feature

Type Members

1. class WeightHotEncoderEstimator extends Estimator[WeightHotEncoderModel] with WeightHotEncoderBase with DefaultParamsWritable

   

   A weighted one-hot encoder that maps a column of category indices to a column of vectors, with at most a single weight value per row that indicates the input category index.

   A weighted one-hot encoder that maps a column of category indices to a column of vectors, with at most a single weight value per row that indicates the input category index. For example with 5 categories and a weight of 0.3, an input value of 2.0 would map to an output vector of [0.0, 0.0, 0.3, 0.0]. The last category is not included by default (configurable via dropLast), because it makes the vector entries linearly dependent. So an input value of 4.0 maps to [0.0, 0.0, 0.0, 0.0].

   When handleInvalid is configured to 'keep', an extra "category" indicating invalid values is added as last category. So when dropLast is true, invalid values are encoded as all-zeros vector.

   A group encoding is also possible. In this case there can be multiple weight values, with one weight value per row of the group. All rows of a group have the same vector. The weight values of a group can further be weighted by the group size.

   Annotations

   @Since( "2.3.0" )

   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.

   See also

   StringIndexer for converting categorical values into category indices

2. class WeightHotEncoderModel extends Model[WeightHotEncoderModel] with WeightHotEncoderBase with MLWritable

   
   Annotations

   @Since( "2.3.0" )