[7.x][DOCS] Update example and nesting in get data frame analytics job stats API (#55612)
This commit is contained in:
Lisa Cawley
GitHub
parent
6e1b958069
commit
314ca78e31
|
|
@ -82,17 +82,26 @@ include::{docdir}/ml/ml-shared.asciidoc[tag=node-datafeeds]
|
|||
--
|
||||
[%collapsible%open]
|
||||
====
|
||||
`id`:::
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-id]
|
||||
|
||||
`name`::: The node name. For example, `0-o0tOo`.
|
||||
`attributes`:::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-attributes]
|
||||
|
||||
`ephemeral_id`:::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-ephemeral-id]
|
||||
|
||||
`transport_address`::: The host and port where transport HTTP connections are
|
||||
accepted. For example, `127.0.0.1:9300`.
|
||||
`attributes`::: For example, `{"ml.machine_memory": "17179869184"}`.
|
||||
`id`:::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-id]
|
||||
|
||||
`name`:::
|
||||
(string)
|
||||
The node name. For example, `0-o0tOo`.
|
||||
|
||||
`transport_address`:::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-transport-address]
|
||||
|
||||
====
|
||||
--
|
||||
|
||||
|
|
|
|||
|
|
@ -281,8 +281,8 @@ available only for open jobs.
|
|||
[%collapsible%open]
|
||||
====
|
||||
`attributes`:::
|
||||
(object) Lists node attributes. For example,
|
||||
`{"ml.machine_memory": "17179869184"}`.
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-attributes]
|
||||
|
||||
`ephemeral_id`:::
|
||||
(string)
|
||||
|
|
@ -293,10 +293,12 @@ include::{docdir}/ml/ml-shared.asciidoc[tag=node-ephemeral-id]
|
|||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-id]
|
||||
|
||||
`name`:::
|
||||
(string) The node name.
|
||||
(string)
|
||||
The node name.
|
||||
|
||||
`transport_address`:::
|
||||
(string) The host and port where transport HTTP connections are accepted.
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-transport-address]
|
||||
====
|
||||
//End node
|
||||
|
||||
|
|
|
|||
|
|
@ -61,12 +61,442 @@ include::{docdir}/ml/ml-shared.asciidoc[tag=size]
|
|||
[[ml-get-dfanalytics-stats-response-body]]
|
||||
==== {api-response-body-title}
|
||||
|
||||
The API returns the following information:
|
||||
|
||||
`data_frame_analytics`::
|
||||
(array)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=data-frame-analytics-stats]
|
||||
An array of objects that contain usage information for {dfanalytics-jobs}, which
|
||||
are sorted by the `id` value in ascending order.
|
||||
+
|
||||
.Properties of {dfanalytics-job} usage resources
|
||||
[%collapsible%open]
|
||||
====
|
||||
//Begin analysis_stats
|
||||
`analysis_stats`:::
|
||||
(object)
|
||||
An object containing information about the analysis job.
|
||||
+
|
||||
.Properties of `analysis_stats`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
//Begin classification_stats
|
||||
`classification_stats`::::
|
||||
(object)
|
||||
An object containing information about the {classanalysis} job.
|
||||
+
|
||||
.Properties of `classification_stats`
|
||||
[%collapsible%open]
|
||||
======
|
||||
//Begin class_hyperparameters
|
||||
`hyperparameters`::::
|
||||
(object)
|
||||
An object containing the parameters of the {classanalysis} job.
|
||||
+
|
||||
.Properties of `hyperparameters`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`alpha`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-alpha]
|
||||
|
||||
`class_assignment_objective`::::
|
||||
(string)
|
||||
Defines whether class assignment maximizes the accuracy or the minimum recall
|
||||
metric. Possible values are `maximize_accuracy` and `maximize_minimum_recall`.
|
||||
|
||||
`downsample_factor`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-downsample-factor]
|
||||
|
||||
`eta`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-eta]
|
||||
|
||||
`eta_growth_rate_per_tree`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-eta-growth]
|
||||
|
||||
`feature_bag_fraction`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-feature-bag-fraction]
|
||||
|
||||
`gamma`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-gamma]
|
||||
|
||||
`lambda`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-lambda]
|
||||
|
||||
`max_attempts_to_add_tree`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-attempts]
|
||||
|
||||
`max_optimization_rounds_per_hyperparameter`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-optimization-rounds]
|
||||
|
||||
`max_trees`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-trees]
|
||||
|
||||
`num_folds`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-num-folds]
|
||||
|
||||
`num_splits_per_feature`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-num-splits]
|
||||
|
||||
`soft_tree_depth_limit`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-soft-limit]
|
||||
|
||||
`soft_tree_depth_tolerance`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-soft-tolerance]
|
||||
=======
|
||||
//End class_hyperparameters
|
||||
|
||||
`iteration`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-iteration]
|
||||
|
||||
`timestamp`::::
|
||||
(date)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timestamp]
|
||||
|
||||
//Begin class_timing_stats
|
||||
`timing_stats`::::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats]
|
||||
+
|
||||
.Properties of `timing_stats`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`elapsed_time`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-elapsed]
|
||||
|
||||
`iteration_time`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-iteration]
|
||||
=======
|
||||
//End class_timing_stats
|
||||
|
||||
//Begin class_validation_loss
|
||||
`validation_loss`::::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss]
|
||||
+
|
||||
.Properties of `validation_loss`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`fold_values`::::
|
||||
(array of strings)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss-fold]
|
||||
|
||||
`loss_type`::::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss-type]
|
||||
=======
|
||||
//End class_validation_loss
|
||||
======
|
||||
//End classification_stats
|
||||
|
||||
//Begin outlier_detection_stats
|
||||
`outlier_detection_stats`::::
|
||||
(object)
|
||||
An object containing information about the {oldetection} job.
|
||||
+
|
||||
.Properties of `outlier_detection_stats`
|
||||
[%collapsible%open]
|
||||
======
|
||||
//Begin parameters
|
||||
`parameters`::::
|
||||
(object)
|
||||
The list of job parameters specified by the user or determined by algorithmic
|
||||
heuristics.
|
||||
+
|
||||
.Properties of `parameters`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`compute_feature_influence`::::
|
||||
(boolean)
|
||||
If true, feature influence calculation is enabled.
|
||||
|
||||
`feature_influence_threshold`::::
|
||||
(double)
|
||||
The minimum {olscore} that a document needs to have to calculate its feature
|
||||
influence score.
|
||||
|
||||
`method`::::
|
||||
(string)
|
||||
The method that {oldetection} uses. Possible values are `lof`, `ldof`,
|
||||
`distance_kth_nn`, `distance_knn`, and `ensemble`.
|
||||
|
||||
`n_neighbors`::::
|
||||
(integer)
|
||||
The value for how many nearest neighbors each method of {oldetection} uses to
|
||||
calculate its outlier score.
|
||||
|
||||
`outlier_fraction`::::
|
||||
(double)
|
||||
The proportion of the data set that is assumed to be outlying prior to
|
||||
{oldetection}.
|
||||
|
||||
`standardization_enabled`::::
|
||||
(boolean)
|
||||
If true, then the following operation is performed on the columns before
|
||||
computing {olscores}: (x_i - mean(x_i)) / sd(x_i).
|
||||
=======
|
||||
//End parameters
|
||||
|
||||
`timestamp`::::
|
||||
(date)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timestamp]
|
||||
|
||||
//Begin od_timing_stats
|
||||
`timing_stats`::::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats]
|
||||
+
|
||||
.Property of `timing_stats`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`elapsed_time`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-elapsed]
|
||||
=======
|
||||
//End od_timing_stats
|
||||
======
|
||||
//End outlier_detection_stats
|
||||
|
||||
//Begin regression_stats
|
||||
`regression_stats`::::
|
||||
(object)
|
||||
An object containing information about the {reganalysis}.
|
||||
+
|
||||
.Properties of `regression_stats`
|
||||
[%collapsible%open]
|
||||
======
|
||||
//Begin reg_hyperparameters
|
||||
`hyperparameters`::::
|
||||
(object)
|
||||
An object containing the parameters of the {reganalysis}.
|
||||
+
|
||||
.Properties of `hyperparameters`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`alpha`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-alpha]
|
||||
|
||||
`downsample_factor`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-downsample-factor]
|
||||
|
||||
`eta`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-eta]
|
||||
|
||||
`eta_growth_rate_per_tree`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-eta-growth]
|
||||
|
||||
`feature_bag_fraction`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-feature-bag-fraction]
|
||||
|
||||
`gamma`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-gamma]
|
||||
|
||||
`lambda`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-lambda]
|
||||
|
||||
`max_attempts_to_add_tree`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-attempts]
|
||||
|
||||
`max_optimization_rounds_per_hyperparameter`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-optimization-rounds]
|
||||
|
||||
`max_trees`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-trees]
|
||||
|
||||
`num_folds`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-num-folds]
|
||||
|
||||
`num_splits_per_feature`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-num-splits]
|
||||
|
||||
`soft_tree_depth_limit`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-soft-limit]
|
||||
|
||||
`soft_tree_depth_tolerance`::::
|
||||
(double)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-soft-tolerance]
|
||||
=======
|
||||
//End reg_hyperparameters
|
||||
|
||||
`iteration`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-iteration]
|
||||
|
||||
`timestamp`::::
|
||||
(date)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timestamp]
|
||||
|
||||
//Begin reg_timing_stats
|
||||
`timing_stats`::::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats]
|
||||
+
|
||||
.Propertis of `timing_stats`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`elapsed_time`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-elapsed]
|
||||
|
||||
`iteration_time`::::
|
||||
(integer)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-iteration]
|
||||
=======
|
||||
//End reg_timing_stats
|
||||
|
||||
//Begin reg_validation_loss
|
||||
`validation_loss`::::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss]
|
||||
+
|
||||
.Properties of `validation_loss`
|
||||
[%collapsible%open]
|
||||
=======
|
||||
`fold_values`::::
|
||||
(array of strings)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss-fold]
|
||||
|
||||
`loss_type`::::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss-type]
|
||||
=======
|
||||
//End reg_validation_loss
|
||||
======
|
||||
//End regression_stats
|
||||
=====
|
||||
//End analysis_stats
|
||||
|
||||
|
||||
`assignment_explanation`:::
|
||||
(string)
|
||||
For running jobs only, contains messages relating to the selection of a node to
|
||||
run the job.
|
||||
|
||||
//Begin data_counts
|
||||
`data_counts`:::
|
||||
(object)
|
||||
An object that provides counts for the quantity of documents skipped, used in
|
||||
training, or available for testing.
|
||||
+
|
||||
.Properties of `data_counts`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
`skipped_docs_count`:::
|
||||
(integer)
|
||||
The number of documents that are skipped during the analysis because they
|
||||
contained values that are not supported by the analysis. For example,
|
||||
{oldetection} does not support missing fields so it skips documents with missing
|
||||
fields. Likewise, all types of analysis skip documents that contain arrays with
|
||||
more than one element.
|
||||
|
||||
`test_docs_count`:::
|
||||
(integer)
|
||||
The number of documents that are not used for training the model and can be used
|
||||
for testing.
|
||||
|
||||
`training_docs_count`:::
|
||||
(integer)
|
||||
The number of documents that are used for training the model.
|
||||
=====
|
||||
//End data_counts
|
||||
|
||||
`id`:::
|
||||
(string)
|
||||
The unique identifier of the {dfanalytics-job}.
|
||||
|
||||
`memory_usage`:::
|
||||
(Optional, object)
|
||||
An object describing memory usage of the analytics. It is present only after the
|
||||
job is started and memory usage is reported.
|
||||
+
|
||||
.Properties of `memory_usage`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
`peak_usage_bytes`:::
|
||||
(long)
|
||||
The number of bytes used at the highest peak of memory usage.
|
||||
|
||||
`timestamp`:::
|
||||
(date)
|
||||
The timestamp when memory usage was calculated.
|
||||
=====
|
||||
|
||||
`node`:::
|
||||
(object)
|
||||
Contains properties for the node that runs the job. This information is
|
||||
available only for running jobs.
|
||||
+
|
||||
.Properties of `node`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
`attributes`:::
|
||||
(object)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-attributes]
|
||||
|
||||
`ephemeral_id`:::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-ephemeral-id]
|
||||
|
||||
`id`:::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-id]
|
||||
|
||||
`name`:::
|
||||
(string)
|
||||
The node name.
|
||||
|
||||
`transport_address`:::
|
||||
(string)
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=node-transport-address]
|
||||
=====
|
||||
|
||||
`progress`:::
|
||||
(array) The progress report of the {dfanalytics-job} by phase.
|
||||
+
|
||||
.Properties of phase objects
|
||||
[%collapsible%open]
|
||||
=====
|
||||
`phase`:::
|
||||
(string) Defines the phase of the {dfanalytics-job}. Possible phases:
|
||||
`reindexing`, `loading_data`, `analyzing`, and `writing_results`.
|
||||
|
||||
`progress_percent`:::
|
||||
(integer) The progress that the {dfanalytics-job} has made expressed in
|
||||
percentage.
|
||||
=====
|
||||
|
||||
`state`:::
|
||||
(string) The status of the {dfanalytics-job}, which can be one of the following
|
||||
values: `analyzing`, `failed`, `reindexing`, `started`, `starting`, `stopped`,
|
||||
`stopping`.
|
||||
====
|
||||
//End of data_frame_analytics
|
||||
|
||||
[[ml-get-dfanalytics-stats-response-codes]]
|
||||
==== {api-response-codes-title}
|
||||
|
|
@ -79,11 +509,14 @@ include::{docdir}/ml/ml-shared.asciidoc[tag=data-frame-analytics-stats]
|
|||
[[ml-get-dfanalytics-stats-example]]
|
||||
==== {api-examples-title}
|
||||
|
||||
The following API retrieves usage information for the
|
||||
{ml-docs}/ecommerce-outliers.html[{oldetection} {dfanalytics-job} example]:
|
||||
|
||||
[source,console]
|
||||
--------------------------------------------------
|
||||
GET _ml/data_frame/analytics/loganalytics/_stats
|
||||
GET _ml/data_frame/analytics/ecommerce/_stats
|
||||
--------------------------------------------------
|
||||
// TEST[skip:TBD]
|
||||
// TEST[skip:Kibana sample data]
|
||||
|
||||
|
||||
The API returns the following results:
|
||||
|
|
@ -91,29 +524,54 @@ The API returns the following results:
|
|||
[source,console-result]
|
||||
----
|
||||
{
|
||||
"count": 1,
|
||||
"data_frame_analytics": [
|
||||
"count" : 1,
|
||||
"data_frame_analytics" : [
|
||||
{
|
||||
"id": "loganalytics",
|
||||
"state": "stopped",
|
||||
"progress": [
|
||||
"id" : "ecommerce",
|
||||
"state" : "stopped",
|
||||
"progress" : [
|
||||
{
|
||||
"phase": "reindexing",
|
||||
"progress_percent": 0
|
||||
"phase" : "reindexing",
|
||||
"progress_percent" : 100
|
||||
},
|
||||
{
|
||||
"phase": "loading_data",
|
||||
"progress_percent": 0
|
||||
"phase" : "loading_data",
|
||||
"progress_percent" : 100
|
||||
},
|
||||
{
|
||||
"phase": "analyzing",
|
||||
"progress_percent": 0
|
||||
"phase" : "analyzing",
|
||||
"progress_percent" : 100
|
||||
},
|
||||
{
|
||||
"phase": "writing_results",
|
||||
"progress_percent": 0
|
||||
"phase" : "writing_results",
|
||||
"progress_percent" : 100
|
||||
}
|
||||
],
|
||||
"data_counts" : {
|
||||
"training_docs_count" : 3321,
|
||||
"test_docs_count" : 0,
|
||||
"skipped_docs_count" : 0
|
||||
},
|
||||
"memory_usage" : {
|
||||
"timestamp" : 1586905058000,
|
||||
"peak_usage_bytes" : 279484
|
||||
},
|
||||
"analysis_stats" : {
|
||||
"outlier_detection_stats" : {
|
||||
"timestamp" : 1586905058000,
|
||||
"parameters" : {
|
||||
"n_neighbors" : 0,
|
||||
"method" : "ensemble",
|
||||
"compute_feature_influence" : true,
|
||||
"feature_influence_threshold" : 0.1,
|
||||
"outlier_fraction" : 0.05,
|
||||
"standardization_enabled" : true
|
||||
},
|
||||
"timing_stats" : {
|
||||
"elapsed_time" : 245
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -371,429 +371,6 @@ include::{docdir}/ml/ml-shared.asciidoc[tag=time-format]
|
|||
====
|
||||
end::data-description[]
|
||||
|
||||
tag::data-frame-analytics-stats[]
|
||||
An array of statistics objects for {dfanalytics-jobs}, which are
|
||||
sorted by the `id` value in ascending order.
|
||||
|
||||
//Begin analysis_stats
|
||||
`analysis_stats`::
|
||||
(object)
|
||||
An object containing statistical data about the analysis.
|
||||
+
|
||||
.Properties of `analysis_stats`
|
||||
[%collapsible%open]
|
||||
====
|
||||
//Begin classification_stats
|
||||
`classification_stats`:::
|
||||
(object)
|
||||
An object containing statistical data about the {classanalysis}.
|
||||
+
|
||||
.Properties of `classification_stats`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
//Begin class_hyperparameters
|
||||
`hyperparameters`::::
|
||||
(object)
|
||||
An object containing the parameters of the {classanalysis}.
|
||||
+
|
||||
.Properties of `hyperparameters`
|
||||
[%collapsible%open]
|
||||
======
|
||||
tag::dfas-alpha[]
|
||||
`alpha`::::
|
||||
(double)
|
||||
Regularization factor to penalize deeper trees when training decision trees.
|
||||
end::dfas-alpha[]
|
||||
|
||||
`class_assignment_objective`::::
|
||||
(string)
|
||||
Defines whether class assignment maximizes the accuracy or the minimum recall
|
||||
metric. Possible values are `maximize_accuracy` and `maximize_minimum_recall`.
|
||||
|
||||
tag::dfas-downsample-factor[]
|
||||
`downsample_factor`::::
|
||||
(double)
|
||||
The value of the downsample factor.
|
||||
end::dfas-downsample-factor[]
|
||||
|
||||
tag::dfas-eta[]
|
||||
`eta`::::
|
||||
(double)
|
||||
The value of the eta hyperparameter.
|
||||
end::dfas-eta[]
|
||||
|
||||
tag::dfas-eta-growth[]
|
||||
`eta_growth_rate_per_tree`::::
|
||||
(double)
|
||||
Specifies the rate at which the `eta` increases for each new tree that is added to the
|
||||
forest. For example, a rate of `1.05` increases `eta` by 5%.
|
||||
end::dfas-eta-growth[]
|
||||
|
||||
tag::dfas-feature-bag-fraction[]
|
||||
`feature_bag_fraction`::::
|
||||
(double)
|
||||
The fraction of features that is used when selecting a random bag for each
|
||||
candidate split.
|
||||
end::dfas-feature-bag-fraction[]
|
||||
|
||||
tag::dfas-gamma[]
|
||||
`gamma`::::
|
||||
(double)
|
||||
Regularization factor to penalize trees with large numbers of nodes.
|
||||
end::dfas-gamma[]
|
||||
|
||||
tag::dfas-lambda[]
|
||||
`lambda`::::
|
||||
(double)
|
||||
Regularization factor to penalize large leaf weights.
|
||||
end::dfas-lambda[]
|
||||
|
||||
tag::dfas-max-attempts[]
|
||||
`max_attempts_to_add_tree`::::
|
||||
(integer)
|
||||
If the algorithm fails to determine a non-trivial tree (more than a single
|
||||
leaf), this parameter determines how many of such consecutive failures are
|
||||
tolerated. Once the number of attempts exceeds the threshold, the forest
|
||||
training stops.
|
||||
end::dfas-max-attempts[]
|
||||
|
||||
tag::dfas-max-optimization-rounds[]
|
||||
`max_optimization_rounds_per_hyperparameter`::::
|
||||
(integer)
|
||||
A multiplier responsible for determining the maximum number of
|
||||
hyperparameter optimization steps in the Bayesian optimization procedure.
|
||||
The maximum number of steps is determined based on the number of undefined hyperparameters
|
||||
times the maximum optimization rounds per hyperparameter.
|
||||
end::dfas-max-optimization-rounds[]
|
||||
|
||||
tag::dfas-max-trees[]
|
||||
`max_trees`::::
|
||||
(integer)
|
||||
The maximum number of trees in the forest.
|
||||
end::dfas-max-trees[]
|
||||
|
||||
tag::dfas-num-folds[]
|
||||
`num_folds`::::
|
||||
(integer)
|
||||
The maximum number of folds for the cross-validation procedure.
|
||||
end::dfas-num-folds[]
|
||||
|
||||
tag::dfas-num-splits[]
|
||||
`num_splits_per_feature`::::
|
||||
(integer)
|
||||
Determines the maximum number of splits for every feature that can occur in a
|
||||
decision tree when the tree is trained.
|
||||
end::dfas-num-splits[]
|
||||
|
||||
tag::dfas-soft-limit[]
|
||||
`soft_tree_depth_limit`::::
|
||||
(double)
|
||||
Tree depth limit is used for calculating the tree depth penalty. This is a soft
|
||||
limit, it can be exceeded.
|
||||
end::dfas-soft-limit[]
|
||||
|
||||
tag::dfas-soft-tolerance[]
|
||||
`soft_tree_depth_tolerance`::::
|
||||
(double)
|
||||
Tree depth tolerance is used for calculating the tree depth penalty. This is a
|
||||
soft limit, it can be exceeded.
|
||||
end::dfas-soft-tolerance[]
|
||||
======
|
||||
//End class_hyperparameters
|
||||
|
||||
tag::dfas-iteration[]
|
||||
`iteration`::::
|
||||
(integer)
|
||||
The number of iterations on the analysis.
|
||||
end::dfas-iteration[]
|
||||
|
||||
tag::dfas-timestamp[]
|
||||
`timestamp`::::
|
||||
(date)
|
||||
The timestamp when the statistics were reported in milliseconds since the epoch.
|
||||
end::dfas-timestamp[]
|
||||
|
||||
//Begin class_timing_stats
|
||||
tag::dfas-timing-stats[]
|
||||
`timing_stats`::::
|
||||
(object)
|
||||
An object containing time statistics about the {dfanalytics-job}.
|
||||
end::dfas-timing-stats[]
|
||||
+
|
||||
.Properties of `timing_stats`
|
||||
[%collapsible%open]
|
||||
======
|
||||
tag::dfas-timing-stats-elapsed[]
|
||||
`elapsed_time`::::
|
||||
(integer)
|
||||
Runtime of the analysis in milliseconds.
|
||||
end::dfas-timing-stats-elapsed[]
|
||||
|
||||
tag::dfas-timing-stats-iteration[]
|
||||
`iteration_time`::::
|
||||
(integer)
|
||||
Runtime of the latest iteration of the analysis in milliseconds.
|
||||
end::dfas-timing-stats-iteration[]
|
||||
======
|
||||
//End class_timing_stats
|
||||
|
||||
//Begin class_validation_loss
|
||||
tag::dfas-validation-loss[]
|
||||
`validation_loss`::::
|
||||
(object)
|
||||
An object containing information about validation loss.
|
||||
end::dfas-validation-loss[]
|
||||
+
|
||||
.Properties of `validation_loss`
|
||||
[%collapsible%open]
|
||||
======
|
||||
tag::dfas-validation-loss-type[]
|
||||
`loss_type`::::
|
||||
(string)
|
||||
The type of the loss metric. For example, `binomial_logistic`.
|
||||
end::dfas-validation-loss-type[]
|
||||
|
||||
tag::dfas-validation-loss-fold[]
|
||||
`fold_values`::::
|
||||
(array of strings)
|
||||
Validation loss values for every added decision tree during the forest growing
|
||||
procedure.
|
||||
end::dfas-validation-loss-fold[]
|
||||
======
|
||||
//End class_validation_loss
|
||||
=====
|
||||
//End classification_stats
|
||||
|
||||
//Begin outlier_detection_stats
|
||||
`outlier_detection_stats`:::
|
||||
(object)
|
||||
An object containing statistical data about the {oldetection} job.
|
||||
+
|
||||
.Properties of `outlier_detection_stats`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
//Begin parameters
|
||||
`parameters`::::
|
||||
(object)
|
||||
The list of job parameters specified by the user or determined by algorithmic
|
||||
heuristics.
|
||||
+
|
||||
.Properties of `parameters`
|
||||
[%collapsible%open]
|
||||
======
|
||||
`compute_feature_influence`::::
|
||||
(boolean)
|
||||
If true, feature influence calculation is enabled.
|
||||
|
||||
`feature_influence_threshold`::::
|
||||
(double)
|
||||
The minimum {olscore} that a document needs to have to calculate its feature
|
||||
influence score.
|
||||
|
||||
`method`::::
|
||||
(string)
|
||||
The method that {oldetection} uses. Possible values are `lof`, `ldof`,
|
||||
`distance_kth_nn`, `distance_knn`, and `ensemble`.
|
||||
|
||||
`n_neighbors`::::
|
||||
(integer)
|
||||
The value for how many nearest neighbors each method of {oldetection} uses to
|
||||
calculate its outlier score.
|
||||
|
||||
`outlier_fraction`::::
|
||||
(double)
|
||||
The proportion of the data set that is assumed to be outlying prior to
|
||||
{oldetection}.
|
||||
|
||||
`standardization_enabled`::::
|
||||
(boolean)
|
||||
If true, then the following operation is performed on the columns before
|
||||
computing {olscores}: (x_i - mean(x_i)) / sd(x_i).
|
||||
======
|
||||
//End parameters
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timestamp]
|
||||
|
||||
//Begin od_timing_stats
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats]
|
||||
+
|
||||
.Property of `timing_stats`
|
||||
[%collapsible%open]
|
||||
======
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-elapsed]
|
||||
======
|
||||
//End od_timing_stats
|
||||
=====
|
||||
//End outlier_detection_stats
|
||||
|
||||
//Begin regression_stats
|
||||
`regression_stats`:::
|
||||
(object)
|
||||
An object containing statistical data about the {reganalysis}.
|
||||
+
|
||||
.Properties of `regression_stats`
|
||||
[%collapsible%open]
|
||||
=====
|
||||
//Begin reg_hyperparameters
|
||||
`hyperparameters`::::
|
||||
(object)
|
||||
An object containing the parameters of the {reganalysis}.
|
||||
+
|
||||
.Properties of `hyperparameters`
|
||||
[%collapsible%open]
|
||||
======
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-alpha]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-downsample-factor]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-eta]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-eta-growth]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-feature-bag-fraction]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-gamma]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-lambda]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-attempts]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-optimization-rounds]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-max-trees]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-num-folds]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-num-splits]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-soft-limit]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-soft-tolerance]
|
||||
======
|
||||
//End reg_hyperparameters
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-iteration]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timestamp]
|
||||
|
||||
//Begin reg_timing_stats
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats]
|
||||
+
|
||||
.Propertis of `timing_stats`
|
||||
[%collapsible%open]
|
||||
======
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-elapsed]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-timing-stats-iteration]
|
||||
======
|
||||
//End reg_timing_stats
|
||||
|
||||
//Begin reg_validation_loss
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss]
|
||||
+
|
||||
.Properties of `validation_loss`
|
||||
[%collapsible%open]
|
||||
======
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss-type]
|
||||
|
||||
include::{docdir}/ml/ml-shared.asciidoc[tag=dfas-validation-loss-fold]
|
||||
======
|
||||
//End reg_validation_loss
|
||||
=====
|
||||
//End regression_stats
|
||||
====
|
||||
//End analysis_stats
|
||||
|
||||
`assignment_explanation`:::
|
||||
(string)
|
||||
For running jobs only, contains messages relating to the selection of a node to
|
||||
run the job.
|
||||
|
||||
//Begin data_counts
|
||||
`data_counts`:::
|
||||
(object)
|
||||
An object containing statistical data about the documents in the analysis.
|
||||
+
|
||||
.Properties of `data_counts`
|
||||
[%collapsible%open]
|
||||
====
|
||||
`skipped_docs_count`:::
|
||||
(integer)
|
||||
The number of documents that are skipped during the analysis because they
|
||||
contained values that are not supported by the analysis. For example,
|
||||
{oldetection} does not support missing fields so it skips documents with missing
|
||||
fields. Likewise, all types of analysis skip documents that contain arrays with
|
||||
more than one element.
|
||||
|
||||
`test_docs_count`:::
|
||||
(integer)
|
||||
The number of documents that are not used for training the model and can be used
|
||||
for testing.
|
||||
|
||||
`training_docs_count`:::
|
||||
(integer)
|
||||
The number of documents that are used for training the model.
|
||||
====
|
||||
//End data_counts
|
||||
|
||||
`id`:::
|
||||
(string)
|
||||
The unique identifier of the {dfanalytics-job}.
|
||||
|
||||
`memory_usage`:::
|
||||
(Optional, object)
|
||||
An object describing memory usage of the analytics. It is present only after the
|
||||
job is started and memory usage is reported.
|
||||
|
||||
`memory_usage`.`peak_usage_bytes`:::
|
||||
(long)
|
||||
The number of bytes used at the highest peak of memory usage.
|
||||
|
||||
`memory_usage`.`timestamp`:::
|
||||
(date)
|
||||
The timestamp when memory usage was calculated.
|
||||
|
||||
`node`:::
|
||||
(object)
|
||||
Contains properties for the node that runs the job. This information is
|
||||
available only for running jobs.
|
||||
|
||||
`node`.`attributes`:::
|
||||
(object)
|
||||
Lists node attributes such as `ml.machine_memory`, `ml.max_open_jobs`, and
|
||||
`xpack.installed`.
|
||||
|
||||
`node`.`ephemeral_id`:::
|
||||
(string)
|
||||
The ephemeral id of the node.
|
||||
|
||||
`node`.`id`:::
|
||||
(string)
|
||||
The unique identifier of the node.
|
||||
|
||||
`node`.`name`:::
|
||||
(string)
|
||||
The node name.
|
||||
|
||||
`node`.`transport_address`:::
|
||||
(string)
|
||||
The host and port where transport HTTP connections are accepted.
|
||||
|
||||
`progress`:::
|
||||
(array) The progress report of the {dfanalytics-job} by phase.
|
||||
|
||||
`progress`.`phase`:::
|
||||
(string) Defines the phase of the {dfanalytics-job}. Possible phases:
|
||||
`reindexing`, `loading_data`, `analyzing`, and `writing_results`.
|
||||
|
||||
`progress`.`progress_percent`:::
|
||||
(integer) The progress that the {dfanalytics-job} has made expressed in
|
||||
percentage.
|
||||
|
||||
`state`:::
|
||||
(string) Current state of the {dfanalytics-job}.
|
||||
end::data-frame-analytics-stats[]
|
||||
|
||||
tag::datafeed-id[]
|
||||
A numerical character string that uniquely identifies the
|
||||
{dfeed}. This identifier can contain lowercase alphanumeric characters (a-z
|
||||
|
|
@ -894,6 +471,106 @@ A unique identifier for the detector. This identifier is based on the order of
|
|||
the detectors in the `analysis_config`, starting at zero.
|
||||
end::detector-index[]
|
||||
|
||||
tag::dfas-alpha[]
|
||||
Regularization factor to penalize deeper trees when training decision trees.
|
||||
end::dfas-alpha[]
|
||||
|
||||
tag::dfas-downsample-factor[]
|
||||
The value of the downsample factor.
|
||||
end::dfas-downsample-factor[]
|
||||
|
||||
tag::dfas-eta[]
|
||||
The value of the eta hyperparameter.
|
||||
end::dfas-eta[]
|
||||
|
||||
tag::dfas-eta-growth[]
|
||||
Specifies the rate at which the `eta` increases for each new tree that is added to the
|
||||
forest. For example, a rate of `1.05` increases `eta` by 5%.
|
||||
end::dfas-eta-growth[]
|
||||
|
||||
tag::dfas-feature-bag-fraction[]
|
||||
The fraction of features that is used when selecting a random bag for each
|
||||
candidate split.
|
||||
end::dfas-feature-bag-fraction[]
|
||||
|
||||
tag::dfas-gamma[]
|
||||
Regularization factor to penalize trees with large numbers of nodes.
|
||||
end::dfas-gamma[]
|
||||
|
||||
tag::dfas-iteration[]
|
||||
The number of iterations on the analysis.
|
||||
end::dfas-iteration[]
|
||||
|
||||
tag::dfas-lambda[]
|
||||
Regularization factor to penalize large leaf weights.
|
||||
end::dfas-lambda[]
|
||||
|
||||
tag::dfas-max-attempts[]
|
||||
If the algorithm fails to determine a non-trivial tree (more than a single
|
||||
leaf), this parameter determines how many of such consecutive failures are
|
||||
tolerated. Once the number of attempts exceeds the threshold, the forest
|
||||
training stops.
|
||||
end::dfas-max-attempts[]
|
||||
|
||||
tag::dfas-max-optimization-rounds[]
|
||||
A multiplier responsible for determining the maximum number of
|
||||
hyperparameter optimization steps in the Bayesian optimization procedure.
|
||||
The maximum number of steps is determined based on the number of undefined hyperparameters
|
||||
times the maximum optimization rounds per hyperparameter.
|
||||
end::dfas-max-optimization-rounds[]
|
||||
|
||||
tag::dfas-max-trees[]
|
||||
The maximum number of trees in the forest.
|
||||
end::dfas-max-trees[]
|
||||
|
||||
tag::dfas-num-folds[]
|
||||
The maximum number of folds for the cross-validation procedure.
|
||||
end::dfas-num-folds[]
|
||||
|
||||
tag::dfas-num-splits[]
|
||||
Determines the maximum number of splits for every feature that can occur in a
|
||||
decision tree when the tree is trained.
|
||||
end::dfas-num-splits[]
|
||||
|
||||
tag::dfas-soft-limit[]
|
||||
Tree depth limit is used for calculating the tree depth penalty. This is a soft
|
||||
limit, it can be exceeded.
|
||||
end::dfas-soft-limit[]
|
||||
|
||||
tag::dfas-soft-tolerance[]
|
||||
Tree depth tolerance is used for calculating the tree depth penalty. This is a
|
||||
soft limit, it can be exceeded.
|
||||
end::dfas-soft-tolerance[]
|
||||
|
||||
tag::dfas-timestamp[]
|
||||
The timestamp when the statistics were reported in milliseconds since the epoch.
|
||||
end::dfas-timestamp[]
|
||||
|
||||
tag::dfas-timing-stats[]
|
||||
An object containing time statistics about the {dfanalytics-job}.
|
||||
end::dfas-timing-stats[]
|
||||
|
||||
tag::dfas-timing-stats-elapsed[]
|
||||
Runtime of the analysis in milliseconds.
|
||||
end::dfas-timing-stats-elapsed[]
|
||||
|
||||
tag::dfas-timing-stats-iteration[]
|
||||
Runtime of the latest iteration of the analysis in milliseconds.
|
||||
end::dfas-timing-stats-iteration[]
|
||||
|
||||
tag::dfas-validation-loss[]
|
||||
An object containing information about validation loss.
|
||||
end::dfas-validation-loss[]
|
||||
|
||||
tag::dfas-validation-loss-fold[]
|
||||
Validation loss values for every added decision tree during the forest growing
|
||||
procedure.
|
||||
end::dfas-validation-loss-fold[]
|
||||
|
||||
tag::dfas-validation-loss-type[]
|
||||
The type of the loss metric. For example, `binomial_logistic`.
|
||||
end::dfas-validation-loss-type[]
|
||||
|
||||
tag::earliest-record-timestamp[]
|
||||
The timestamp of the earliest chronologically input document.
|
||||
end::earliest-record-timestamp[]
|
||||
|
|
@ -1334,6 +1011,10 @@ tag::node-address[]
|
|||
The network address of the node.
|
||||
end::node-address[]
|
||||
|
||||
tag::node-attributes[]
|
||||
Lists node attributes such as `ml.machine_memory` or `ml.max_open_jobs` settings.
|
||||
end::node-attributes[]
|
||||
|
||||
tag::node-datafeeds[]
|
||||
For started {dfeeds} only, this information pertains to the node upon which the
|
||||
{dfeed} is started.
|
||||
|
|
@ -1352,6 +1033,10 @@ Contains properties for the node that runs the job. This information is
|
|||
available only for open jobs.
|
||||
end::node-jobs[]
|
||||
|
||||
tag::node-transport-address[]
|
||||
The host and port where transport HTTP connections are accepted.
|
||||
end::node-transport-address[]
|
||||
|
||||
tag::open-time[]
|
||||
For open jobs only, the elapsed time for which the job has been open.
|
||||
end::open-time[]
|
||||
|
|
|
|||
Loading…
Reference in New Issue