AutoMLChannel

A channel is a named input source that training algorithms can consume. The validation dataset size is limited to less than 2 GB. The training dataset size must be less than 100 GB. For more information, see Channel.

Note

A validation dataset must contain the same headers as the training dataset.

ChannelType

The channel type (optional) is an enum string. The default value is training. Channels for training and validation must share the same ContentType and TargetAttributeName. For information on specifying training and validation channel types, see How to specify training and validation datasets.

Type: String

Valid Values: training | validation

Required: No

CompressionType

You can use Gzip or None. The default value is None.

Type: String

Valid Values: None | Gzip

Required: No

ContentType

The content type of the data from the input source. You can use text/csv;header=present or x-application/vnd.amazon+parquet. The default value is text/csv;header=present.

Type: String

Length Constraints: Maximum length of 256.

Pattern: .*

Required: No

DataSource

The data source for an AutoML channel.

Type: AutoMLDataSource object

Required: Yes

TargetAttributeName

The name of the target variable in supervised learning, usually represented by 'y'.

Type: String

Length Constraints: Minimum length of 1.

Required: Yes

AutoMLChannel

Contents

See Also