elasticsearch/_async/client/ml.py [3779:3974]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
self,
*,
job_id: str,
analysis_config: t.Optional[t.Mapping[str, t.Any]] = None,
data_description: t.Optional[t.Mapping[str, t.Any]] = None,
allow_lazy_open: t.Optional[bool] = None,
allow_no_indices: t.Optional[bool] = None,
analysis_limits: t.Optional[t.Mapping[str, t.Any]] = None,
background_persist_interval: t.Optional[
t.Union[str, t.Literal[-1], t.Literal[0]]
] = None,
custom_settings: t.Optional[t.Any] = None,
daily_model_snapshot_retention_after_days: t.Optional[int] = None,
datafeed_config: t.Optional[t.Mapping[str, t.Any]] = None,
description: t.Optional[str] = None,
error_trace: t.Optional[bool] = None,
expand_wildcards: t.Optional[
t.Union[
t.Sequence[
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]]
],
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]],
]
] = None,
filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
groups: t.Optional[t.Sequence[str]] = None,
human: t.Optional[bool] = None,
ignore_throttled: t.Optional[bool] = None,
ignore_unavailable: t.Optional[bool] = None,
model_plot_config: t.Optional[t.Mapping[str, t.Any]] = None,
model_snapshot_retention_days: t.Optional[int] = None,
pretty: t.Optional[bool] = None,
renormalization_window_days: t.Optional[int] = None,
results_index_name: t.Optional[str] = None,
results_retention_days: t.Optional[int] = None,
body: t.Optional[t.Dict[str, t.Any]] = None,
) -> ObjectApiResponse[t.Any]:
"""
.. raw:: html
Create an anomaly detection job.
If you include a datafeed_config, you must have read index privileges on the source index.
If you include a datafeed_config but do not provide a query, the datafeed uses {"match_all": {"boost": 1}}.
``_
:param job_id: The 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.
:param analysis_config: Specifies how to analyze the data. After you create a
job, you cannot change the analysis configuration; all the properties are
informational.
:param 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. When data is received via the post
data API, it is not stored in Elasticsearch. Only the results for anomaly
detection are retained.
:param allow_lazy_open: 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. By default, if a machine learning
node with capacity to run the job cannot immediately be found, the open anomaly
detection jobs API returns an error. However, this is also subject to the
cluster-wide `xpack.ml.max_lazy_ml_nodes` setting. If this option is set
to true, the open anomaly detection jobs API does not return an error and
the job waits in the opening state until sufficient machine learning node
capacity is available.
:param allow_no_indices: If `true`, wildcard indices expressions that resolve
into no concrete indices are ignored. This includes the `_all` string or
when no indices are specified.
:param analysis_limits: 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.
:param background_persist_interval: 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. For very large models (several
GB), persistence could take 10-20 minutes, so do not set the `background_persist_interval`
value too low.
:param custom_settings: Advanced configuration option. Contains custom meta data
about the job.
:param daily_model_snapshot_retention_after_days: 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`.
:param datafeed_config: Defines a datafeed for the anomaly detection job. If
Elasticsearch security features are enabled, your datafeed remembers which
roles the user who created it had at the time of creation and runs the query
using those same roles. If you provide secondary authorization headers, those
credentials are used instead.
:param description: A description of the job.
:param expand_wildcards: Type of index that wildcard patterns can match. If the
request can target data streams, this argument determines whether wildcard
expressions match hidden data streams. Supports comma-separated values. Valid
values are: * `all`: Match any data stream or index, including hidden ones.
* `closed`: Match closed, non-hidden indices. Also matches any non-hidden
data stream. Data streams cannot be closed. * `hidden`: Match hidden data
streams and hidden indices. Must be combined with `open`, `closed`, or both.
* `none`: Wildcard patterns are not accepted. * `open`: Match open, non-hidden
indices. Also matches any non-hidden data stream.
:param groups: A list of job groups. A job can belong to no groups or many.
:param ignore_throttled: If `true`, concrete, expanded or aliased indices are
ignored when frozen.
:param ignore_unavailable: If `true`, unavailable indices (missing or closed)
are ignored.
:param model_plot_config: This advanced configuration option stores model information
along with the results. It provides a more detailed view into anomaly detection.
If you enable model plot it can add considerable overhead to the performance
of the system; it is not feasible for jobs with many entities. Model plot
provides a simplified and indicative view of the model and its bounds. It
does not display complex features such as multivariate correlations or multimodal
data. As such, anomalies may occasionally be reported which cannot be seen
in the model plot. Model plot config can be configured when the job is created
or updated later. It must be disabled if performance issues are experienced.
:param model_snapshot_retention_days: 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.
:param renormalization_window_days: 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.
:param results_index_name: A text string that affects the name of the machine
learning results index. By default, the job generates an index named `.ml-anomalies-shared`.
:param results_retention_days: 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.
"""
if job_id in SKIP_IN_PATH:
raise ValueError("Empty value passed for parameter 'job_id'")
if analysis_config is None and body is None:
raise ValueError("Empty value passed for parameter 'analysis_config'")
if data_description is None and body is None:
raise ValueError("Empty value passed for parameter 'data_description'")
__path_parts: t.Dict[str, str] = {"job_id": _quote(job_id)}
__path = f'/_ml/anomaly_detectors/{__path_parts["job_id"]}'
__query: t.Dict[str, t.Any] = {}
__body: t.Dict[str, t.Any] = body if body is not None else {}
if allow_no_indices is not None:
__query["allow_no_indices"] = allow_no_indices
if error_trace is not None:
__query["error_trace"] = error_trace
if expand_wildcards is not None:
__query["expand_wildcards"] = expand_wildcards
if filter_path is not None:
__query["filter_path"] = filter_path
if human is not None:
__query["human"] = human
if ignore_throttled is not None:
__query["ignore_throttled"] = ignore_throttled
if ignore_unavailable is not None:
__query["ignore_unavailable"] = ignore_unavailable
if pretty is not None:
__query["pretty"] = pretty
if not __body:
if analysis_config is not None:
__body["analysis_config"] = analysis_config
if data_description is not None:
__body["data_description"] = data_description
if allow_lazy_open is not None:
__body["allow_lazy_open"] = allow_lazy_open
if analysis_limits is not None:
__body["analysis_limits"] = analysis_limits
if background_persist_interval is not None:
__body["background_persist_interval"] = background_persist_interval
if custom_settings is not None:
__body["custom_settings"] = custom_settings
if daily_model_snapshot_retention_after_days is not None:
__body["daily_model_snapshot_retention_after_days"] = (
daily_model_snapshot_retention_after_days
)
if datafeed_config is not None:
__body["datafeed_config"] = datafeed_config
if description is not None:
__body["description"] = description
if groups is not None:
__body["groups"] = groups
if model_plot_config is not None:
__body["model_plot_config"] = model_plot_config
if model_snapshot_retention_days is not None:
__body["model_snapshot_retention_days"] = model_snapshot_retention_days
if renormalization_window_days is not None:
__body["renormalization_window_days"] = renormalization_window_days
if results_index_name is not None:
__body["results_index_name"] = results_index_name
if results_retention_days is not None:
__body["results_retention_days"] = results_retention_days
__headers = {"accept": "application/json", "content-type": "application/json"}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
elasticsearch/_sync/client/ml.py [3779:3974]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
self,
*,
job_id: str,
analysis_config: t.Optional[t.Mapping[str, t.Any]] = None,
data_description: t.Optional[t.Mapping[str, t.Any]] = None,
allow_lazy_open: t.Optional[bool] = None,
allow_no_indices: t.Optional[bool] = None,
analysis_limits: t.Optional[t.Mapping[str, t.Any]] = None,
background_persist_interval: t.Optional[
t.Union[str, t.Literal[-1], t.Literal[0]]
] = None,
custom_settings: t.Optional[t.Any] = None,
daily_model_snapshot_retention_after_days: t.Optional[int] = None,
datafeed_config: t.Optional[t.Mapping[str, t.Any]] = None,
description: t.Optional[str] = None,
error_trace: t.Optional[bool] = None,
expand_wildcards: t.Optional[
t.Union[
t.Sequence[
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]]
],
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]],
]
] = None,
filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
groups: t.Optional[t.Sequence[str]] = None,
human: t.Optional[bool] = None,
ignore_throttled: t.Optional[bool] = None,
ignore_unavailable: t.Optional[bool] = None,
model_plot_config: t.Optional[t.Mapping[str, t.Any]] = None,
model_snapshot_retention_days: t.Optional[int] = None,
pretty: t.Optional[bool] = None,
renormalization_window_days: t.Optional[int] = None,
results_index_name: t.Optional[str] = None,
results_retention_days: t.Optional[int] = None,
body: t.Optional[t.Dict[str, t.Any]] = None,
) -> ObjectApiResponse[t.Any]:
"""
.. raw:: html
Create an anomaly detection job.
If you include a datafeed_config, you must have read index privileges on the source index.
If you include a datafeed_config but do not provide a query, the datafeed uses {"match_all": {"boost": 1}}.
``_
:param job_id: The 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.
:param analysis_config: Specifies how to analyze the data. After you create a
job, you cannot change the analysis configuration; all the properties are
informational.
:param 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. When data is received via the post
data API, it is not stored in Elasticsearch. Only the results for anomaly
detection are retained.
:param allow_lazy_open: 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. By default, if a machine learning
node with capacity to run the job cannot immediately be found, the open anomaly
detection jobs API returns an error. However, this is also subject to the
cluster-wide `xpack.ml.max_lazy_ml_nodes` setting. If this option is set
to true, the open anomaly detection jobs API does not return an error and
the job waits in the opening state until sufficient machine learning node
capacity is available.
:param allow_no_indices: If `true`, wildcard indices expressions that resolve
into no concrete indices are ignored. This includes the `_all` string or
when no indices are specified.
:param analysis_limits: 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.
:param background_persist_interval: 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. For very large models (several
GB), persistence could take 10-20 minutes, so do not set the `background_persist_interval`
value too low.
:param custom_settings: Advanced configuration option. Contains custom meta data
about the job.
:param daily_model_snapshot_retention_after_days: 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`.
:param datafeed_config: Defines a datafeed for the anomaly detection job. If
Elasticsearch security features are enabled, your datafeed remembers which
roles the user who created it had at the time of creation and runs the query
using those same roles. If you provide secondary authorization headers, those
credentials are used instead.
:param description: A description of the job.
:param expand_wildcards: Type of index that wildcard patterns can match. If the
request can target data streams, this argument determines whether wildcard
expressions match hidden data streams. Supports comma-separated values. Valid
values are: * `all`: Match any data stream or index, including hidden ones.
* `closed`: Match closed, non-hidden indices. Also matches any non-hidden
data stream. Data streams cannot be closed. * `hidden`: Match hidden data
streams and hidden indices. Must be combined with `open`, `closed`, or both.
* `none`: Wildcard patterns are not accepted. * `open`: Match open, non-hidden
indices. Also matches any non-hidden data stream.
:param groups: A list of job groups. A job can belong to no groups or many.
:param ignore_throttled: If `true`, concrete, expanded or aliased indices are
ignored when frozen.
:param ignore_unavailable: If `true`, unavailable indices (missing or closed)
are ignored.
:param model_plot_config: This advanced configuration option stores model information
along with the results. It provides a more detailed view into anomaly detection.
If you enable model plot it can add considerable overhead to the performance
of the system; it is not feasible for jobs with many entities. Model plot
provides a simplified and indicative view of the model and its bounds. It
does not display complex features such as multivariate correlations or multimodal
data. As such, anomalies may occasionally be reported which cannot be seen
in the model plot. Model plot config can be configured when the job is created
or updated later. It must be disabled if performance issues are experienced.
:param model_snapshot_retention_days: 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.
:param renormalization_window_days: 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.
:param results_index_name: A text string that affects the name of the machine
learning results index. By default, the job generates an index named `.ml-anomalies-shared`.
:param results_retention_days: 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.
"""
if job_id in SKIP_IN_PATH:
raise ValueError("Empty value passed for parameter 'job_id'")
if analysis_config is None and body is None:
raise ValueError("Empty value passed for parameter 'analysis_config'")
if data_description is None and body is None:
raise ValueError("Empty value passed for parameter 'data_description'")
__path_parts: t.Dict[str, str] = {"job_id": _quote(job_id)}
__path = f'/_ml/anomaly_detectors/{__path_parts["job_id"]}'
__query: t.Dict[str, t.Any] = {}
__body: t.Dict[str, t.Any] = body if body is not None else {}
if allow_no_indices is not None:
__query["allow_no_indices"] = allow_no_indices
if error_trace is not None:
__query["error_trace"] = error_trace
if expand_wildcards is not None:
__query["expand_wildcards"] = expand_wildcards
if filter_path is not None:
__query["filter_path"] = filter_path
if human is not None:
__query["human"] = human
if ignore_throttled is not None:
__query["ignore_throttled"] = ignore_throttled
if ignore_unavailable is not None:
__query["ignore_unavailable"] = ignore_unavailable
if pretty is not None:
__query["pretty"] = pretty
if not __body:
if analysis_config is not None:
__body["analysis_config"] = analysis_config
if data_description is not None:
__body["data_description"] = data_description
if allow_lazy_open is not None:
__body["allow_lazy_open"] = allow_lazy_open
if analysis_limits is not None:
__body["analysis_limits"] = analysis_limits
if background_persist_interval is not None:
__body["background_persist_interval"] = background_persist_interval
if custom_settings is not None:
__body["custom_settings"] = custom_settings
if daily_model_snapshot_retention_after_days is not None:
__body["daily_model_snapshot_retention_after_days"] = (
daily_model_snapshot_retention_after_days
)
if datafeed_config is not None:
__body["datafeed_config"] = datafeed_config
if description is not None:
__body["description"] = description
if groups is not None:
__body["groups"] = groups
if model_plot_config is not None:
__body["model_plot_config"] = model_plot_config
if model_snapshot_retention_days is not None:
__body["model_snapshot_retention_days"] = model_snapshot_retention_days
if renormalization_window_days is not None:
__body["renormalization_window_days"] = renormalization_window_days
if results_index_name is not None:
__body["results_index_name"] = results_index_name
if results_retention_days is not None:
__body["results_retention_days"] = results_retention_days
__headers = {"accept": "application/json", "content-type": "application/json"}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -