Package org.apache.spark.ml.feature

Class TargetEncoder

Object
org.apache.spark.ml.PipelineStage
org.apache.spark.ml.Estimator<TargetEncoderModel>
org.apache.spark.ml.feature.TargetEncoder
All Implemented Interfaces:
Serializable, org.apache.spark.internal.Logging, TargetEncoderBase, Params, HasHandleInvalid, HasInputCol, HasInputCols, HasLabelCol, HasOutputCol, HasOutputCols, DefaultParamsWritable, Identifiable, MLWritable
public class TargetEncoder extends Estimator<TargetEncoderModel> implements TargetEncoderBase, DefaultParamsWritable
Target Encoding maps a column of categorical indices into a numerical feature derived from the target.

When handleInvalid is configured to 'keep', previously unseen values of a feature are mapped to the dataset overall statistics.

When 'targetType' is configured to 'binary', categories are encoded as the conditional probability of the target given that category (bin counting). When 'targetType' is configured to 'continuous', categories are encoded as the average of the target given that category (mean encoding)

Parameter 'smoothing' controls how in-category stats and overall stats are weighted.

See Also:
  • StringIndexer for converting categorical values into category indices
  • Serialized Form
Note:
When encoding multi-column by using inputCols and outputCols params, input/output cols come in pairs, specified by the order in the arrays, and each pair is treated independently.

  • Constructor Details

    • TargetEncoder

      public TargetEncoder(String uid)

    • TargetEncoder

      public TargetEncoder()

  • Method Details

    • load

      public static TargetEncoder load(String path)

    • read

      public static MLReader<T> read()

    • handleInvalid

      public Param<String> handleInvalid()
      Description copied from interface: TargetEncoderBase
      Param for how to handle invalid data during transform(). Options are 'keep' (invalid data presented as an extra categorical feature) or 'error' (throw an error). Note that this Param is only used during transform; during fitting, invalid data will result in an error. Default: "error"
      Specified by:
      handleInvalid in interface HasHandleInvalid
      Specified by:
      handleInvalid in interface TargetEncoderBase
      Returns:
      (undocumented)

    • targetType

      public Param<String> targetType()
      Specified by:
      targetType in interface TargetEncoderBase

    • smoothing

      public DoubleParam smoothing()
      Specified by:
      smoothing in interface TargetEncoderBase

    • outputCols

      public final StringArrayParam outputCols()
      Description copied from interface: HasOutputCols
      Param for output column names.
      Specified by:
      outputCols in interface HasOutputCols
      Returns:
      (undocumented)

    • outputCol

      public final Param<String> outputCol()
      Description copied from interface: HasOutputCol
      Param for output column name.
      Specified by:
      outputCol in interface HasOutputCol
      Returns:
      (undocumented)

    • inputCols

      public final StringArrayParam inputCols()
      Description copied from interface: HasInputCols
      Param for input column names.
      Specified by:
      inputCols in interface HasInputCols
      Returns:
      (undocumented)

    • inputCol

      public final Param<String> inputCol()
      Description copied from interface: HasInputCol
      Param for input column name.
      Specified by:
      inputCol in interface HasInputCol
      Returns:
      (undocumented)

    • labelCol

      public final Param<String> labelCol()
      Description copied from interface: HasLabelCol
      Param for label column name.
      Specified by:
      labelCol in interface HasLabelCol
      Returns:
      (undocumented)

    • uid

      public String uid()
      Description copied from interface: Identifiable
      An immutable unique ID for the object and its derivatives.
      Specified by:
      uid in interface Identifiable
      Returns:
      (undocumented)

    • setLabelCol

      public TargetEncoder setLabelCol(String value)

    • setInputCol

      public TargetEncoder setInputCol(String value)

    • setOutputCol

      public TargetEncoder setOutputCol(String value)

    • setInputCols

      public TargetEncoder setInputCols(String[] values)

    • setOutputCols

      public TargetEncoder setOutputCols(String[] values)

    • setHandleInvalid

      public TargetEncoder setHandleInvalid(String value)

    • setTargetType

      public TargetEncoder setTargetType(String value)

    • setSmoothing

      public TargetEncoder setSmoothing(double value)

    • transformSchema

      public StructType transformSchema(StructType schema)
      Description copied from class: PipelineStage
      Check transform validity and derive the output schema from the input schema.

      We check validity for interactions between parameters during transformSchema and raise an exception if any parameter value is invalid. Parameter value checks which do not depend on other parameters are handled by Param.validate().

      Typical implementation should first conduct verification on schema change and parameter validity, including complex parameter interaction checks.

      Specified by:
      transformSchema in class PipelineStage
      Parameters:
      schema - (undocumented)
      Returns:
      (undocumented)

    • fit

      public TargetEncoderModel fit(Dataset<?> dataset)
      Description copied from class: Estimator
      Fits a model to the input data.
      Specified by:
      fit in class Estimator<TargetEncoderModel>
      Parameters:
      dataset - (undocumented)
      Returns:
      (undocumented)

    • copy

      public TargetEncoder copy(ParamMap extra)
      Description copied from interface: Params
      Creates a copy of this instance with the same UID and some extra params. Subclasses should implement this method and set the return type properly. See defaultCopy().
      Specified by:
      copy in interface Params
      Specified by:
      copy in class Estimator<TargetEncoderModel>
      Parameters:
      extra - (undocumented)
      Returns:
      (undocumented)