AutoMLChannel ¶

class AutoMLChannel(TypedDict, closed=True):
    data_source: NotRequired[
        "capo_sagemaker.types.auto_ml_data_source.AutoMLDataSource"
    ]
    """<p>The data source for an AutoML channel.</p>"""
    compression_type: NotRequired[
        "capo_sagemaker.types.compression_type.CompressionType"
    ]
    """<p>You can use <code>Gzip</code> or <code>None</code>. The default value is <code>None</code>.</p>"""
    target_attribute_name: NotRequired[
        "capo_sagemaker.types.target_attribute_name.TargetAttributeName"
    ]
    """<p>The name of the target variable in supervised learning, usually represented by 'y'.</p>"""
    content_type: NotRequired["capo_sagemaker.types.content_type.ContentType"]
    """<p>The content type of the data from the input source. You can use <code>text/csv;header=present</code> or <code>x-application/vnd.amazon+parquet</code>. The default value is <code>text/csv;header=present</code>.</p>"""
    channel_type: NotRequired[
        "capo_sagemaker.types.auto_ml_channel_type.AutoMLChannelType"
    ]
    """<p>The channel type (optional) is an <code>enum</code> string. The default value is <code>training</code>. Channels for training and validation must share the same <code>ContentType</code> and <code>TargetAttributeName</code>. For information on specifying training and validation channel types, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-datasets-problem-types.html#autopilot-data-sources-training-or-validation">How to specify training and validation datasets</a>.</p>"""
    sample_weight_attribute_name: NotRequired[
        "capo_sagemaker.types.sample_weight_attribute_name.SampleWeightAttributeName"
    ]
    """<p>If specified, this column name indicates which column of the dataset should be treated as sample weights for use by the objective metric during the training, evaluation, and the selection of the best model. This column is not considered as a predictive feature. For more information on Autopilot metrics, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-metrics-validation.html">Metrics and validation</a>.</p> <p>Sample weights should be numeric, non-negative, with larger values indicating which rows are more important than others. Data points that have invalid or no weight value are excluded.</p> <p>Support for sample weights is available in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_AutoMLAlgorithmConfig.html">Ensembling</a> mode only.</p>"""