kumoai.pquery.TrainingTableGenerationPlan#

class kumoai.pquery.TrainingTableGenerationPlan[source]#

Configuration parameters that define the construction of a Kumo training table from a predictive query. Please see the Kumo documentation for more information.

Variables:

  • split – (str) A custom split that is used to generate a training, validation, and test set in the training table (default: "inferred"). Supported Task Types: All

  • train_start_offset – (int | "inferred”) Defines the numerical offset from the most recent entry to use to generate training data labels. Unless a custom time unit is specified in the aggregation, this value is in days (default: "inferred"). Eventually we would like to migrate this parameter to start_time. Supported Task Types: Temporal

  • train_end_offset – (int | "inferred") Defines the numerical offset from the most recent entry to not use to generate training data labels. Unless a custom time unit is specified in the aggregation, this value is in days (default: "inferred"). Eventually we would like to migrate this parameter to end_time. Supported Task Types: Temporal

  • start_time – (int | "inferred" | str) Defines the absolute start time to use for generating training data. Can be specified either as a pandas Timestamp compatible string (e.g. ‘2024-04-01’) or as a non-positive integer offset in days from the current time (e.g. -30 for 30 days ago) (default: "inferred"). Supported Task Types: Temporal

  • end_time – (int | "inferred" | str) Defines the absolute end time to use for generating training data. Can be specified either as a pandas Timestamp compatible string (e.g. ‘2024-04-01’) or as a non-positive integer offset in days from the current time (e.g. -30 for 30 days ago) (default: "inferred"). Supported Task Types: Temporal

  • timeframe_step – (int | "inferred") Defines the step size of generating time intervals for training table generation (default: "inferred"). Supported Task Types: Temporal

  • forecast_length – (int) Turns a node regression problem into a forecasting problem (default: "missing"). Supported Task Types: Temporal Regression

  • lag_timesteps – (int) For forecasting problems, leverage the auto-regressive labels as inputs. This parameter controls the number of previous values that should be considered as auto-regressive labels (default: "missing"). Supported Task Types: Temporal Regression

  • year_over_year – (bool) For forecasting problems, integrate Year-Over-Year features as inputs to give more attention to the data from the previous year when making a prediction. (default: "missing")