diff --git a/output/schema/schema.json b/output/schema/schema.json index 0756efdbcb..2cd472add7 100644 --- a/output/schema/schema.json +++ b/output/schema/schema.json @@ -132458,7 +132458,7 @@ }, "properties": [ { - "description": "The size of the interval that the analysis is aggregated into, typically between `5m` and `1h`. This value should be either a whole number of days or equate to a\nwhole number of buckets in one day. If the anomaly detection job uses a datafeed with aggregations, this value must also be divisible by the interval of the date histogram aggregation.", + "description": "The size of the interval that the analysis is aggregated into, typically between `5m` and `1h`.", "name": "bucket_span", "required": true, "serverDefault": "5m", @@ -132471,7 +132471,7 @@ } }, { - "description": "If `categorization_field_name` is specified, you can also define the analyzer that is used to interpret the categorization field. This property cannot be used at the same time as `categorization_filters`. The categorization analyzer specifies how the `categorization_field` is interpreted by the categorization process. The `categorization_analyzer` field can be specified either as a string or as an object. If it is a string, it must refer to a built-in analyzer or one added by another plugin.", + "description": "If `categorization_field_name` is specified, you can also define the analyzer that is used to interpret the categorization field.\nThis property cannot be used at the same time as `categorization_filters`.\nThe categorization analyzer specifies how the `categorization_field` is interpreted by the categorization process.", "name": "categorization_analyzer", "required": false, "type": { @@ -132483,7 +132483,7 @@ } }, { - "description": "If this property is specified, the values of the specified field will be categorized. The resulting categories must be used in a detector by setting `by_field_name`, `over_field_name`, or `partition_field_name` to the keyword `mlcategory`.", + "description": "If this property is specified, the values of the specified field will be categorized.\nThe resulting categories must be used in a detector by setting `by_field_name`, `over_field_name`, or `partition_field_name` to the keyword `mlcategory`.", "name": "categorization_field_name", "required": false, "type": { @@ -132495,7 +132495,7 @@ } }, { - "description": "If `categorization_field_name` is specified, you can also define optional filters. This property expects an array of regular expressions. The expressions are used to filter out matching sequences from the categorization field values. You can use this functionality to fine tune the categorization by excluding sequences from consideration when categories are defined. For example, you can exclude SQL statements that appear in your log files. This property cannot be used at the same time as `categorization_analyzer`. If you only want to define simple regular expression filters that are applied prior to tokenization, setting this property is the easiest method. If you also want to customize the tokenizer or post-tokenization filtering, use the `categorization_analyzer` property instead and include the filters as pattern_replace character filters. The effect is exactly the same.", + "description": "If `categorization_field_name` is specified, you can also define optional filters.\nThis property expects an array of regular expressions.\nThe expressions are used to filter out matching sequences from the categorization field values.", "name": "categorization_filters", "required": false, "type": { @@ -132510,7 +132510,7 @@ } }, { - "description": "Detector configuration objects specify which data fields a job analyzes. They also specify which analytical functions are used. You can specify multiple detectors for a job. If the detectors array does not contain at least one detector, no analysis can occur and an error is returned.", + "description": "An array of detector configuration objects.\nDetector configuration objects specify which data fields a job analyzes.\nThey also specify which analytical functions are used.\nYou can specify multiple detectors for a job.", "name": "detectors", "required": true, "type": { @@ -132525,7 +132525,7 @@ } }, { - "description": "A comma separated list of influencer field names. Typically these can be the by, over, or partition fields that are used in the detector configuration. You might also want to use a field name that is not specifically named in a detector, but is available as part of the input data. When you use multiple detectors, the use of influencers is recommended as it aggregates results for each influencer entity.", + "description": "A comma separated list of influencer field names.\nTypically these can be the by, over, or partition fields that are used in the detector configuration.\nYou might also want to use a field name that is not specifically named in a detector, but is available as part of the input data.\nWhen you use multiple detectors, the use of influencers is recommended as it aggregates results for each influencer entity.", "name": "influencers", "required": true, "type": { @@ -132540,7 +132540,7 @@ } }, { - "description": "Advanced configuration option. Affects the pruning of models that have not been updated for the given time duration. The value must be set to a multiple of the `bucket_span`. If set too low, important information may be removed from the model. For jobs created in 8.1 and later, the default value is the greater of `30d` or 20 times `bucket_span`.", + "description": "Advanced configuration option.\nAffects the pruning of models that have not been updated for the given time duration.\nThe value must be set to a multiple of the `bucket_span`.\nIf set too low, important information may be removed from the model.\nTypically, set to `30d` or longer.\nIf not set, model pruning only occurs if the model memory status reaches the soft limit or the hard limit.\nFor jobs created in 8.1 and later, the default value is the greater of `30d` or 20 times `bucket_span`.", "name": "model_prune_window", "required": false, "type": { @@ -132552,7 +132552,7 @@ } }, { - "description": "The size of the window in which to expect data that is out of time order. If you specify a non-zero value, it must be greater than or equal to one second. NOTE: Latency is applicable only when you send data by using the post data API.", + "description": "The size of the window in which to expect data that is out of time order.\nDefaults to no latency.\nIf you specify a non-zero value, it must be greater than or equal to one second.", "name": "latency", "required": false, "serverDefault": "0", @@ -132565,7 +132565,7 @@ } }, { - "description": "This functionality is reserved for internal use. It is not supported for use in customer environments and is not subject to the support SLA of official GA features. If set to `true`, the analysis will automatically find correlations between metrics for a given by field value and report anomalies when those correlations cease to hold. For example, suppose CPU and memory usage on host A is usually highly correlated with the same metrics on host B. Perhaps this correlation occurs because they are running a load-balanced application. If you enable this property, anomalies will be reported when, for example, CPU usage on host A is high and the value of CPU usage on host B is low. That is to say, you’ll see an anomaly when the CPU of host A is unusual given the CPU of host B. To use the `multivariate_by_fields` property, you must also specify `by_field_name` in your detector.", + "description": "This functionality is reserved for internal use.\nIt is not supported for use in customer environments and is not subject to the support SLA of official GA features.\nIf set to `true`, the analysis will automatically find correlations between metrics for a given by field value and report anomalies when those correlations cease to hold.", "name": "multivariate_by_fields", "required": false, "type": { @@ -132589,7 +132589,7 @@ } }, { - "description": "If this property is specified, the data that is fed to the job is expected to be pre-summarized. This property value is the name of the field that contains the count of raw data points that have been summarized. The same `summary_count_field_name` applies to all detectors in the job. NOTE: The `summary_count_field_name` property cannot be used with the `metric` function.", + "description": "If this property is specified, the data that is fed to the job is expected to be pre-summarized.\nThis property value is the name of the field that contains the count of raw data points that have been summarized.\nThe same `summary_count_field_name` applies to all detectors in the job.", "name": "summary_count_field_name", "required": false, "type": { @@ -132601,7 +132601,7 @@ } } ], - "specLocation": "ml/_types/Analysis.ts#L79-L91" + "specLocation": "ml/_types/Analysis.ts#L79-L148" }, { "kind": "interface", @@ -132637,7 +132637,7 @@ } } ], - "specLocation": "ml/_types/Analysis.ts#L104-L115" + "specLocation": "ml/_types/Analysis.ts#L161-L172" }, { "kind": "interface", @@ -132659,7 +132659,7 @@ } } ], - "specLocation": "ml/_types/Analysis.ts#L117-L122" + "specLocation": "ml/_types/Analysis.ts#L174-L179" }, { "kind": "interface", @@ -133758,7 +133758,7 @@ "name": "CategorizationAnalyzer", "namespace": "ml._types" }, - "specLocation": "ml/_types/Analysis.ts#L124-L125", + "specLocation": "ml/_types/Analysis.ts#L181-L182", "type": { "items": [ { @@ -133829,7 +133829,7 @@ } } ], - "specLocation": "ml/_types/Analysis.ts#L127-L140" + "specLocation": "ml/_types/Analysis.ts#L184-L197" }, { "kind": "enum", @@ -134061,7 +134061,7 @@ } } ], - "specLocation": "ml/_types/Datafeed.ts#L180-L193" + "specLocation": "ml/_types/Datafeed.ts#L239-L252" }, { "kind": "enum", @@ -134080,7 +134080,7 @@ "name": "ChunkingMode", "namespace": "ml._types" }, - "specLocation": "ml/_types/Datafeed.ts#L174-L178" + "specLocation": "ml/_types/Datafeed.ts#L233-L237" }, { "kind": "interface", @@ -134406,7 +134406,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L142-L162" + "specLocation": "ml/_types/Job.ts#L352-L372" }, { "kind": "interface", @@ -134465,7 +134465,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L164-L180" + "specLocation": "ml/_types/Job.ts#L374-L390" }, { "kind": "interface", @@ -134951,6 +134951,7 @@ }, "properties": [ { + "description": "Indicates if the datafeed is \"real-time\"; meaning that the datafeed has no configured `end` time.", "name": "real_time_configured", "required": true, "type": { @@ -134962,6 +134963,7 @@ } }, { + "description": "Indicates whether the datafeed has finished running on the available past data.\nFor datafeeds without a configured `end` time, this means that the datafeed is now running on \"real-time\" data.", "name": "real_time_running", "required": true, "type": { @@ -134973,6 +134975,7 @@ } }, { + "description": "Provides the latest time interval the datafeed has searched.", "name": "search_interval", "required": false, "type": { @@ -134984,7 +134987,7 @@ } } ], - "specLocation": "ml/_types/Datafeed.ts#L161-L165" + "specLocation": "ml/_types/Datafeed.ts#L198-L212" }, { "kind": "enum", @@ -135016,6 +135019,7 @@ }, "properties": [ { + "description": "For started datafeeds only, contains messages relating to the selection of a node.", "name": "assignment_explanation", "required": false, "type": { @@ -135027,6 +135031,7 @@ } }, { + "description": "A numerical character string that uniquely identifies the datafeed.\nThis identifier can contain lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores.\nIt must start and end with alphanumeric characters.", "name": "datafeed_id", "required": true, "type": { @@ -135041,6 +135046,7 @@ "availability": { "stack": {} }, + "description": "For started datafeeds only, this information pertains to the node upon which the datafeed is started.", "name": "node", "required": false, "type": { @@ -135052,6 +135058,7 @@ } }, { + "description": "The status of the datafeed, which can be one of the following values: `starting`, `started`, `stopping`, `stopped`.", "name": "state", "required": true, "type": { @@ -135063,6 +135070,7 @@ } }, { + "description": "An object that provides statistical information about timing aspect of this datafeed.", "name": "timing_stats", "required": true, "type": { @@ -135074,6 +135082,7 @@ } }, { + "description": "An object containing the running state for this datafeed.\nIt is only provided if the datafeed is started.", "name": "running_state", "required": false, "type": { @@ -135085,7 +135094,7 @@ } } ], - "specLocation": "ml/_types/Datafeed.ts#L140-L150" + "specLocation": "ml/_types/Datafeed.ts#L140-L169" }, { "kind": "interface", @@ -135095,6 +135104,7 @@ }, "properties": [ { + "description": "The number of buckets processed.", "name": "bucket_count", "required": true, "type": { @@ -135106,6 +135116,7 @@ } }, { + "description": "The exponential average search time per hour, in milliseconds.", "name": "exponential_average_search_time_per_hour_ms", "required": true, "type": { @@ -135126,6 +135137,7 @@ } }, { + "description": "Identifier for the anomaly detection job.", "name": "job_id", "required": true, "type": { @@ -135137,6 +135149,7 @@ } }, { + "description": "The number of searches run by the datafeed.", "name": "search_count", "required": true, "type": { @@ -135148,6 +135161,7 @@ } }, { + "description": "The total time the datafeed spent searching, in milliseconds.", "name": "total_search_time_ms", "required": true, "type": { @@ -135168,6 +135182,7 @@ } }, { + "description": "The average search time per bucket, in milliseconds.", "name": "average_search_time_per_bucket_ms", "required": false, "type": { @@ -135188,7 +135203,7 @@ } } ], - "specLocation": "ml/_types/Datafeed.ts#L152-L159" + "specLocation": "ml/_types/Datafeed.ts#L171-L196" }, { "kind": "interface", @@ -136502,6 +136517,7 @@ }, "properties": [ { + "description": "An object containing the parameters of the classification analysis job.", "name": "hyperparameters", "required": true, "type": { @@ -136525,6 +136541,7 @@ } }, { + "description": "The timestamp when the statistics were reported in milliseconds since the epoch.", "name": "timestamp", "required": true, "type": { @@ -136545,6 +136562,7 @@ } }, { + "description": "An object containing time statistics about the data frame analytics job.", "name": "timing_stats", "required": true, "type": { @@ -136556,6 +136574,7 @@ } }, { + "description": "An object containing information about validation loss.", "name": "validation_loss", "required": true, "type": { @@ -136567,7 +136586,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L383-L390" + "specLocation": "ml/_types/DataframeAnalytics.ts#L383-L402" }, { "kind": "interface", @@ -136644,6 +136663,7 @@ }, "properties": [ { + "description": "The list of job parameters specified by the user or determined by algorithmic heuristics.", "name": "parameters", "required": true, "type": { @@ -136655,6 +136675,7 @@ } }, { + "description": "The timestamp when the statistics were reported in milliseconds since the epoch.", "name": "timestamp", "required": true, "type": { @@ -136675,6 +136696,7 @@ } }, { + "description": "An object containing time statistics about the data frame analytics job.", "name": "timing_stats", "required": true, "type": { @@ -136686,7 +136708,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L392-L396" + "specLocation": "ml/_types/DataframeAnalytics.ts#L404-L417" }, { "kind": "interface", @@ -137728,7 +137750,7 @@ }, "properties": [ { - "description": "The field used to split the data. In particular, this property is used for analyzing the splits with respect to their own history. It is used for finding unusual values in the context of the split.", + "description": "The field used to split the data.\nIn particular, this property is used for analyzing the splits with respect to their own history.\nIt is used for finding unusual values in the context of the split.", "name": "by_field_name", "required": false, "type": { @@ -137740,7 +137762,7 @@ } }, { - "description": "Custom rules enable you to customize the way detectors operate. For example, a rule may dictate conditions under which results should be skipped. Kibana refers to custom rules as job rules.", + "description": "An array of custom rule objects, which enable you to customize the way detectors operate.\nFor example, a rule may dictate to the detector conditions under which results should be skipped.\nKibana refers to custom rules as job rules.", "name": "custom_rules", "required": false, "type": { @@ -137767,7 +137789,7 @@ } }, { - "description": "A unique identifier for the detector. This identifier is based on the order of the detectors in the `analysis_config`, starting at zero. If you specify a value for this property, it is ignored.", + "description": "A unique identifier for the detector.\nThis identifier is based on the order of the detectors in the `analysis_config`, starting at zero.", "name": "detector_index", "required": false, "type": { @@ -137779,7 +137801,7 @@ } }, { - "description": "If set, frequent entities are excluded from influencing the anomaly results. Entities can be considered frequent over time or frequent in a population. If you are working with both over and by fields, you can set `exclude_frequent` to `all` for both fields, or to `by` or `over` for those specific fields.", + "description": "Contains one of the following values: `all`, `none`, `by`, or `over`.\nIf set, frequent entities are excluded from influencing the anomaly results.\nEntities can be considered frequent over time or frequent in a population.\nIf you are working with both over and by fields, then you can set `exclude_frequent` to all for both fields, or to `by` or `over` for those specific fields.", "name": "exclude_frequent", "required": false, "type": { @@ -137791,7 +137813,7 @@ } }, { - "description": "The field that the detector uses in the function. If you use an event rate function such as count or rare, do not specify this field. The `field_name` cannot contain double quotes or backslashes.", + "description": "The field that the detector uses in the function.\nIf you use an event rate function such as `count` or `rare`, do not specify this field.", "name": "field_name", "required": false, "type": { @@ -137803,7 +137825,9 @@ } }, { - "description": "The analysis function that is used. For example, `count`, `rare`, `mean`, `min`, `max`, or `sum`.", + "description": "The analysis function that is used.\nFor example, `count`, `rare`, `mean`, `min`, `max`, and `sum`.", + "docId": "ml-functions", + "docUrl": "https://www.elastic.co/guide/en/machine-learning/{branch}/ml-functions.html", "name": "function", "required": true, "type": { @@ -137815,7 +137839,7 @@ } }, { - "description": "The field used to split the data. In particular, this property is used for analyzing the splits with respect to the history of all splits. It is used for finding unusual values in the population of all splits.", + "description": "The field used to split the data.\nIn particular, this property is used for analyzing the splits with respect to the history of all splits.\nIt is used for finding unusual values in the population of all splits.", "name": "over_field_name", "required": false, "type": { @@ -137827,7 +137851,7 @@ } }, { - "description": "The field used to segment the analysis. When you use this property, you have completely independent baselines for each value of this field.", + "description": "The field used to segment the analysis.\nWhen you use this property, you have completely independent baselines for each value of this field.", "name": "partition_field_name", "required": false, "type": { @@ -137852,7 +137876,7 @@ } } ], - "specLocation": "ml/_types/Detector.ts#L69-L80" + "specLocation": "ml/_types/Detector.ts#L69-L125" }, { "kind": "interface", @@ -137950,7 +137974,7 @@ "name": "ExcludeFrequent", "namespace": "ml._types" }, - "specLocation": "ml/_types/Detector.ts#L82-L87" + "specLocation": "ml/_types/Detector.ts#L127-L132" }, { "description": "Fill mask inference options", @@ -138271,6 +138295,7 @@ }, "properties": [ { + "description": "Advanced configuration option.\nMachine learning uses loss guided tree growing, which means that the decision trees grow where the regularized loss decreases most quickly.\nThis parameter affects loss calculations by acting as a multiplier of the tree depth.\nHigher alpha values result in shallower trees and faster training times.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be greater than or equal to zero.", "name": "alpha", "required": false, "type": { @@ -138282,6 +138307,7 @@ } }, { + "description": "Advanced configuration option.\nRegularization parameter to prevent overfitting on the training data set.\nMultiplies an L2 regularization term which applies to leaf weights of the individual trees in the forest.\nA high lambda value causes training to favor small leaf weights.\nThis behavior makes the prediction function smoother at the expense of potentially not being able to capture relevant relationships between the features and the dependent variable.\nA small lambda value results in large individual trees and slower training.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be a nonnegative value.", "name": "lambda", "required": false, "type": { @@ -138293,6 +138319,7 @@ } }, { + "description": "Advanced configuration option.\nRegularization parameter to prevent overfitting on the training data set.\nMultiplies a linear penalty associated with the size of individual trees in the forest.\nA high gamma value causes training to prefer small trees.\nA small gamma value results in larger individual trees and slower training.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be a nonnegative value.", "name": "gamma", "required": false, "type": { @@ -138304,6 +138331,7 @@ } }, { + "description": "Advanced configuration option.\nThe shrinkage applied to the weights.\nSmaller values result in larger forests which have a better generalization error.\nHowever, larger forests cause slower training.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be a value between `0.001` and `1`.", "name": "eta", "required": false, "type": { @@ -138315,6 +138343,7 @@ } }, { + "description": "Advanced configuration option.\nSpecifies the rate at which `eta` increases for each new tree that is added to the forest.\nFor example, a rate of 1.05 increases `eta` by 5% for each extra tree.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be between `0.5` and `2`.", "name": "eta_growth_rate_per_tree", "required": false, "type": { @@ -138326,6 +138355,7 @@ } }, { + "description": "Advanced configuration option.\nDefines the fraction of features that will be used when selecting a random bag for each candidate split.\nBy default, this value is calculated during hyperparameter optimization.", "name": "feature_bag_fraction", "required": false, "type": { @@ -138337,6 +138367,7 @@ } }, { + "description": "Advanced configuration option.\nControls the fraction of data that is used to compute the derivatives of the loss function for tree training.\nA small value results in the use of a small fraction of the data.\nIf this value is set to be less than 1, accuracy typically improves.\nHowever, too small a value may result in poor convergence for the ensemble and so require more trees.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be greater than zero and less than or equal to 1.", "name": "downsample_factor", "required": false, "type": { @@ -138348,6 +138379,7 @@ } }, { + "description": "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.\nOnce the number of attempts exceeds the threshold, the forest training stops.", "name": "max_attempts_to_add_tree", "required": false, "type": { @@ -138359,6 +138391,7 @@ } }, { + "description": "Advanced configuration option.\nA multiplier responsible for determining the maximum number of hyperparameter optimization steps in the Bayesian optimization procedure.\nThe maximum number of steps is determined based on the number of undefined hyperparameters times the maximum optimization rounds per hyperparameter.\nBy default, this value is calculated during hyperparameter optimization.", "name": "max_optimization_rounds_per_hyperparameter", "required": false, "type": { @@ -138370,6 +138403,7 @@ } }, { + "description": "Advanced configuration option.\nDefines the maximum number of decision trees in the forest.\nThe maximum value is 2000.\nBy default, this value is calculated during hyperparameter optimization.", "name": "max_trees", "required": false, "type": { @@ -138381,6 +138415,7 @@ } }, { + "description": "The maximum number of folds for the cross-validation procedure.", "name": "num_folds", "required": false, "type": { @@ -138392,6 +138427,7 @@ } }, { + "description": "Determines the maximum number of splits for every feature that can occur in a decision tree when the tree is trained.", "name": "num_splits_per_feature", "required": false, "type": { @@ -138403,6 +138439,7 @@ } }, { + "description": "Advanced configuration option.\nMachine learning uses loss guided tree growing, which means that the decision trees grow where the regularized loss decreases most quickly.\nThis soft limit combines with the `soft_tree_depth_tolerance` to penalize trees that exceed the specified depth; the regularized loss increases quickly beyond this depth.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be greater than or equal to 0.", "name": "soft_tree_depth_limit", "required": false, "type": { @@ -138414,6 +138451,7 @@ } }, { + "description": "Advanced configuration option.\nThis option controls how quickly the regularized loss increases when the tree depth exceeds `soft_tree_depth_limit`.\nBy default, this value is calculated during hyperparameter optimization.\nIt must be greater than or equal to 0.01.", "name": "soft_tree_depth_tolerance", "required": false, "type": { @@ -138425,7 +138463,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L398-L413" + "specLocation": "ml/_types/DataframeAnalytics.ts#L419-L525" }, { "kind": "enum", @@ -139113,6 +139151,7 @@ }, "properties": [ { + "description": "Advanced configuration option.\nSpecifies whether this job can open when there is insufficient machine learning node capacity for it to be immediately assigned to a node.", "name": "allow_lazy_open", "required": true, "type": { @@ -139124,6 +139163,7 @@ } }, { + "description": "The analysis configuration, which specifies how to analyze the data.\nAfter you create a job, you cannot change the analysis configuration; all the properties are informational.", "name": "analysis_config", "required": true, "type": { @@ -139135,6 +139175,7 @@ } }, { + "description": "Limits can be applied for the resources required to hold the mathematical models in memory.\nThese limits are approximate and can be set per job.\nThey do not control the memory used by other processes, for example the Elasticsearch Java processes.", "name": "analysis_limits", "required": false, "type": { @@ -139146,6 +139187,7 @@ } }, { + "description": "Advanced configuration option.\nThe time between each periodic persistence of the model.\nThe default value is a randomized value between 3 to 4 hours, which avoids all jobs persisting at exactly the same time.\nThe smallest allowed value is 1 hour.", "name": "background_persist_interval", "required": false, "type": { @@ -139179,6 +139221,7 @@ } }, { + "description": "Advanced configuration option.\nContains custom metadata about the job.", "name": "custom_settings", "required": false, "type": { @@ -139190,8 +139233,10 @@ } }, { + "description": "Advanced configuration option, which affects the automatic removal of old model snapshots for this job.\nIt specifies a period of time (in days) after which only the first snapshot per day is retained.\nThis period is relative to the timestamp of the most recent snapshot for this job.\nValid values range from 0 to `model_snapshot_retention_days`.", "name": "daily_model_snapshot_retention_after_days", "required": false, + "serverDefault": 1, "type": { "kind": "instance_of", "type": { @@ -139201,6 +139246,7 @@ } }, { + "description": "The data description defines the format of the input data when you send data to the job by using the post data API.\nNote that when configuring a datafeed, these properties are automatically set.\nWhen data is received via the post data API, it is not stored in Elasticsearch.\nOnly the results for anomaly detection are retained.", "name": "data_description", "required": true, "type": { @@ -139212,6 +139258,7 @@ } }, { + "description": "The datafeed, which retrieves data from Elasticsearch for analysis by the job.\nYou can associate only one datafeed with each anomaly detection job.", "name": "datafeed_config", "required": false, "type": { @@ -139223,6 +139270,7 @@ } }, { + "description": "Indicates that the process of deleting the job is in progress but not yet completed.\nIt is only reported when `true`.", "name": "deleting", "required": false, "type": { @@ -139234,6 +139282,7 @@ } }, { + "description": "A description of the job.", "name": "description", "required": false, "type": { @@ -139245,6 +139294,7 @@ } }, { + "description": "If the job closed or failed, this is the time the job finished, otherwise it is `null`.\nThis property is informational; you cannot change its value.", "name": "finished_time", "required": false, "type": { @@ -139256,6 +139306,7 @@ } }, { + "description": "A list of job groups.\nA job can belong to no groups or many.", "name": "groups", "required": false, "type": { @@ -139270,6 +139321,7 @@ } }, { + "description": "Identifier for the anomaly detection job.\nThis identifier can contain lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores.\nIt must start and end with alphanumeric characters.", "name": "job_id", "required": true, "type": { @@ -139281,6 +139333,7 @@ } }, { + "description": "Reserved for future use, currently set to `anomaly_detector`.", "name": "job_type", "required": false, "type": { @@ -139292,6 +139345,7 @@ } }, { + "description": "The machine learning configuration version number at which the the job was created.", "name": "job_version", "required": false, "type": { @@ -139303,6 +139357,7 @@ } }, { + "description": "This advanced configuration option stores model information along with the results.\nIt provides a more detailed view into anomaly detection.\nModel plot provides a simplified and indicative view of the model and its bounds.", "name": "model_plot_config", "required": false, "type": { @@ -139325,6 +139380,7 @@ } }, { + "description": "Advanced configuration option, which affects the automatic removal of old model snapshots for this job.\nIt specifies the maximum period of time (in days) that snapshots are retained.\nThis period is relative to the timestamp of the most recent snapshot for this job.\nBy default, snapshots ten days older than the newest snapshot are deleted.", "name": "model_snapshot_retention_days", "required": true, "type": { @@ -139336,6 +139392,7 @@ } }, { + "description": "Advanced configuration option.\nThe period over which adjustments to the score are applied, as new data is seen.\nThe default value is the longer of 30 days or 100 `bucket_spans`.", "name": "renormalization_window_days", "required": false, "type": { @@ -139347,6 +139404,7 @@ } }, { + "description": "A text string that affects the name of the machine learning results index.\nThe default value is `shared`, which generates an index named `.ml-anomalies-shared`.", "name": "results_index_name", "required": true, "type": { @@ -139358,6 +139416,7 @@ } }, { + "description": "Advanced configuration option.\nThe period of time (in days) that results are retained.\nAge is calculated relative to the timestamp of the latest bucket result.\nIf this property has a non-null value, once per day at 00:30 (server time), results that are the specified number of days older than the latest bucket result are deleted from Elasticsearch.\nThe default value is null, which means all results are retained.\nAnnotations generated by the system also count as results for retention purposes; they are deleted after the same number of days as results.\nAnnotations added by users are retained forever.", "name": "results_retention_days", "required": false, "type": { @@ -139369,7 +139428,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L61-L85" + "specLocation": "ml/_types/Job.ts#L61-L180" }, { "kind": "interface", @@ -139401,7 +139460,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L182-L185" + "specLocation": "ml/_types/Job.ts#L392-L395" }, { "kind": "enum", @@ -139420,7 +139479,7 @@ "name": "JobBlockedReason", "namespace": "ml._types" }, - "specLocation": "ml/_types/Job.ts#L187-L191" + "specLocation": "ml/_types/Job.ts#L397-L401" }, { "kind": "interface", @@ -139430,8 +139489,12 @@ }, "properties": [ { + "description": "Advanced configuration option. Specifies whether this job can open when there is insufficient machine learning node capacity for it to be immediately assigned to a node.", + "docId": "ml-put-job", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/ml-put-job.html", "name": "allow_lazy_open", "required": false, + "serverDefault": false, "type": { "kind": "instance_of", "type": { @@ -139441,6 +139504,7 @@ } }, { + "description": "The analysis configuration, which specifies how to analyze the data.\nAfter you create a job, you cannot change the analysis configuration; all the properties are informational.", "name": "analysis_config", "required": true, "type": { @@ -139452,6 +139516,7 @@ } }, { + "description": "Limits can be applied for the resources required to hold the mathematical models in memory.\nThese limits are approximate and can be set per job.\nThey do not control the memory used by other processes, for example the Elasticsearch Java processes.", "name": "analysis_limits", "required": false, "type": { @@ -139463,6 +139528,7 @@ } }, { + "description": "Advanced configuration option.\nThe time between each periodic persistence of the model.\nThe default value is a randomized value between 3 to 4 hours, which avoids all jobs persisting at exactly the same time.\nThe smallest allowed value is 1 hour.", "name": "background_persist_interval", "required": false, "type": { @@ -139474,6 +139540,7 @@ } }, { + "description": "Advanced configuration option.\nContains custom metadata about the job.", "name": "custom_settings", "required": false, "type": { @@ -139485,8 +139552,10 @@ } }, { + "description": "Advanced configuration option, which affects the automatic removal of old model snapshots for this job.\nIt specifies a period of time (in days) after which only the first snapshot per day is retained.\nThis period is relative to the timestamp of the most recent snapshot for this job.", "name": "daily_model_snapshot_retention_after_days", "required": false, + "serverDefault": 1, "type": { "kind": "instance_of", "type": { @@ -139496,6 +139565,7 @@ } }, { + "description": "The data description defines the format of the input data when you send data to the job by using the post data API.\nNote that when configure a datafeed, these properties are automatically set.", "name": "data_description", "required": true, "type": { @@ -139507,6 +139577,7 @@ } }, { + "description": "The datafeed, which retrieves data from Elasticsearch for analysis by the job.\nYou can associate only one datafeed with each anomaly detection job.", "name": "datafeed_config", "required": false, "type": { @@ -139518,6 +139589,7 @@ } }, { + "description": "A description of the job.", "name": "description", "required": false, "type": { @@ -139529,6 +139601,7 @@ } }, { + "description": "A list of job groups. A job can belong to no groups or many.", "name": "groups", "required": false, "type": { @@ -139543,6 +139616,7 @@ } }, { + "description": "Identifier for the anomaly detection job.\nThis identifier can contain lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores.\nIt must start and end with alphanumeric characters.", "name": "job_id", "required": false, "type": { @@ -139554,6 +139628,7 @@ } }, { + "description": "Reserved for future use, currently set to `anomaly_detector`.", "name": "job_type", "required": false, "type": { @@ -139565,6 +139640,7 @@ } }, { + "description": "This advanced configuration option stores model information along with the results.\nIt provides a more detailed view into anomaly detection.\nModel plot provides a simplified and indicative view of the model and its bounds.", "name": "model_plot_config", "required": false, "type": { @@ -139576,8 +139652,10 @@ } }, { + "description": "Advanced configuration option, which affects the automatic removal of old model snapshots for this job.\nIt specifies the maximum period of time (in days) that snapshots are retained.\nThis period is relative to the timestamp of the most recent snapshot for this job.\nThe default value is `10`, which means snapshots ten days older than the newest snapshot are deleted.", "name": "model_snapshot_retention_days", "required": false, + "serverDefault": 10, "type": { "kind": "instance_of", "type": { @@ -139587,6 +139665,7 @@ } }, { + "description": "Advanced configuration option.\nThe period over which adjustments to the score are applied, as new data is seen.\nThe default value is the longer of 30 days or 100 `bucket_spans`.", "name": "renormalization_window_days", "required": false, "type": { @@ -139598,8 +139677,10 @@ } }, { + "description": "A text string that affects the name of the machine learning results index.\nThe default value is `shared`, which generates an index named `.ml-anomalies-shared`.", "name": "results_index_name", "required": false, + "serverDefault": "shared", "type": { "kind": "instance_of", "type": { @@ -139609,6 +139690,7 @@ } }, { + "description": "Advanced configuration option.\nThe period of time (in days) that results are retained.\nAge is calculated relative to the timestamp of the latest bucket result.\nIf this property has a non-null value, once per day at 00:30 (server time), results that are the specified number of days older than the latest bucket result are deleted from Elasticsearch.\nThe default value is null, which means all results are retained.\nAnnotations generated by the system also count as results for retention purposes; they are deleted after the same number of days as results.\nAnnotations added by users are retained forever.", "name": "results_retention_days", "required": false, "type": { @@ -139620,7 +139702,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L87-L105" + "specLocation": "ml/_types/Job.ts#L182-L283" }, { "kind": "interface", @@ -139707,7 +139789,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L133-L140" + "specLocation": "ml/_types/Job.ts#L343-L350" }, { "kind": "enum", @@ -139801,6 +139883,7 @@ }, "properties": [ { + "description": "For open anomaly detection jobs only, contains messages relating to the selection of a node to run the job.", "name": "assignment_explanation", "required": false, "type": { @@ -139812,6 +139895,7 @@ } }, { + "description": "An object that describes the quantity of input to the job and any related error counts.\nThe `data_count` values are cumulative for the lifetime of a job.\nIf a model snapshot is reverted or old results are deleted, the job counts are not reset.", "name": "data_counts", "required": true, "type": { @@ -139823,6 +139907,7 @@ } }, { + "description": "An object that provides statistical information about forecasts belonging to this job.\nSome statistics are omitted if no forecasts have been made.", "name": "forecasts_stats", "required": true, "type": { @@ -139834,6 +139919,7 @@ } }, { + "description": "Identifier for the anomaly detection job.", "name": "job_id", "required": true, "type": { @@ -139845,6 +139931,7 @@ } }, { + "description": "An object that provides information about the size and contents of the model.", "name": "model_size_stats", "required": true, "type": { @@ -139859,6 +139946,7 @@ "availability": { "stack": {} }, + "description": "Contains properties for the node that runs the job.\nThis information is available only for open jobs.", "name": "node", "required": false, "type": { @@ -139870,6 +139958,7 @@ } }, { + "description": "For open jobs only, the elapsed time for which the job has been open.", "name": "open_time", "required": false, "type": { @@ -139881,6 +139970,7 @@ } }, { + "description": "The status of the anomaly detection job, which can be one of the following values: `closed`, `closing`, `failed`, `opened`, `opening`.", "name": "state", "required": true, "type": { @@ -139892,6 +139982,7 @@ } }, { + "description": "An object that provides statistical information about timing aspect of this job.", "name": "timing_stats", "required": true, "type": { @@ -139903,6 +139994,7 @@ } }, { + "description": "Indicates that the process of deleting the job is in progress but not yet completed. It is only reported when `true`.", "name": "deleting", "required": false, "type": { @@ -139914,7 +140006,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L106-L120" + "specLocation": "ml/_types/Job.ts#L284-L330" }, { "kind": "interface", @@ -140066,7 +140158,7 @@ } } ], - "specLocation": "ml/_types/Job.ts#L122-L131" + "specLocation": "ml/_types/Job.ts#L332-L341" }, { "kind": "enum", @@ -140877,8 +140969,10 @@ }, "properties": [ { + "description": "Specifies whether the feature influence calculation is enabled.", "name": "compute_feature_influence", "required": false, + "serverDefault": true, "type": { "kind": "instance_of", "type": { @@ -140888,8 +140982,10 @@ } }, { + "description": "The minimum outlier score that a document needs to have in order to calculate its feature influence score.\nValue range: 0-1", "name": "feature_influence_threshold", "required": false, + "serverDefault": 0.1, "type": { "kind": "instance_of", "type": { @@ -140899,6 +140995,7 @@ } }, { + "description": "The method that outlier detection uses.\nAvailable methods are `lof`, `ldof`, `distance_kth_nn`, `distance_knn`, and `ensemble`.\nThe default value is ensemble, which means that outlier detection uses an ensemble of different methods and normalises and combines their individual outlier scores to obtain the overall outlier score.", "name": "method", "required": false, "type": { @@ -140910,6 +141007,7 @@ } }, { + "description": "Defines the value for how many nearest neighbors each method of outlier detection uses to calculate its outlier score.\nWhen the value is not set, different values are used for different ensemble members.\nThis default behavior helps improve the diversity in the ensemble; only override it if you are confident that the value you choose is appropriate for the data set.", "name": "n_neighbors", "required": false, "type": { @@ -140921,6 +141019,7 @@ } }, { + "description": "The proportion of the data set that is assumed to be outlying prior to outlier detection.\nFor example, 0.05 means it is assumed that 5% of values are real outliers and 95% are inliers.", "name": "outlier_fraction", "required": false, "type": { @@ -140932,8 +141031,10 @@ } }, { + "description": "If `true`, the following operation is performed on the columns before computing outlier scores: (x_i - mean(x_i)) / sd(x_i).", "name": "standardization_enabled", "required": false, + "serverDefault": true, "type": { "kind": "instance_of", "type": { @@ -140943,7 +141044,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L415-L422" + "specLocation": "ml/_types/DataframeAnalytics.ts#L527-L561" }, { "kind": "interface", @@ -141240,7 +141341,7 @@ } } ], - "specLocation": "ml/_types/Analysis.ts#L93-L102" + "specLocation": "ml/_types/Analysis.ts#L150-L159" }, { "kind": "type_alias", @@ -141551,6 +141652,7 @@ }, "properties": [ { + "description": "The end time.", "name": "end", "required": false, "type": { @@ -141562,6 +141664,7 @@ } }, { + "description": "The end time as an epoch in milliseconds.", "name": "end_ms", "required": true, "type": { @@ -141582,6 +141685,7 @@ } }, { + "description": "The start time.", "name": "start", "required": false, "type": { @@ -141593,6 +141697,7 @@ } }, { + "description": "The start time as an epoch in milliseconds.", "name": "start_ms", "required": true, "type": { @@ -141613,7 +141718,7 @@ } } ], - "specLocation": "ml/_types/Datafeed.ts#L167-L172" + "specLocation": "ml/_types/Datafeed.ts#L214-L231" }, { "kind": "enum", @@ -141958,7 +142063,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L424-L429" + "specLocation": "ml/_types/DataframeAnalytics.ts#L563-L568" }, { "description": "Tokenization options stored in inference configuration", @@ -143732,7 +143837,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L431-L436" + "specLocation": "ml/_types/DataframeAnalytics.ts#L570-L575" }, { "kind": "interface", @@ -144183,7 +144288,7 @@ }, "path": [ { - "description": "The ID of the calendar to modify", + "description": "A string that uniquely identifies a calendar.", "name": "calendar_id", "required": true, "type": { @@ -144195,7 +144300,7 @@ } }, { - "description": "The ID of the event to remove from the calendar", + "description": "Identifier for the scheduled event.\nYou can obtain this identifier by using the get calendar events API.", "name": "event_id", "required": true, "type": { @@ -144208,7 +144313,7 @@ } ], "query": [], - "specLocation": "ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts#L23-L35" + "specLocation": "ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts#L23-L42" }, { "body": { @@ -145187,7 +145292,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L84-L89" + "specLocation": "ml/evaluate_data_frame/types.ts#L125-L130" }, { "kind": "interface", @@ -145219,7 +145324,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L91-L94" + "specLocation": "ml/evaluate_data_frame/types.ts#L132-L135" }, { "kind": "interface", @@ -145281,7 +145386,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L96-L117" + "specLocation": "ml/evaluate_data_frame/types.ts#L137-L158" }, { "kind": "interface", @@ -145291,6 +145396,7 @@ }, "properties": [ { + "description": "The AUC ROC (area under the curve of the receiver operating characteristic) score and optionally the curve.\nIt is calculated for a specific class (provided as \"class_name\") treated as positive.", "name": "auc_roc", "required": false, "type": { @@ -145302,6 +145408,7 @@ } }, { + "description": "Accuracy of predictions (per-class and overall).", "name": "accuracy", "required": false, "type": { @@ -145313,6 +145420,7 @@ } }, { + "description": "Multiclass confusion matrix.", "name": "multiclass_confusion_matrix", "required": false, "type": { @@ -145324,6 +145432,7 @@ } }, { + "description": "Precision of predictions (per-class and average).", "name": "precision", "required": false, "type": { @@ -145335,6 +145444,7 @@ } }, { + "description": "Recall of predictions (per-class and average).", "name": "recall", "required": false, "type": { @@ -145346,7 +145456,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L31-L37" + "specLocation": "ml/evaluate_data_frame/types.ts#L44-L66" }, { "kind": "interface", @@ -145381,7 +145491,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L70-L73" + "specLocation": "ml/evaluate_data_frame/types.ts#L111-L114" }, { "kind": "interface", @@ -145416,7 +145526,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L79-L82" + "specLocation": "ml/evaluate_data_frame/types.ts#L120-L123" }, { "kind": "interface", @@ -145451,7 +145561,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L60-L63" + "specLocation": "ml/evaluate_data_frame/types.ts#L101-L104" }, { "kind": "interface", @@ -145486,7 +145596,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L65-L68" + "specLocation": "ml/evaluate_data_frame/types.ts#L106-L109" }, { "inherits": { @@ -145513,7 +145623,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L75-L77" + "specLocation": "ml/evaluate_data_frame/types.ts#L116-L118" }, { "inherits": { @@ -145543,7 +145653,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L50-L52" + "specLocation": "ml/evaluate_data_frame/types.ts#L91-L93" }, { "kind": "interface", @@ -145586,7 +145696,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L54-L58" + "specLocation": "ml/evaluate_data_frame/types.ts#L95-L99" }, { "kind": "interface", @@ -145607,7 +145717,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L46-L48" + "specLocation": "ml/evaluate_data_frame/types.ts#L87-L89" }, { "kind": "interface", @@ -145617,8 +145727,10 @@ }, "properties": [ { + "description": "The AUC ROC (area under the curve of the receiver operating characteristic) score and optionally the curve.", "name": "auc_roc", "required": false, + "serverDefault": "{\"include_curve\": false}", "type": { "kind": "instance_of", "type": { @@ -145628,6 +145740,7 @@ } }, { + "description": "Set the different thresholds of the outlier score at where the metric is calculated.", "name": "precision", "required": false, "type": { @@ -145650,6 +145763,7 @@ } }, { + "description": "Set the different thresholds of the outlier score at where the metric is calculated.", "name": "recall", "required": false, "type": { @@ -145672,6 +145786,7 @@ } }, { + "description": "Set the different thresholds of the outlier score at where the metrics (`tp` - true positive, `fp` - false positive, `tn` - true negative, `fn` - false negative) are calculated.", "name": "confusion_matrix", "required": false, "type": { @@ -145694,7 +145809,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L24-L29" + "specLocation": "ml/evaluate_data_frame/types.ts#L24-L42" }, { "kind": "interface", @@ -145704,6 +145819,7 @@ }, "properties": [ { + "description": "Pseudo Huber loss function.", "name": "huber", "required": false, "type": { @@ -145715,6 +145831,7 @@ } }, { + "description": "Average squared difference between the predicted values and the actual (`ground truth`) value.", "name": "mse", "required": false, "type": { @@ -145726,6 +145843,7 @@ } }, { + "description": "Average squared difference between the logarithm of the predicted values and the logarithm of the actual (`ground truth`) value.", "name": "msle", "required": false, "type": { @@ -145737,6 +145855,7 @@ } }, { + "description": "Proportion of the variance in the dependent variable that is predictable from the independent variables.", "name": "r_squared", "required": false, "type": { @@ -145748,7 +145867,7 @@ } } ], - "specLocation": "ml/evaluate_data_frame/types.ts#L39-L44" + "specLocation": "ml/evaluate_data_frame/types.ts#L68-L85" }, { "attachedBehaviors": [ @@ -147004,6 +147123,7 @@ "kind": "properties", "properties": [ { + "description": "Configures pagination.\nThis parameter has the `from` and `size` properties.", "name": "page", "required": false, "type": { @@ -147094,7 +147214,7 @@ } } ], - "specLocation": "ml/get_categories/MlGetCategoriesRequest.ts#L25-L66" + "specLocation": "ml/get_categories/MlGetCategoriesRequest.ts#L25-L70" }, { "body": { @@ -147686,6 +147806,7 @@ "kind": "properties", "properties": [ { + "description": "Configures pagination.\nThis parameter has the `from` and `size` properties.", "name": "page", "required": false, "type": { @@ -147829,7 +147950,7 @@ } } ], - "specLocation": "ml/get_influencers/MlGetInfluencersRequest.ts#L26-L93" + "specLocation": "ml/get_influencers/MlGetInfluencersRequest.ts#L26-L97" }, { "body": { diff --git a/specification/_doc_ids/table.csv b/specification/_doc_ids/table.csv index 32c326c02d..b7d0dfdac5 100644 --- a/specification/_doc_ids/table.csv +++ b/specification/_doc_ids/table.csv @@ -248,6 +248,7 @@ ml-delete-snapshot,https://www.elastic.co/guide/en/elasticsearch/reference/{bran ml-feature-importance,https://www.elastic.co/guide/en/machine-learning/{branch}/ml-feature-importance.html ml-flush-job,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/ml-flush-job.html ml-forecast,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/ml-forecast.html +ml-functions,https://www.elastic.co/guide/en/machine-learning/{branch}/ml-functions.html ml-get-bucket,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/ml-get-bucket.html ml-get-calendar-event,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/ml-get-calendar-event.html ml-get-calendar,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/ml-get-calendar.html diff --git a/specification/ml/_types/Analysis.ts b/specification/ml/_types/Analysis.ts index f9b47ca867..4022270390 100644 --- a/specification/ml/_types/Analysis.ts +++ b/specification/ml/_types/Analysis.ts @@ -77,16 +77,73 @@ whole number of buckets in one day. If the anomaly detection job uses a datafeed } export class AnalysisConfigRead implements OverloadOf { + /** + * The size of the interval that the analysis is aggregated into, typically between `5m` and `1h`. + */ bucket_span: Duration + /** + * If `categorization_field_name` is specified, you can also define the analyzer that is used to interpret the categorization field. + * This property cannot be used at the same time as `categorization_filters`. + * The categorization analyzer specifies how the `categorization_field` is interpreted by the categorization process. + */ categorization_analyzer?: CategorizationAnalyzer + /** + * If this property is specified, the values of the specified field will be categorized. + * The resulting categories must be used in a detector by setting `by_field_name`, `over_field_name`, or `partition_field_name` to the keyword `mlcategory`. + */ categorization_field_name?: Field + /** + * If `categorization_field_name` is specified, you can also define optional filters. + * This property expects an array of regular expressions. + * The expressions are used to filter out matching sequences from the categorization field values. + */ categorization_filters?: string[] + /** + * An array of detector configuration objects. + * Detector configuration objects specify which data fields a job analyzes. + * They also specify which analytical functions are used. + * You can specify multiple detectors for a job. + */ detectors: DetectorRead[] + /** + * A comma separated list of influencer field names. + * Typically these can be the by, over, or partition fields that are used in the detector configuration. + * You might also want to use a field name that is not specifically named in a detector, but is available as part of the input data. + * When you use multiple detectors, the use of influencers is recommended as it aggregates results for each influencer entity. + */ influencers: Field[] + /** + * Advanced configuration option. + * Affects the pruning of models that have not been updated for the given time duration. + * The value must be set to a multiple of the `bucket_span`. + * If set too low, important information may be removed from the model. + * Typically, set to `30d` or longer. + * If not set, model pruning only occurs if the model memory status reaches the soft limit or the hard limit. + * For jobs created in 8.1 and later, the default value is the greater of `30d` or 20 times `bucket_span`. + */ model_prune_window?: Duration + /** + * The size of the window in which to expect data that is out of time order. + * Defaults to no latency. + * If you specify a non-zero value, it must be greater than or equal to one second. + * @server_default 0 + */ latency?: Duration + /** + * This functionality is reserved for internal use. + * It is not supported for use in customer environments and is not subject to the support SLA of official GA features. + * If set to `true`, the analysis will automatically find correlations between metrics for a given by field value and report anomalies when those correlations cease to hold. + */ multivariate_by_fields?: boolean + /** + * Settings related to how categorization interacts with partition fields. + */ per_partition_categorization?: PerPartitionCategorization + /** + * If this property is specified, the data that is fed to the job is expected to be pre-summarized. + * This property value is the name of the field that contains the count of raw data points that have been summarized. + * The same `summary_count_field_name` applies to all detectors in the job. + */ summary_count_field_name?: Field } diff --git a/specification/ml/_types/Datafeed.ts b/specification/ml/_types/Datafeed.ts index ea32e2014c..4cd58fa3ba 100644 --- a/specification/ml/_types/Datafeed.ts +++ b/specification/ml/_types/Datafeed.ts @@ -138,36 +138,95 @@ export enum DatafeedState { } export class DatafeedStats { + /** + * For started datafeeds only, contains messages relating to the selection of a node. + */ assignment_explanation?: string + /** + * A numerical character string that uniquely identifies the datafeed. + * This identifier can contain lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores. + * It must start and end with alphanumeric characters. + */ datafeed_id: Id /** + * For started datafeeds only, this information pertains to the node upon which the datafeed is started. * @availability stack */ node?: DiscoveryNode + /** + * The status of the datafeed, which can be one of the following values: `starting`, `started`, `stopping`, `stopped`. + */ state: DatafeedState + /** + * An object that provides statistical information about timing aspect of this datafeed. + */ timing_stats: DatafeedTimingStats + /** + * An object containing the running state for this datafeed. + * It is only provided if the datafeed is started. + */ running_state?: DatafeedRunningState } export class DatafeedTimingStats { + /** + * The number of buckets processed. + */ bucket_count: long + /** + * The exponential average search time per hour, in milliseconds. + */ exponential_average_search_time_per_hour_ms: DurationValue + /** + * Identifier for the anomaly detection job. + */ job_id: Id + /** + * The number of searches run by the datafeed. + */ search_count: long + /** + * The total time the datafeed spent searching, in milliseconds. + */ total_search_time_ms: DurationValue + /** + * The average search time per bucket, in milliseconds. + */ average_search_time_per_bucket_ms?: DurationValue } export class DatafeedRunningState { + /** + * Indicates if the datafeed is "real-time"; meaning that the datafeed has no configured `end` time. + */ real_time_configured: boolean + /** + * Indicates whether the datafeed has finished running on the available past data. + * For datafeeds without a configured `end` time, this means that the datafeed is now running on "real-time" data. + */ real_time_running: boolean + /** + * Provides the latest time interval the datafeed has searched. + */ search_interval?: RunningStateSearchInterval } export class RunningStateSearchInterval { + /** + * The end time. + */ end?: Duration + /** + * The end time as an epoch in milliseconds. + */ end_ms: DurationValue + /** + * The start time. + */ start?: Duration + /** + * The start time as an epoch in milliseconds. + */ start_ms: DurationValue } diff --git a/specification/ml/_types/DataframeAnalytics.ts b/specification/ml/_types/DataframeAnalytics.ts index df34bb71d7..c7cb6b21dc 100644 --- a/specification/ml/_types/DataframeAnalytics.ts +++ b/specification/ml/_types/DataframeAnalytics.ts @@ -381,43 +381,182 @@ export class DataframeAnalyticsStatsContainer { } export class DataframeAnalyticsStatsHyperparameters { + /** + * An object containing the parameters of the classification analysis job. + */ hyperparameters: Hyperparameters /** The number of iterations on the analysis. */ iteration: integer + /** + * The timestamp when the statistics were reported in milliseconds since the epoch. + */ timestamp: EpochTime + /** + * An object containing time statistics about the data frame analytics job. + */ timing_stats: TimingStats + /** + * An object containing information about validation loss. + */ validation_loss: ValidationLoss } export class DataframeAnalyticsStatsOutlierDetection { + /** + * The list of job parameters specified by the user or determined by algorithmic heuristics. + */ parameters: OutlierDetectionParameters + /** + * The timestamp when the statistics were reported in milliseconds since the epoch. + */ timestamp: EpochTime + /** + * An object containing time statistics about the data frame analytics job. + */ timing_stats: TimingStats } export class Hyperparameters { + /** + * Advanced configuration option. + * Machine learning uses loss guided tree growing, which means that the decision trees grow where the regularized loss decreases most quickly. + * This parameter affects loss calculations by acting as a multiplier of the tree depth. + * Higher alpha values result in shallower trees and faster training times. + * By default, this value is calculated during hyperparameter optimization. + * It must be greater than or equal to zero. + */ alpha?: double + /** + * Advanced configuration option. + * Regularization parameter to prevent overfitting on the training data set. + * Multiplies an L2 regularization term which applies to leaf weights of the individual trees in the forest. + * A high lambda value causes training to favor small leaf weights. + * This behavior makes the prediction function smoother at the expense of potentially not being able to capture relevant relationships between the features and the dependent variable. + * A small lambda value results in large individual trees and slower training. + * By default, this value is calculated during hyperparameter optimization. + * It must be a nonnegative value. + */ lambda?: double + /** + * Advanced configuration option. + * Regularization parameter to prevent overfitting on the training data set. + * Multiplies a linear penalty associated with the size of individual trees in the forest. + * A high gamma value causes training to prefer small trees. + * A small gamma value results in larger individual trees and slower training. + * By default, this value is calculated during hyperparameter optimization. + * It must be a nonnegative value. + */ gamma?: double + /** + * Advanced configuration option. + * The shrinkage applied to the weights. + * Smaller values result in larger forests which have a better generalization error. + * However, larger forests cause slower training. + * By default, this value is calculated during hyperparameter optimization. + * It must be a value between `0.001` and `1`. + */ eta?: double + /** + * Advanced configuration option. + * Specifies the rate at which `eta` increases for each new tree that is added to the forest. + * For example, a rate of 1.05 increases `eta` by 5% for each extra tree. + * By default, this value is calculated during hyperparameter optimization. + * It must be between `0.5` and `2`. + */ eta_growth_rate_per_tree?: double + /** + * Advanced configuration option. + * Defines the fraction of features that will be used when selecting a random bag for each candidate split. + * By default, this value is calculated during hyperparameter optimization. + */ feature_bag_fraction?: double + /** + * Advanced configuration option. + * Controls the fraction of data that is used to compute the derivatives of the loss function for tree training. + * A small value results in the use of a small fraction of the data. + * If this value is set to be less than 1, accuracy typically improves. + * However, too small a value may result in poor convergence for the ensemble and so require more trees. + * By default, this value is calculated during hyperparameter optimization. + * It must be greater than zero and less than or equal to 1. + */ downsample_factor?: double + /** + * 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. + */ max_attempts_to_add_tree?: integer + /** + * Advanced configuration option. + * 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. + * By default, this value is calculated during hyperparameter optimization. + */ max_optimization_rounds_per_hyperparameter?: integer + /** + * Advanced configuration option. + * Defines the maximum number of decision trees in the forest. + * The maximum value is 2000. + * By default, this value is calculated during hyperparameter optimization. + */ max_trees?: integer + /** + * The maximum number of folds for the cross-validation procedure. + */ num_folds?: integer + /** + * Determines the maximum number of splits for every feature that can occur in a decision tree when the tree is trained. + */ num_splits_per_feature?: integer + /** + * Advanced configuration option. + * Machine learning uses loss guided tree growing, which means that the decision trees grow where the regularized loss decreases most quickly. + * This soft limit combines with the `soft_tree_depth_tolerance` to penalize trees that exceed the specified depth; the regularized loss increases quickly beyond this depth. + * By default, this value is calculated during hyperparameter optimization. + * It must be greater than or equal to 0. + */ soft_tree_depth_limit?: integer + /** + * Advanced configuration option. + * This option controls how quickly the regularized loss increases when the tree depth exceeds `soft_tree_depth_limit`. + * By default, this value is calculated during hyperparameter optimization. + * It must be greater than or equal to 0.01. + */ soft_tree_depth_tolerance?: double } export class OutlierDetectionParameters { + /** + * Specifies whether the feature influence calculation is enabled. + * @server_default true + */ compute_feature_influence?: boolean + /** + * The minimum outlier score that a document needs to have in order to calculate its feature influence score. + * Value range: 0-1 + * @server_default 0.1 + */ feature_influence_threshold?: double + /** + * The method that outlier detection uses. + * Available methods are `lof`, `ldof`, `distance_kth_nn`, `distance_knn`, and `ensemble`. + * The default value is ensemble, which means that outlier detection uses an ensemble of different methods and normalises and combines their individual outlier scores to obtain the overall outlier score. + */ method?: string + /** + * Defines the value for how many nearest neighbors each method of outlier detection uses to calculate its outlier score. + * When the value is not set, different values are used for different ensemble members. + * This default behavior helps improve the diversity in the ensemble; only override it if you are confident that the value you choose is appropriate for the data set. + */ n_neighbors?: integer + /** + * The proportion of the data set that is assumed to be outlying prior to outlier detection. + * For example, 0.05 means it is assumed that 5% of values are real outliers and 95% are inliers. + */ outlier_fraction?: double + /** + * If `true`, the following operation is performed on the columns before computing outlier scores: (x_i - mean(x_i)) / sd(x_i). + * @server_default true + */ standardization_enabled?: boolean } diff --git a/specification/ml/_types/Detector.ts b/specification/ml/_types/Detector.ts index 7de426a8c4..b97202470e 100644 --- a/specification/ml/_types/Detector.ts +++ b/specification/ml/_types/Detector.ts @@ -67,15 +67,60 @@ export class Detector { } export class DetectorRead implements OverloadOf { + /** + * The field used to split the data. + * In particular, this property is used for analyzing the splits with respect to their own history. + * It is used for finding unusual values in the context of the split. + */ by_field_name?: Field + /** + * An array of custom rule objects, which enable you to customize the way detectors operate. + * For example, a rule may dictate to the detector conditions under which results should be skipped. + * Kibana refers to custom rules as job rules. + */ custom_rules?: DetectionRule[] + /** + * A description of the detector. + */ detector_description?: string + /** + * A unique identifier for the detector. + * This identifier is based on the order of the detectors in the `analysis_config`, starting at zero. + */ detector_index?: integer + /** + * Contains one of the following values: `all`, `none`, `by`, or `over`. + * If set, frequent entities are excluded from influencing the anomaly results. + * Entities can be considered frequent over time or frequent in a population. + * If you are working with both over and by fields, then you can set `exclude_frequent` to all for both fields, or to `by` or `over` for those specific fields. + */ exclude_frequent?: ExcludeFrequent + /** + * The field that the detector uses in the function. + * If you use an event rate function such as `count` or `rare`, do not specify this field. + */ field_name?: Field + /** + * The analysis function that is used. + * For example, `count`, `rare`, `mean`, `min`, `max`, and `sum`. + * @doc_id ml-functions + */ function: string + /** + * The field used to split the data. + * In particular, this property is used for analyzing the splits with respect to the history of all splits. + * It is used for finding unusual values in the population of all splits. + */ over_field_name?: Field + /** + * The field used to segment the analysis. + * When you use this property, you have completely independent baselines for each value of this field. + */ partition_field_name?: Field + /** + * Defines whether a new series is used as the null series when there is no value for the by or partition fields. + * @server_default false + */ use_null?: boolean } diff --git a/specification/ml/_types/Job.ts b/specification/ml/_types/Job.ts index 9babc92acc..e090f1cf20 100644 --- a/specification/ml/_types/Job.ts +++ b/specification/ml/_types/Job.ts @@ -59,63 +59,273 @@ export class JobStatistics { } export class Job { + /** + * Advanced configuration option. + * Specifies whether this job can open when there is insufficient machine learning node capacity for it to be immediately assigned to a node. + */ allow_lazy_open: boolean + /** + * The analysis configuration, which specifies how to analyze the data. + * After you create a job, you cannot change the analysis configuration; all the properties are informational. + */ analysis_config: AnalysisConfig + /** + * Limits can be applied for the resources required to hold the mathematical models in memory. + * These limits are approximate and can be set per job. + * They do not control the memory used by other processes, for example the Elasticsearch Java processes. + */ analysis_limits?: AnalysisLimits + /** + * Advanced configuration option. + * The time between each periodic persistence of the model. + * The default value is a randomized value between 3 to 4 hours, which avoids all jobs persisting at exactly the same time. + * The smallest allowed value is 1 hour. + */ background_persist_interval?: Duration blocked?: JobBlocked create_time?: DateTime + /** + * Advanced configuration option. + * Contains custom metadata about the job. + */ custom_settings?: CustomSettings + /** + * Advanced configuration option, which affects the automatic removal of old model snapshots for this job. + * It specifies a period of time (in days) after which only the first snapshot per day is retained. + * This period is relative to the timestamp of the most recent snapshot for this job. + * Valid values range from 0 to `model_snapshot_retention_days`. + * @server_default 1 + */ daily_model_snapshot_retention_after_days?: long + /** + * The data description defines the format of the input data when you send data to the job by using the post data API. + * Note that when configuring a datafeed, these properties are automatically set. + * When data is received via the post data API, it is not stored in Elasticsearch. + * Only the results for anomaly detection are retained. + */ data_description: DataDescription + /** + * The datafeed, which retrieves data from Elasticsearch for analysis by the job. + * You can associate only one datafeed with each anomaly detection job. + */ datafeed_config?: Datafeed + /** + * Indicates that the process of deleting the job is in progress but not yet completed. + * It is only reported when `true`. + */ deleting?: boolean + /** + * A description of the job. + */ description?: string + /** + * If the job closed or failed, this is the time the job finished, otherwise it is `null`. + * This property is informational; you cannot change its value. + */ finished_time?: DateTime + /** + * A list of job groups. + * A job can belong to no groups or many. + */ groups?: string[] + /** + * Identifier for the anomaly detection job. + * This identifier can contain lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores. + * It must start and end with alphanumeric characters. + */ job_id: Id + /** + * Reserved for future use, currently set to `anomaly_detector`. + */ job_type?: string + /** + * The machine learning configuration version number at which the the job was created. + */ job_version?: VersionString + /** + * This advanced configuration option stores model information along with the results. + * It provides a more detailed view into anomaly detection. + * Model plot provides a simplified and indicative view of the model and its bounds. + */ model_plot_config?: ModelPlotConfig model_snapshot_id?: Id + /** + * Advanced configuration option, which affects the automatic removal of old model snapshots for this job. + * It specifies the maximum period of time (in days) that snapshots are retained. + * This period is relative to the timestamp of the most recent snapshot for this job. + * By default, snapshots ten days older than the newest snapshot are deleted. + */ model_snapshot_retention_days: long + /** + * Advanced configuration option. + * The period over which adjustments to the score are applied, as new data is seen. + * The default value is the longer of 30 days or 100 `bucket_spans`. + */ renormalization_window_days?: long + /** + * A text string that affects the name of the machine learning results index. + * The default value is `shared`, which generates an index named `.ml-anomalies-shared`. + */ results_index_name: IndexName + /** + * Advanced configuration option. + * The period of time (in days) that results are retained. + * Age is calculated relative to the timestamp of the latest bucket result. + * If this property has a non-null value, once per day at 00:30 (server time), results that are the specified number of days older than the latest bucket result are deleted from Elasticsearch. + * The default value is null, which means all results are retained. + * Annotations generated by the system also count as results for retention purposes; they are deleted after the same number of days as results. + * Annotations added by users are retained forever. + */ results_retention_days?: long } export class JobConfig { + /** + * Advanced configuration option. Specifies whether this job can open when there is insufficient machine learning node capacity for it to be immediately assigned to a node. + * @server_default false + * @doc_id ml-put-job + */ allow_lazy_open?: boolean + /** + * The analysis configuration, which specifies how to analyze the data. + * After you create a job, you cannot change the analysis configuration; all the properties are informational. + */ analysis_config: AnalysisConfig + /** + * Limits can be applied for the resources required to hold the mathematical models in memory. + * These limits are approximate and can be set per job. + * They do not control the memory used by other processes, for example the Elasticsearch Java processes. + */ analysis_limits?: AnalysisLimits + /** + * Advanced configuration option. + * The time between each periodic persistence of the model. + * The default value is a randomized value between 3 to 4 hours, which avoids all jobs persisting at exactly the same time. + * The smallest allowed value is 1 hour. + */ background_persist_interval?: Duration + /** + * Advanced configuration option. + * Contains custom metadata about the job. + */ custom_settings?: CustomSettings + /** + * Advanced configuration option, which affects the automatic removal of old model snapshots for this job. + * It specifies a period of time (in days) after which only the first snapshot per day is retained. + * This period is relative to the timestamp of the most recent snapshot for this job. + * @server_default 1 + */ daily_model_snapshot_retention_after_days?: long + /** + * The data description defines the format of the input data when you send data to the job by using the post data API. + * Note that when configure a datafeed, these properties are automatically set. + */ data_description: DataDescription + /** + * The datafeed, which retrieves data from Elasticsearch for analysis by the job. + * You can associate only one datafeed with each anomaly detection job. + */ datafeed_config?: DatafeedConfig + /** + * A description of the job. + */ description?: string + /** + * A list of job groups. A job can belong to no groups or many. + */ groups?: string[] + /** + * Identifier for the anomaly detection job. + * This identifier can contain lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores. + * It must start and end with alphanumeric characters. + */ job_id?: Id + /** + * Reserved for future use, currently set to `anomaly_detector`. + */ job_type?: string + /** + * This advanced configuration option stores model information along with the results. + * It provides a more detailed view into anomaly detection. + * Model plot provides a simplified and indicative view of the model and its bounds. + */ model_plot_config?: ModelPlotConfig + /** + * Advanced configuration option, which affects the automatic removal of old model snapshots for this job. + * It specifies the maximum period of time (in days) that snapshots are retained. + * This period is relative to the timestamp of the most recent snapshot for this job. + * The default value is `10`, which means snapshots ten days older than the newest snapshot are deleted. + * @server_default 10 + */ model_snapshot_retention_days?: long + /** + * Advanced configuration option. + * The period over which adjustments to the score are applied, as new data is seen. + * The default value is the longer of 30 days or 100 `bucket_spans`. + */ renormalization_window_days?: long + /** + * A text string that affects the name of the machine learning results index. + * The default value is `shared`, which generates an index named `.ml-anomalies-shared`. + * @server_default shared + */ results_index_name?: IndexName + /** + * Advanced configuration option. + * The period of time (in days) that results are retained. + * Age is calculated relative to the timestamp of the latest bucket result. + * If this property has a non-null value, once per day at 00:30 (server time), results that are the specified number of days older than the latest bucket result are deleted from Elasticsearch. + * The default value is null, which means all results are retained. + * Annotations generated by the system also count as results for retention purposes; they are deleted after the same number of days as results. + * Annotations added by users are retained forever. + */ results_retention_days?: long } export class JobStats { + /** + * For open anomaly detection jobs only, contains messages relating to the selection of a node to run the job. + */ assignment_explanation?: string + /** + * An object that describes the quantity of input to the job and any related error counts. + * The `data_count` values are cumulative for the lifetime of a job. + * If a model snapshot is reverted or old results are deleted, the job counts are not reset. + */ data_counts: DataCounts + /** + * An object that provides statistical information about forecasts belonging to this job. + * Some statistics are omitted if no forecasts have been made. + */ forecasts_stats: JobForecastStatistics + /** + * Identifier for the anomaly detection job. + */ job_id: string + /** + * An object that provides information about the size and contents of the model. + */ model_size_stats: ModelSizeStats /** + * Contains properties for the node that runs the job. + * This information is available only for open jobs. * @availability stack */ node?: DiscoveryNode + /** + * For open jobs only, the elapsed time for which the job has been open. + */ open_time?: DateTime + /** + * The status of the anomaly detection job, which can be one of the following values: `closed`, `closing`, `failed`, `opened`, `opening`. + */ state: JobState + /** + * An object that provides statistical information about timing aspect of this job. + */ timing_stats: JobTimingStats + /** + * Indicates that the process of deleting the job is in progress but not yet completed. It is only reported when `true`. + */ deleting?: boolean } diff --git a/specification/ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts b/specification/ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts index 1f6a10f354..16c7378fcf 100644 --- a/specification/ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts +++ b/specification/ml/delete_calendar_event/MlDeleteCalendarEventRequest.ts @@ -29,7 +29,14 @@ import { Id } from '@_types/common' */ export interface Request extends RequestBase { path_parts: { + /** + * A string that uniquely identifies a calendar. + */ calendar_id: Id + /** + * Identifier for the scheduled event. + * You can obtain this identifier by using the get calendar events API. + */ event_id: Id } } diff --git a/specification/ml/evaluate_data_frame/types.ts b/specification/ml/evaluate_data_frame/types.ts index 1fc221b24d..bf2553cbd8 100644 --- a/specification/ml/evaluate_data_frame/types.ts +++ b/specification/ml/evaluate_data_frame/types.ts @@ -22,24 +22,65 @@ import { Name } from '@_types/common' import { double, integer } from '@_types/Numeric' export class DataframeOutlierDetectionSummary { + /** + * The AUC ROC (area under the curve of the receiver operating characteristic) score and optionally the curve. + * @server_default {"include_curve": false} + */ auc_roc?: DataframeEvaluationSummaryAucRoc + /** + * Set the different thresholds of the outlier score at where the metric is calculated. + */ precision?: Dictionary + /** + * Set the different thresholds of the outlier score at where the metric is calculated. + */ recall?: Dictionary + /** + * Set the different thresholds of the outlier score at where the metrics (`tp` - true positive, `fp` - false positive, `tn` - true negative, `fn` - false negative) are calculated. + */ confusion_matrix?: Dictionary } export class DataframeClassificationSummary { + /** + * The AUC ROC (area under the curve of the receiver operating characteristic) score and optionally the curve. + * It is calculated for a specific class (provided as "class_name") treated as positive. + */ auc_roc?: DataframeEvaluationSummaryAucRoc + /** + * Accuracy of predictions (per-class and overall). + */ accuracy?: DataframeClassificationSummaryAccuracy + /** + * Multiclass confusion matrix. + */ multiclass_confusion_matrix?: DataframeClassificationSummaryMulticlassConfusionMatrix + /** + * Precision of predictions (per-class and average). + */ precision?: DataframeClassificationSummaryPrecision + /** + * Recall of predictions (per-class and average). + */ recall?: DataframeClassificationSummaryRecall } export class DataframeRegressionSummary { + /** + * Pseudo Huber loss function. + */ huber?: DataframeEvaluationValue + /** + * Average squared difference between the predicted values and the actual (`ground truth`) value. + */ mse?: DataframeEvaluationValue + /** + * Average squared difference between the logarithm of the predicted values and the logarithm of the actual (`ground truth`) value. + */ msle?: DataframeEvaluationValue + /** + * Proportion of the variance in the dependent variable that is predictable from the independent variables. + */ r_squared?: DataframeEvaluationValue } diff --git a/specification/ml/get_categories/MlGetCategoriesRequest.ts b/specification/ml/get_categories/MlGetCategoriesRequest.ts index 66b93087a0..bd0b4fea02 100644 --- a/specification/ml/get_categories/MlGetCategoriesRequest.ts +++ b/specification/ml/get_categories/MlGetCategoriesRequest.ts @@ -61,6 +61,10 @@ export interface Request extends RequestBase { size?: integer } body: { + /** + * Configures pagination. + * This parameter has the `from` and `size` properties. + */ page?: Page } } diff --git a/specification/ml/get_influencers/MlGetInfluencersRequest.ts b/specification/ml/get_influencers/MlGetInfluencersRequest.ts index 3f4bfca588..e8a431d3ec 100644 --- a/specification/ml/get_influencers/MlGetInfluencersRequest.ts +++ b/specification/ml/get_influencers/MlGetInfluencersRequest.ts @@ -88,6 +88,10 @@ export interface Request extends RequestBase { start?: DateTime } body: { + /** + * Configures pagination. + * This parameter has the `from` and `size` properties. + */ page?: Page } }