AdditiveModelForecastFitAndSave

class hana_ai.tools.hana_ml_tools.additive_model_forecast_tools.AdditiveModelForecastFitAndSave(connection_context: ConnectionContext, return_direct: bool = False)

This tool is used to fit and predict the additive model forecast.

Parameters:

connection_contextConnectionContext

Connection context to the HANA database.

Returns:

str

The result string containing the training table name, model storage name, and model storage version.

Note

args_schema is used to define the schema of the inputs as follows:

Field	Description
fit_table	The name of the table containing the training data.
fit_schema	The schema of the fit_table, it is optional.
key	The key column in the training table.
endog	The endogenous variable column in the training table.
exog	External regressors to include in the model.
holiday_table	The name of the table containing holiday data, it is optional.
holiday_schema	The schema of the holiday_table, it is optional.
name	The name of the model to save.
version	The version of the model to save.
categorical_variable	The categorical variable columns in the training table.
growth	The growth of the model chosen from {'linear', 'logistic'}.
logistic_growth_capacity	The logistic growth capacity of the model only valid when growth is 'logistic'.
seasonality_mode	The seasonality mode of the model chosen from {'additive', 'multiplicative'}.
period	The period of the seasonality or a list of periods.
num_changepoints	The number of changepoints in the model.
changepoint_range	The proportion of history in which trend changepoints will be estimated.
regressor	Specifies the regressor in a list of json such that ['{"NAME": "X1", "PRIOR_SCALE":4, "MODE": "additive" }'].
changepoints	Specifies a list of changepoints in the format of timestamp, such as ['2019-01-01 00:00:00, '2019-02-04 00:00:00'].
yearly_seasonality	Specifies whether or not to fit yearly seasonality chosen from {'auto', 'false', 'true'}.
weekly_seasonality	Specifies whether or not to fit weekly seasonality chosen from {'auto', 'false', 'true'}.
daily_seasonality	Specifies whether or not to fit daily seasonality chosen from {'auto', 'false', 'true'}.
seasonality_prior_scale	The parameter modulating the strength of the seasonality model.
holiday_prior_scale	The parameter modulating the strength of the holiday model.
changepoint_prior_scale	The parameter modulating the flexibility of the automatic changepoint selection.

name: str

Name of the tool.

description: str

Description of the tool.

connection_context: ConnectionContext

Connection context to the HANA database.