {
"extended_stats": {
"field": "taxful_total_price"
}
}
}
}
}
}
}
}
yielding

Elasticsearch Aggregations: Only return results of one of them?

I'm trying to find a way to only return the results of one aggregation in an Elasticsearch query. I have a max bucket aggregation (the one that I want to see) that is calculated from a sum bucket aggregation based on a date histogram aggregation. Right now, I have to go through 1,440 results to get to the one I want to see. I've already removed the results of the base query with the size: 0 modifier, but is there a way to do something similar with the aggregations as well? I've tried slipping the same thing into a few places with no luck.
Here's the query:
{
"size": 0,
"query": {
"range": {
"timestamp": {
"gte": "2018-11-28",
"lte": "2018-11-28"
}
}
},
"aggs": {
"hits_per_minute": {
"date_histogram": {
"field": "timestamp",
"interval": "minute"
},
"aggs": {
"total_hits": {
"sum": {
"field": "hits_count"
}
}
}
},
"max_transactions_per_minute": {
"max_bucket": {
"buckets_path": "hits_per_minute>total_hits"
}
}
}
}
Fortunately enough, you can do that with bucket_sort aggregation, which was added in Elasticsearch 6.4.
Do it with bucket_sort
POST my_index/doc/_search
{
"size": 0,
"query": {
"range": {
"timestamp": {
"gte": "2018-11-28",
"lte": "2018-11-28"
}
}
},
"aggs": {
"hits_per_minute": {
"date_histogram": {
"field": "timestamp",
"interval": "minute"
},
"aggs": {
"total_hits": {
"sum": {
"field": "hits_count"
}
},
"max_transactions_per_minute": {
"bucket_sort": {
"sort": [
{"total_hits": {"order": "desc"}}
],
"size": 1
}
}
}
}
}
}
This will give you a response like this:
{
...
"aggregations": {
"hits_per_minute": {
"buckets": [
{
"key_as_string": "2018-11-28T21:10:00.000Z",
"key": 1543957800000,
"doc_count": 3,
"total_hits": {
"value": 11
}
}
]
}
}
}
Note that there is no extra aggregation in the output and the output of hits_per_minute is truncated (because we asked to give exactly one, topmost bucket).
Do it with filter_path
There is also a generic way to filter the output of Elasticsearch: Response filtering, as this answer suggests.
In this case it will be enough to just do the following query:
POST my_index/doc/_search?filter_path=aggregations.max_transactions_per_minute
{ ... (original query) ... }
That would give the response:
{
"aggregations": {
"max_transactions_per_minute": {
"value": 11,
"keys": [
"2018-12-04T21:10:00.000Z"
]
}
}
}

How to display only the key from the bucket

I have an index with millions of documents. Suppose each of my documents has some code, and I need to find the list of codes matching some criteria. The only way I found doing that, is using whole lot of aggregations, so I created an ugly query which does exactly what I want:
POST my-index/_search
{
"query": {
"range": {
"timestamp": {
"gte": "2017-08-01T00:00:00.000",
"lt": "2017-08-08T00:00:00.000"
}
}
},
"size": 0,
"aggs": {
"codes": {
"terms": {
"field": "code",
"size": 10000
},
"aggs": {
"days": {
"date_histogram": {
"field": "timestamp",
"interval": "day",
"format": "dd"
},
"aggs": {
"hours": {
"date_histogram": {
"field": "timestamp",
"interval": "hour",
"format": "yyyy-MM-dd:HH"
},
"aggs": {
"hour_income": {
"sum": {
"field": "price"
}
}
}
},
"max_income": {
"max_bucket": {
"buckets_path": "hours>hour_income"
}
},
"day_income": {
"sum_bucket": {
"buckets_path": "hours.hour_income"
}
},
"more_than_sixty_percent": {
"bucket_script": {
"buckets_path": {
"dayIncome": "day_income",
"maxIncome": "max_income"
},
"script": "params.maxIncome - params.dayIncome * 60 / 100 > 0 ? 1 : 0"
}
}
}
},
"amount_of_days": {
"sum_bucket": {
"buckets_path": "days.more_than_sixty_percent"
}
},
"bucket_filter": {
"bucket_selector": {
"buckets_path": {
"amountOfDays": "amount_of_days"
},
"script": "params.amountOfDays >= 3"
}
}
}
}
}
}
The response I get is a few millions lines of JSON, consisting of buckets. Each bucket has more than 700 lines (and buckets of its own), but all I need is its key, so that I have my list of codes. I guess it's not good having a response a few thousand times larger than neccessary, and there might be problems with parsing. So I wanted to ask, is there any way to hide the other info in the bucket and get only the keys?
Thanks.

Resources