def pipeline():
dataset_create_op = TabularDatasetCreateOp(
project=self._project,
display_name=self._display_name,
gcs_source=self._gcs_source,
)
training_job_run_op = AutoMLTabularTrainingJobRunOp(
project=self._project,
display_name=self._display_name,
optimization_prediction_type="regression",
optimization_objective="minimize-rmse",
column_transformations=[
{
"numeric": {
"column_name": "longitude"
}
},
],
target_column="longitude",
dataset=dataset_create_op.outputs["dataset"],
)
dataset_export_op = TabularDatasetExportDataOp(
project=self._project,
dataset=dataset_create_op.outputs["dataset"],
output_dir=self._gcs_output_dir,
)
def pipeline():
dataset_create_op = TabularDatasetCreateOp(
project=self._project,
display_name=self._display_name,
gcs_source=self._gcs_source,
)
training_job_run_op = AutoMLTabularTrainingJobRunOp(
project=self._project,
display_name=self._display_name,
optimization_prediction_type='regression',
optimization_objective='minimize-rmse',
column_transformations=[
{
"numeric": {
"column_name": "longitude"
}
},
],
target_column="longitude",
dataset=dataset_create_op.outputs["dataset"],
)
model_deploy_op = ModelDeployOp(
project=self._project,
model=training_job_run_op.outputs["model"]
)
batch_predict_op = ModelBatchPredictOp(
project=self._project,
model=training_job_run_op.outputs["model"],
job_display_name=self._display_name,
gcs_source=self._gcs_source,
gcs_destination_prefix=self._gcs_destination_prefix,
)
dataset_export_op = TabularDatasetExportDataOp(
project=self._project,
dataset=dataset_create_op.outputs["dataset"],
output_dir=self._gcs_output_dir,
)