kumoai.Stype#

class kumoai.Stype[source]#

Bases: StrEnum

The semantic type of a column.

A semantic type denotes the semantic meaning of a column, and determines the preprocessing that is applied to the column. Semantic types can be passed to methods in the SDK as strings (e.g. "numerical").

Note

For more information about how to select a semantic type, please refer to https://docs.kumo.ai/docs/column-preprocessing.

numerical#

A numerical column. Typically integers or floats.

categorical#

A categorical column. Typically boolean or string values typically a single token in length.

multicategorical#

A multi-categorical column. Typically a concatenation of multiple categories under a single string representation.

ID#

A column holding IDs. Typically numerical values used to uniquely identify different entities.

text#

A text column. String values typically multiple tokens in length, where the actual language content of the value has semantic meaning.

timestamp#

A date/time column.

sequence#

A column holding sequences/embeddings. Consists of lists of floats, all of equal length, and are typically the output of another AI model

image#

A column holding image URLs.