/AWS1/CL_NED=>STARTMLDATAPROCESSINGJOB()
¶
About StartMLDataProcessingJob¶
Creates a new Neptune ML data processing job for processing the
graph data exported from Neptune for training. See The
dataprocessing
command.
When invoking this operation in a Neptune cluster that has IAM authentication enabled, the IAM user or role making the request must have a policy attached that allows the neptune-db:StartMLModelDataProcessingJob IAM action in that cluster.
Method Signature¶
IMPORTING¶
Required arguments:¶
IV_INPUTDATAS3LOCATION
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The URI of the Amazon S3 location where you want SageMaker to download the data needed to run the data processing job.
IV_PROCESSEDDATAS3LOCATION
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The URI of the Amazon S3 location where you want SageMaker to save the results of a data processing job.
Optional arguments:¶
IV_ID
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
A unique identifier for the new job. The default is an autogenerated UUID.
IV_PREVIOUSDATAPROCINGJOBID
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The job ID of a completed data processing job run on an earlier version of the data.
IV_SAGEMAKERIAMROLEARN
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The ARN of an IAM role for SageMaker execution. This must be listed in your DB cluster parameter group or an error will occur.
IV_NEPTUNEIAMROLEARN
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The Amazon Resource Name (ARN) of an IAM role that SageMaker can assume to perform tasks on your behalf. This must be listed in your DB cluster parameter group or an error will occur.
IV_PROCESSINGINSTANCETYPE
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The type of ML instance used during data processing. Its memory should be large enough to hold the processed dataset. The default is the smallest ml.r5 type whose memory is ten times larger than the size of the exported graph data on disk.
IV_PROCINGINSTVOLUMESIZEINGB
TYPE /AWS1/NEDINTEGER
/AWS1/NEDINTEGER
¶
The disk volume size of the processing instance. Both input data and processed data are stored on disk, so the volume size must be large enough to hold both data sets. The default is 0. If not specified or 0, Neptune ML chooses the volume size automatically based on the data size.
IV_PROCESSINGTMOUTINSECONDS
TYPE /AWS1/NEDINTEGER
/AWS1/NEDINTEGER
¶
Timeout in seconds for the data processing job. The default is 86,400 (1 day).
IV_MODELTYPE
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
One of the two model types that Neptune ML currently supports: heterogeneous graph models (
heterogeneous
), and knowledge graph (kge
). The default is none. If not specified, Neptune ML chooses the model type automatically based on the data.
IV_CONFIGFILENAME
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
A data specification file that describes how to load the exported graph data for training. The file is automatically generated by the Neptune export toolkit. The default is
training-data-configuration.json
.
IT_SUBNETS
TYPE /AWS1/CL_NEDSTRINGLIST_W=>TT_STRINGLIST
TT_STRINGLIST
¶
The IDs of the subnets in the Neptune VPC. The default is None.
IT_SECURITYGROUPIDS
TYPE /AWS1/CL_NEDSTRINGLIST_W=>TT_STRINGLIST
TT_STRINGLIST
¶
The VPC security group IDs. The default is None.
IV_VOLUMEENCRYPTIONKMSKEY
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The Amazon Key Management Service (Amazon KMS) key that SageMaker uses to encrypt data on the storage volume attached to the ML compute instances that run the training job. The default is None.
IV_S3OUTPUTENCRYPTIONKMSKEY
TYPE /AWS1/NEDSTRING
/AWS1/NEDSTRING
¶
The Amazon Key Management Service (Amazon KMS) key that SageMaker uses to encrypt the output of the processing job. The default is none.