ReferenceForecast#

class ReferenceForecast(*, aggregate_reference_timesteps: bool = False, aggregation_time_window: str = '6 hours', aggregate_reference_timeseries: bool = False, df: DataFrame = None)[source]#

Model for generating a synthetic reference forecast timeseries.

Parameters:

  • aggregate_reference_timeseries (bool) – Whether to aggregate the reference timeseries. Defaults to False.

  • aggregation_time_window (str) – The time window for aggregation. Defaults to “6 hours”.

  • df (ps.DataFrame) – The DataFrame containing the timeseries data.

Notes

This model generates a synthetic reference forecast timeseries based on an input timeseries DataFrame. It assigns the values from the input timeseries to the forecast timeseries based on value time, optionally aggregrating values within a specified time window.

This requires specific timeseries to work with.

Methods

generate

Generate synthetic reference forecast timeseries.

Attributes

model_computed_fields

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_extra

Get extra fields set during validation.

model_fields

model_fields_set

Returns the set of fields that have been explicitly set on this model instance.

aggregate_reference_timeseries

aggregation_time_window

df

aggregate_reference_timesteps

generate(ev: Evaluation, reference_sdf: DataFrame, template_sdf: DataFrame, partition_by: List[str], output_configuration_name: str) → DataFrame[source]#

Generate synthetic reference forecast timeseries.

Parameters:

  • ev (Evaluation) – The Evaluation object containing the evaluation context.

  • reference_sdf (ps.DataFrame) – The DataFrame containing the reference timeseries data.

  • template_sdf (ps.DataFrame) – The DataFrame containing the template forecast timeseries data.

  • partition_by (List[str]) – The list of columns to partition by when aggregating the time step.

  • output_configuration_name (str) – The configuration name to assign to the output timeseries.

Returns:

ps.DataFrame – The DataFrame containing the generated reference forecast timeseries.