
为模型训练准备数据集
|
223
s3_client.upload_file(flow_file_name, bucket,
f"{prefix}/{flow_name}.flow")
pipeline_name = f"datawrangler-pipeline-{int(time.time() * 10**7)}"
instance_type = ParameterString(name="InstanceType",
default_value="ml.m5.4xlarge")
instance_count = ParameterInteger(name="InstanceCount",
default_value=1)
step_process = Step(
name="DataWranglerProcessingStep",
step_type=StepTypeEnum.PROCESSING,
step_args=processing_job_arguments
)
pipeline = Pipeline(
name=pipeline_name,
parameters=[instance_type, instance_count],
steps=[step_process],
sagemaker_session=sess
)
pipeline.create(role_arn=role) ...