Re-enable doc testing for Pipeline Aggregations (#24374)
* Re-enable doc testing for Pipeline Aggregations Also adds a response + test for movavg pipeline
This commit is contained in:
Zachary Tong
GitHub
parent
62712bf653
commit
130f1a56f1
|
|
@ -39,20 +39,6 @@ buildRestTests.expectedUnconvertedCandidates = [
|
|||
'reference/aggregations/metrics/scripted-metric-aggregation.asciidoc',
|
||||
'reference/aggregations/metrics/stats-aggregation.asciidoc',
|
||||
'reference/aggregations/metrics/tophits-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline.asciidoc',
|
||||
'reference/aggregations/pipeline/avg-bucket-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/bucket-script-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/bucket-selector-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/cumulative-sum-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/derivative-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/extended-stats-bucket-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/max-bucket-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/min-bucket-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/movavg-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/percentiles-bucket-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/serial-diff-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/stats-bucket-aggregation.asciidoc',
|
||||
'reference/aggregations/pipeline/sum-bucket-aggregation.asciidoc',
|
||||
'reference/cat/snapshots.asciidoc',
|
||||
'reference/cat/templates.asciidoc',
|
||||
'reference/cat/thread_pool.asciidoc',
|
||||
|
|
|
|||
|
|
@ -194,6 +194,7 @@ may be referred to as:
|
|||
---------------
|
||||
"buckets_path": "my_percentile[99.9]"
|
||||
---------------
|
||||
// NOTCONSOLE
|
||||
|
||||
[[gap-policy]]
|
||||
[float]
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ An `avg_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`avg_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -22,6 +22,7 @@ A `bucket_script` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
<1> Here, `my_var1` is the name of the variable for this buckets path to use in the script, `the_sum` is the path to
|
||||
the metrics to use for that variable.
|
||||
|
||||
|
|
|
|||
|
|
@ -27,6 +27,7 @@ A `bucket_selector` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
<1> Here, `my_var1` is the name of the variable for this buckets path to use in the script, `the_sum` is the path to
|
||||
the metrics to use for that variable.
|
||||
|
||||
|
|
|
|||
|
|
@ -19,6 +19,7 @@ A `cumulative_sum` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`cumulative_sum` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@ A `derivative` aggregation looks like this in isolation:
|
|||
"buckets_path": "the_sum"
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`derivative` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -20,6 +20,7 @@ A `extended_stats_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`extended_stats_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -19,6 +19,7 @@ A `max_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`max_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -19,6 +19,7 @@ A `min_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`min_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -34,6 +34,7 @@ A `moving_avg` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`moving_avg` Parameters
|
||||
|===
|
||||
|
|
@ -58,12 +59,12 @@ POST /_search
|
|||
"aggs": {
|
||||
"my_date_histo":{ <1>
|
||||
"date_histogram":{
|
||||
"field":"timestamp",
|
||||
"interval":"day"
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "lemmings" } <2>
|
||||
"sum":{ "field": "price" } <2>
|
||||
},
|
||||
"the_movavg":{
|
||||
"moving_avg":{ "buckets_path": "the_sum" } <3>
|
||||
|
|
@ -74,6 +75,7 @@ POST /_search
|
|||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
<1> A `date_histogram` named "my_date_histo" is constructed on the "timestamp" field, with one-day intervals
|
||||
<2> A `sum` metric is used to calculate the sum of a field. This could be any metric (sum, min, max, etc)
|
||||
|
|
@ -84,6 +86,57 @@ add normal metrics, such as a `sum`, inside of that histogram. Finally, the `mo
|
|||
The `buckets_path` parameter is then used to "point" at one of the sibling metrics inside of the histogram (see
|
||||
<<buckets-path-syntax>> for a description of the syntax for `buckets_path`.
|
||||
|
||||
An example response from the above aggregation may look like:
|
||||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
{
|
||||
"took": 11,
|
||||
"timed_out": false,
|
||||
"_shards": ...,
|
||||
"hits": ...,
|
||||
"aggregations": {
|
||||
"my_date_histo": {
|
||||
"buckets": [
|
||||
{
|
||||
"key_as_string": "2015/01/01 00:00:00",
|
||||
"key": 1420070400000,
|
||||
"doc_count": 3,
|
||||
"the_sum": {
|
||||
"value": 550.0
|
||||
}
|
||||
},
|
||||
{
|
||||
"key_as_string": "2015/02/01 00:00:00",
|
||||
"key": 1422748800000,
|
||||
"doc_count": 2,
|
||||
"the_sum": {
|
||||
"value": 60.0
|
||||
},
|
||||
"the_movavg": {
|
||||
"value": 550.0
|
||||
}
|
||||
},
|
||||
{
|
||||
"key_as_string": "2015/03/01 00:00:00",
|
||||
"key": 1425168000000,
|
||||
"doc_count": 2,
|
||||
"the_sum": {
|
||||
"value": 375.0
|
||||
},
|
||||
"the_movavg": {
|
||||
"value": 305.0
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// TESTRESPONSE[s/"took": 11/"took": $body.took/]
|
||||
// TESTRESPONSE[s/"_shards": \.\.\./"_shards": $body._shards/]
|
||||
// TESTRESPONSE[s/"hits": \.\.\./"hits": $body.hits/]
|
||||
|
||||
|
||||
==== Models
|
||||
|
||||
|
|
@ -102,16 +155,33 @@ the values from a `simple` moving average tend to "lag" behind the real data.
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "simple"
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "simple"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
A `simple` model has no special settings to configure
|
||||
|
||||
|
|
@ -138,15 +208,33 @@ the "lag" behind the data's mean, since older points have less influence.
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "linear"
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "linear"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
A `linear` model has no special settings to configure
|
||||
|
||||
|
|
@ -179,19 +267,36 @@ The EWMA model can be <<movavg-minimizer, Minimized>>
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "ewma",
|
||||
"settings" : {
|
||||
"alpha" : 0.5
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "ewma",
|
||||
"settings" : {
|
||||
"alpha" : 0.5
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
|
||||
[[single_0.2alpha]]
|
||||
|
|
@ -221,19 +326,37 @@ The Holt-Linear model can be <<movavg-minimizer, Minimized>>
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "holt",
|
||||
"settings" : {
|
||||
"alpha" : 0.5,
|
||||
"beta" : 0.5
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "holt",
|
||||
"settings" : {
|
||||
"alpha" : 0.5,
|
||||
"beta" : 0.5
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
In practice, the `alpha` value behaves very similarly in `holt` as `ewma`: small values produce more smoothing
|
||||
and more lag, while larger values produce closer tracking and less lag. The value of `beta` is often difficult
|
||||
|
|
@ -291,22 +414,40 @@ The additive Holt-Winters model can be <<movavg-minimizer, Minimized>>
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "holt_winters",
|
||||
"settings" : {
|
||||
"type" : "add",
|
||||
"alpha" : 0.5,
|
||||
"beta" : 0.5,
|
||||
"gamma" : 0.5,
|
||||
"period" : 7
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "holt_winters",
|
||||
"settings" : {
|
||||
"type" : "add",
|
||||
"alpha" : 0.5,
|
||||
"beta" : 0.5,
|
||||
"gamma" : 0.5,
|
||||
"period" : 7
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
|
||||
[[holt_winters_add]]
|
||||
|
|
@ -334,23 +475,41 @@ you can disable this behavior with `pad: false`
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "holt_winters",
|
||||
"settings" : {
|
||||
"type" : "mult",
|
||||
"alpha" : 0.5,
|
||||
"beta" : 0.5,
|
||||
"gamma" : 0.5,
|
||||
"period" : 7,
|
||||
"pad" : true
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "holt_winters",
|
||||
"settings" : {
|
||||
"type" : "mult",
|
||||
"alpha" : 0.5,
|
||||
"beta" : 0.5,
|
||||
"gamma" : 0.5,
|
||||
"period" : 7,
|
||||
"pad" : true
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
==== Prediction
|
||||
|
||||
|
|
@ -363,16 +522,34 @@ as your buckets:
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "simple",
|
||||
"predict" : 10
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"window" : 30,
|
||||
"model" : "simple",
|
||||
"predict" : 10
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
The `simple`, `linear` and `ewma` models all produce "flat" predictions: they essentially converge on the mean
|
||||
of the last value in the series, producing a flat:
|
||||
|
|
@ -423,19 +600,38 @@ Minimization is enabled/disabled via the `minimize` parameter:
|
|||
|
||||
[source,js]
|
||||
--------------------------------------------------
|
||||
POST /_search
|
||||
{
|
||||
"the_movavg":{
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"model" : "holt_winters",
|
||||
"window" : 30,
|
||||
"minimize" : true, <1>
|
||||
"settings" : {
|
||||
"period" : 7
|
||||
"size": 0,
|
||||
"aggs": {
|
||||
"my_date_histo":{
|
||||
"date_histogram":{
|
||||
"field":"date",
|
||||
"interval":"1M"
|
||||
},
|
||||
"aggs":{
|
||||
"the_sum":{
|
||||
"sum":{ "field": "price" }
|
||||
},
|
||||
"the_movavg": {
|
||||
"moving_avg":{
|
||||
"buckets_path": "the_sum",
|
||||
"model" : "holt_winters",
|
||||
"window" : 30,
|
||||
"minimize" : true, <1>
|
||||
"settings" : {
|
||||
"period" : 7
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// CONSOLE
|
||||
// TEST[setup:sales]
|
||||
|
||||
<1> Minimization is enabled with the `minimize` parameter
|
||||
|
||||
When enabled, minimization will find the optimal values for `alpha`, `beta` and `gamma`. The user should still provide
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ A `percentiles_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`sum_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -46,6 +46,7 @@ A `serial_diff` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`serial_diff` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ A `stats_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`stats_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ A `sum_bucket` aggregation looks like this in isolation:
|
|||
}
|
||||
}
|
||||
--------------------------------------------------
|
||||
// NOTCONSOLE
|
||||
|
||||
.`sum_bucket` Parameters
|
||||
|===
|
||||
|
|
|
|||
Loading…
Reference in New Issue