Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJob
- Inherits:
-
Object
- Object
- Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJob
- Includes:
- Core::Hashable, Core::JsonObjectSupport
- Defined in:
- lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb
Overview
A job that uses a Model to produce predictions on multiple input instances. If predictions for significant portion of the instances fail, the job may finish without attempting predictions for all remaining instances.
Instance Attribute Summary collapse
-
#completion_stats ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1CompletionStats
Success and error statistics of processing multiple entities (for example, DataItems or structured data rows) in batch.
-
#create_time ⇒ String
Output only.
-
#dedicated_resources ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchDedicatedResources
A description of resources that are used for performing batch operations, are dedicated to a Model, and need manual configuration.
-
#disable_container_logging ⇒ Boolean
(also: #disable_container_logging?)
For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderrandstdoutstreams to Cloud Logging by default. -
#display_name ⇒ String
Required.
-
#encryption_spec ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EncryptionSpec
Represents a customer-managed encryption key spec that can be applied to a top- level resource.
-
#end_time ⇒ String
Output only.
-
#error ⇒ Google::Apis::AiplatformV1beta1::GoogleRpcStatus
The
Statustype defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. -
#explanation_spec ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ExplanationSpec
Specification of Model explanation.
-
#generate_explanation ⇒ Boolean
(also: #generate_explanation?)
Generate explanation with the batch prediction results.
-
#input_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobInputConfig
Configures the input to BatchPredictionJob.
-
#instance_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobInstanceConfig
Configuration defining how to transform batch prediction input instances to the instances that the Model accepts.
-
#labels ⇒ Hash<String,String>
The labels with user-defined metadata to organize BatchPredictionJobs.
-
#manual_batch_tuning_parameters ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ManualBatchTuningParameters
Manual batch tuning parameters.
-
#model ⇒ String
The name of the Model resource that produces the predictions via this job, must share the same ancestor Location.
-
#model_monitoring_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelMonitoringConfig
The model monitoring configuration used for Batch Prediction Job.
-
#model_monitoring_stats_anomalies ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelMonitoringStatsAnomalies>
Get batch prediction job monitoring statistics.
-
#model_monitoring_status ⇒ Google::Apis::AiplatformV1beta1::GoogleRpcStatus
The
Statustype defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. -
#model_parameters ⇒ Object
The parameters that govern the predictions.
-
#model_version_id ⇒ String
Output only.
-
#name ⇒ String
Output only.
-
#output_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobOutputConfig
Configures the output of BatchPredictionJob.
-
#output_info ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobOutputInfo
Further describes this job's output.
-
#partial_failures ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleRpcStatus>
Output only.
-
#resources_consumed ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ResourcesConsumed
Statistics information about resource consumption.
-
#service_account ⇒ String
The service account that the DeployedModel's container runs as.
-
#start_time ⇒ String
Output only.
-
#state ⇒ String
Output only.
-
#unmanaged_container_model ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1UnmanagedContainerModel
Contains model information necessary to perform batch prediction without requiring a full model import.
-
#update_time ⇒ String
Output only.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1BatchPredictionJob
constructor
A new instance of GoogleCloudAiplatformV1beta1BatchPredictionJob.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1BatchPredictionJob
Returns a new instance of GoogleCloudAiplatformV1beta1BatchPredictionJob.
2444 2445 2446 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2444 def initialize(**args) update!(**args) end |
Instance Attribute Details
#completion_stats ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1CompletionStats
Success and error statistics of processing multiple entities (for example,
DataItems or structured data rows) in batch.
Corresponds to the JSON property completionStats
2242 2243 2244 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2242 def completion_stats @completion_stats end |
#create_time ⇒ String
Output only. Time when the BatchPredictionJob was created.
Corresponds to the JSON property createTime
2247 2248 2249 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2247 def create_time @create_time end |
#dedicated_resources ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchDedicatedResources
A description of resources that are used for performing batch operations, are
dedicated to a Model, and need manual configuration.
Corresponds to the JSON property dedicatedResources
2253 2254 2255 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2253 def dedicated_resources @dedicated_resources end |
#disable_container_logging ⇒ Boolean Also known as: disable_container_logging?
For custom-trained Models and AutoML Tabular Models, the container of the
DeployedModel instances will send stderr and stdout streams to Cloud
Logging by default. Please note that the logs incur cost, which are subject to
Cloud Logging pricing. User can
disable container logging by setting this flag to true.
Corresponds to the JSON property disableContainerLogging
2262 2263 2264 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2262 def disable_container_logging @disable_container_logging end |
#display_name ⇒ String
Required. The user-defined name of this BatchPredictionJob.
Corresponds to the JSON property displayName
2268 2269 2270 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2268 def display_name @display_name end |
#encryption_spec ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EncryptionSpec
Represents a customer-managed encryption key spec that can be applied to a top-
level resource.
Corresponds to the JSON property encryptionSpec
2274 2275 2276 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2274 def encryption_spec @encryption_spec end |
#end_time ⇒ String
Output only. Time when the BatchPredictionJob entered any of the following
states: JOB_STATE_SUCCEEDED, JOB_STATE_FAILED, JOB_STATE_CANCELLED.
Corresponds to the JSON property endTime
2280 2281 2282 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2280 def end_time @end_time end |
#error ⇒ Google::Apis::AiplatformV1beta1::GoogleRpcStatus
The Status type defines a logical error model that is suitable for different
programming environments, including REST APIs and RPC APIs. It is used by
gRPC. Each Status message contains three pieces of
data: error code, error message, and error details. You can find out more
about this error model and how to work with it in the API Design Guide.
Corresponds to the JSON property error
2290 2291 2292 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2290 def error @error end |
#explanation_spec ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ExplanationSpec
Specification of Model explanation.
Corresponds to the JSON property explanationSpec
2295 2296 2297 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2295 def explanation_spec @explanation_spec end |
#generate_explanation ⇒ Boolean Also known as: generate_explanation?
Generate explanation with the batch prediction results. When set to true,
the batch prediction output changes based on the predictions_format field of
the BatchPredictionJob.output_config object: * bigquery: output includes a
column named explanation. The value is a struct that conforms to the
Explanation object. * jsonl: The JSON objects on each line include an
additional entry keyed explanation. The value of the entry is a JSON object
that conforms to the Explanation object. * csv: Generating explanations for
CSV format is not supported. If this field is set to true, either the Model.
explanation_spec or explanation_spec must be populated.
Corresponds to the JSON property generateExplanation
2308 2309 2310 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2308 def generate_explanation @generate_explanation end |
#input_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobInputConfig
Configures the input to BatchPredictionJob. See Model.
supported_input_storage_formats for Model's supported input formats, and how
instances should be expressed via any of them.
Corresponds to the JSON property inputConfig
2316 2317 2318 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2316 def input_config @input_config end |
#instance_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobInstanceConfig
Configuration defining how to transform batch prediction input instances to
the instances that the Model accepts.
Corresponds to the JSON property instanceConfig
2322 2323 2324 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2322 def instance_config @instance_config end |
#labels ⇒ Hash<String,String>
The labels with user-defined metadata to organize BatchPredictionJobs. Label
keys and values can be no longer than 64 characters (Unicode codepoints), can
only contain lowercase letters, numeric characters, underscores and dashes.
International characters are allowed. See https://goo.gl/xmQnxf for more
information and examples of labels.
Corresponds to the JSON property labels
2331 2332 2333 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2331 def labels @labels end |
#manual_batch_tuning_parameters ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ManualBatchTuningParameters
Manual batch tuning parameters.
Corresponds to the JSON property manualBatchTuningParameters
2336 2337 2338 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2336 def manual_batch_tuning_parameters @manual_batch_tuning_parameters end |
#model ⇒ String
The name of the Model resource that produces the predictions via this job,
must share the same ancestor Location. Starting this job has no impact on any
existing deployments of the Model and their resources. Exactly one of model
and unmanaged_container_model must be set. The model resource name may contain
version id or version alias to specify the version. Example: projects/
project/locations/location/models/model@2 or projects/project/
locations/location/models/model@golden if no version is specified, the
default version will be deployed. The model resource could also be a publisher
model. Example: publishers/publisher/models/modelor `projects/`project`/
locations/`location`/publishers/`publisher`/models/`model
Corresponds to the JSON property model
2350 2351 2352 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2350 def model @model end |
#model_monitoring_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelMonitoringConfig
The model monitoring configuration used for Batch Prediction Job.
Corresponds to the JSON property modelMonitoringConfig
2355 2356 2357 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2355 def model_monitoring_config @model_monitoring_config end |
#model_monitoring_stats_anomalies ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ModelMonitoringStatsAnomalies>
Get batch prediction job monitoring statistics.
Corresponds to the JSON property modelMonitoringStatsAnomalies
2360 2361 2362 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2360 def model_monitoring_stats_anomalies @model_monitoring_stats_anomalies end |
#model_monitoring_status ⇒ Google::Apis::AiplatformV1beta1::GoogleRpcStatus
The Status type defines a logical error model that is suitable for different
programming environments, including REST APIs and RPC APIs. It is used by
gRPC. Each Status message contains three pieces of
data: error code, error message, and error details. You can find out more
about this error model and how to work with it in the API Design Guide.
Corresponds to the JSON property modelMonitoringStatus
2370 2371 2372 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2370 def model_monitoring_status @model_monitoring_status end |
#model_parameters ⇒ Object
The parameters that govern the predictions. The schema of the parameters may
be specified via the Model's PredictSchemata's parameters_schema_uri.
Corresponds to the JSON property modelParameters
2376 2377 2378 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2376 def model_parameters @model_parameters end |
#model_version_id ⇒ String
Output only. The version ID of the Model that produces the predictions via
this job.
Corresponds to the JSON property modelVersionId
2382 2383 2384 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2382 def model_version_id @model_version_id end |
#name ⇒ String
Output only. Resource name of the BatchPredictionJob.
Corresponds to the JSON property name
2387 2388 2389 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2387 def name @name end |
#output_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobOutputConfig
Configures the output of BatchPredictionJob. See Model.
supported_output_storage_formats for supported output formats, and how
predictions are expressed via any of them.
Corresponds to the JSON property outputConfig
2394 2395 2396 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2394 def output_config @output_config end |
#output_info ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1BatchPredictionJobOutputInfo
Further describes this job's output. Supplements output_config.
Corresponds to the JSON property outputInfo
2399 2400 2401 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2399 def output_info @output_info end |
#partial_failures ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleRpcStatus>
Output only. Partial failures encountered. For example, single files that can'
t be read. This field never exceeds 20 entries. Status details fields contain
standard Google Cloud error details.
Corresponds to the JSON property partialFailures
2406 2407 2408 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2406 def partial_failures @partial_failures end |
#resources_consumed ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1ResourcesConsumed
Statistics information about resource consumption.
Corresponds to the JSON property resourcesConsumed
2411 2412 2413 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2411 def resources_consumed @resources_consumed end |
#service_account ⇒ String
The service account that the DeployedModel's container runs as. If not
specified, a system generated one will be used, which has minimal permissions
and the custom container, if used, may not have enough permission to access
other Google Cloud resources. Users deploying the Model must have the iam.
serviceAccounts.actAs permission on this service account.
Corresponds to the JSON property serviceAccount
2420 2421 2422 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2420 def service_account @service_account end |
#start_time ⇒ String
Output only. Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING state.
Corresponds to the JSON property startTime
2426 2427 2428 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2426 def start_time @start_time end |
#state ⇒ String
Output only. The detailed state of the job.
Corresponds to the JSON property state
2431 2432 2433 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2431 def state @state end |
#unmanaged_container_model ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1UnmanagedContainerModel
Contains model information necessary to perform batch prediction without
requiring a full model import.
Corresponds to the JSON property unmanagedContainerModel
2437 2438 2439 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2437 def unmanaged_container_model @unmanaged_container_model end |
#update_time ⇒ String
Output only. Time when the BatchPredictionJob was most recently updated.
Corresponds to the JSON property updateTime
2442 2443 2444 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2442 def update_time @update_time end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 2449 def update!(**args) @completion_stats = args[:completion_stats] if args.key?(:completion_stats) @create_time = args[:create_time] if args.key?(:create_time) @dedicated_resources = args[:dedicated_resources] if args.key?(:dedicated_resources) @disable_container_logging = args[:disable_container_logging] if args.key?(:disable_container_logging) @display_name = args[:display_name] if args.key?(:display_name) @encryption_spec = args[:encryption_spec] if args.key?(:encryption_spec) @end_time = args[:end_time] if args.key?(:end_time) @error = args[:error] if args.key?(:error) @explanation_spec = args[:explanation_spec] if args.key?(:explanation_spec) @generate_explanation = args[:generate_explanation] if args.key?(:generate_explanation) @input_config = args[:input_config] if args.key?(:input_config) @instance_config = args[:instance_config] if args.key?(:instance_config) @labels = args[:labels] if args.key?(:labels) @manual_batch_tuning_parameters = args[:manual_batch_tuning_parameters] if args.key?(:manual_batch_tuning_parameters) @model = args[:model] if args.key?(:model) @model_monitoring_config = args[:model_monitoring_config] if args.key?(:model_monitoring_config) @model_monitoring_stats_anomalies = args[:model_monitoring_stats_anomalies] if args.key?(:model_monitoring_stats_anomalies) @model_monitoring_status = args[:model_monitoring_status] if args.key?(:model_monitoring_status) @model_parameters = args[:model_parameters] if args.key?(:model_parameters) @model_version_id = args[:model_version_id] if args.key?(:model_version_id) @name = args[:name] if args.key?(:name) @output_config = args[:output_config] if args.key?(:output_config) @output_info = args[:output_info] if args.key?(:output_info) @partial_failures = args[:partial_failures] if args.key?(:partial_failures) @resources_consumed = args[:resources_consumed] if args.key?(:resources_consumed) @service_account = args[:service_account] if args.key?(:service_account) @start_time = args[:start_time] if args.key?(:start_time) @state = args[:state] if args.key?(:state) @unmanaged_container_model = args[:unmanaged_container_model] if args.key?(:unmanaged_container_model) @update_time = args[:update_time] if args.key?(:update_time) end |