AccuracyMeasure

class hana_ai.tools.hana_ml_tools.ts_accuracy_measure_tools.AccuracyMeasure(connection_context: ConnectionContext, return_direct: bool = False)

This tool calculates the accuracy measure for the time series forecast.

Parameters:

connection_contextConnectionContext

Connection context to the HANA database.

Returns:

str

The accuracy measure result in JSON format.

Note

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

Field	Description
predict_table	The name of the prediction result table.
actual_table	The name of the actual result table.
predict_key	The key column name of the prediction result.
actual_key	The key column name of the actual result.
predict_target	The target column name of the prediction result.
actual_target	The target column name of the actual result.
predict_schema	The schema of the prediction table, it is optional
actual_schema	The schema of the actual table, it is optional
evaluation_metric	The accuracy measures to compute. It could be one or a list of the following options: 'mpe', 'mse', 'rmse', 'et', 'mad', 'mase', 'wmape', 'smape', 'mape' and 'spec'.
ignore_zero	Specifies whether or not to ignore zero values when calculating accuracy measure 'mpe' or 'mape'. It is optional.
alpha2	Specifies the unit stock-keeping cost parameter of accuracy measure 'spec'.
alpha1	Specifies the unit opportunity cost parameter of accuracy measure 'spec'.

name: str

Name of the tool.

description: str

Description of the tool.

connection_context: ConnectionContext

Connection context to the HANA database.