IntermittentForecast

class hana_ai.tools.hana_ml_tools.intermittent_forecast_tools.IntermittentForecast(connection_context: ConnectionContext, return_direct: bool = False)

This tool generates forecast for the intermittent demand dataset.

Parameters:

connection_contextConnectionContext

Connection context to the HANA database.

Returns:

str

The name of the predicted result table and the statistics of the forecast.

Note

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

Field	Description
table_name	the name of the table. If not provided, ask the user. Do not guess.
key	the key of the dataset. If not provided, ask the user. Do not guess.
endog	the endog of the dataset. If not provided, ask the user. Do not guess.
alpha	Smoothing parameter for demand, it is optional
beta	Smoothing parameter for probability, it is optional
forecast_num	Number of values to be forecast, it is optional
method	Method to be used from sporadic or constant, it is optional
accuracy_measure	The metric to quantify how well a model fits input data. Options: 'mpe', 'mse', 'rmse', 'et', 'mad', 'mase', 'wmape', 'smape', 'mape'., it is optional
ignore_zero	Ignore zero values or not in the dataset and only valid when accuracy_measure is 'mpe' or 'mape'., it is optional
remove_leading_zeros	When it is set to True, the leading zeros are ignored for calculating measure, it is optional

name: str

Name of the tool.

description: str

Description of the tool.

connection_context: ConnectionContext

Connection context to the HANA database.