Table
data class TableVerticalFeaturizationSettingsArgs(val blockedTransformers: Output<List<Either<String, BlockedTransformers>>>? = null, val columnNameAndTypes: Output<Map<String, String>>? = null, val datasetLanguage: Output<String>? = null, val enableDnnFeaturization: Output<Boolean>? = null, val mode: Output<Either<String, FeaturizationMode>>? = null, val transformerParams: Output<Map<String, List<ColumnTransformerArgs>>>? = null) : ConvertibleToJava<TableVerticalFeaturizationSettingsArgs>
Featurization Configuration.
Constructors
Link copied to clipboard
constructor(blockedTransformers: Output<List<Either<String, BlockedTransformers>>>? = null, columnNameAndTypes: Output<Map<String, String>>? = null, datasetLanguage: Output<String>? = null, enableDnnFeaturization: Output<Boolean>? = null, mode: Output<Either<String, FeaturizationMode>>? = null, transformerParams: Output<Map<String, List<ColumnTransformerArgs>>>? = null)
Properties
Link copied to clipboard
These transformers shall not be used in featurization.
Link copied to clipboard
Dictionary of column name and its type (int, float, string, datetime etc).
Link copied to clipboard
Dataset language, useful for the text data.
Link copied to clipboard
Determines whether to use Dnn based featurizers for data featurization.
Link copied to clipboard
Featurization mode - User can keep the default 'Auto' mode and AutoML will take care of necessary transformation of the data in featurization phase. If 'Off' is selected then no featurization is done. If 'Custom' is selected then user can specify additional inputs to customize how featurization is done.
Link copied to clipboard
User can specify additional transformers to be used along with the columns to which it would be applied and parameters for the transformer constructor.