Executes an training job https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.trainingPipelines/create

Executes an training job https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.trainingPipelines/create

gcva_run_job(
  projectId = gcva_project_get(),
  locationId = gcva_region_get(),
  baseOutputDir = gcva_bucket_get(),
  job,
  dataset,
  targetColumn = NULL,
  trainingFractionSplit = 0.8,
  validationFractionSplit = 0.1,
  testFractionSplit = 0.1,
  modelDisplayName,
  disableEarlyStopping = FALSE,
  machineType = NULL,
  sync = TRUE
)

Arguments

projectId

GCP project id

locationId

location of GCP resources

job

a job object of: "gcva_automlTabularTrainingJob" OR TBD

dataset

a vertex ai dataset object with class "gcva_dataset"

targetColumn

STRING full column name of the model target

trainingFractionSplit

decimal, percentage of dataset to use for training model during training

validationFractionSplit

decimal, percentage of dataset to use for validating model during training

testFractionSplit

decimal, percentage of dataset to use for testing model during training

modelDisplayName

display name of the model

disableEarlyStopping

disable early stopping default FALSE

sync

If set to TRUE, the call will block while waiting for the asynchronous batch job to complete.

Value

trainingPipeline object