- EncoderMethod
[Required]
- If the response variable is following a binary classification, for example, values are either 0 or 1, use EncoderMethod as CBM_BETA.
- If the response variable is following a multi-class classification, for example. values are (1,...,k, where k is the number of classes), use EncoderMethod as CBM_DIRICHLET.
- If the response variable is following a regression, for example, values are contiguous numeric values, use EncoderMethod as CBM_GAUSSIAN_INVERSE_GAMMA.
The maximum length supported is 128. Not case sensitive.
Tokens are CBM_BETA, CBM_DIRICHLET, and CBM_GAUSSIAN_INVERSE_GAMMA.
- TargetColumns
- [Required] Specify the column from the InputTable that contains the categorical values to be encoded. The maximum length supported is 128. The maximum list length is 2018. Not case sensitive.
- ResponseColumn
- [Required] Specify column from the InputTable that contains the response values. The maximum length supported is 128. Not case sensitive.
- AlphaPrior
- [Optional] Specify the prior parameter of the CBM_BETA encoder method.
- BetaPrior
- [Optional] Specify the prior parameter of the CBM_BETA encoder method.
- AlphaPriors
- [Optional] Specify the prior parameter of the CBM_DIRICHLET encoder method. The number of values specified in this argument must be equal to the NumDistinctResponses value. The maximum list length is 2018.
- NumDistinctResponses
- Required if EncoderMethod is 'CBM_DIRICHLET', otherwise optional. Specify the number of distinct values present in ResponseColumn.
- U0Prior
- [Optional] Specify the prior parameter of the CBM_GAUSSIAN_INVERSE_GAMMA encoder method.
- V0Prior
- [Optional] Specify the prior parameter of the CBM_GAUSSIAN_INVERSE_GAMMA encoder method.
- Alpha0Prior
- [Optional] Specify the prior parameter of the CBM_GAUSSIAN_INVERSE_GAMMA encoder method.
- Beta0Prior
- [Optional] Specify the prior parameter of the CBM_GAUSSIAN_INVERSE_GAMMA encoder method.
- DefaultValues
- [Optional] Specify the values to use when the category is not found during transform. If only one value is specified, it will be applied to all the target columns, otherwise the number of default values must be equal to the number of target columns. The maximum list length is 2018.