rohe_reports

qoa4ml.reports.rohe_reports

Classes

RoheReport

RoheReport manages the reporting of metrics and inference data for a specific application.

Parameters:

Name	Type	Description	Default
client_config	ClientInfo	Configuration settings related to the client.	required

Attributes:

Name	Type	Description
client_config	ClientInfo	A deep copy of the client configuration.
init_time	float	The initialization time of the report.
previous_report	list[RoheReportModel]	A list of previously processed reports.
inference_report	EnsembleInferenceReport	The current inference report.
execution_graph	ExecutionGraph	The current execution graph.
report	RoheReportModel	The current state of the report.
previous_microservice_instance	list[MicroserviceInstance]	List of previous microservice instances.
execution_instance	MicroserviceInstance	An instance representing the current execution context.

Methods:

Name	Description
reset	Reset the report to an initial state.
import_report_from_file	Import a report from a specified file path.
combine_stage_report	Combine metrics from the current and previous stage reports.
process_previous_report	Process and incorporate a previous report.
build_execution_graph	Build the execution graph for the current report.
observe_metric	Observe and record a metric.
observe_inference	Observe and record inference data.
observe_inference_metric	Observe and record an inference-specific metric.
generate_report	Generate the report and optionally reset the current report state.

Functions

__init__(client_config)

Initialize an instance of RoheReport.

Parameters:

Name	Type	Description	Default
client_config	ClientInfo	Configuration settings related to the client.	required

build_execution_graph()

Build the execution graph for the current report.

Notes

• Creates a new endpoint in the execution graph linking to previous microservice instances.

combine_stage_report(current_stage_report, previous_stage_report)

Combine metrics from the current and previous stage reports.

Parameters:

Name	Type	Description	Default
current_stage_report	dict	The current stage report containing metrics.	required
previous_stage_report	dict	The previous stage report containing metrics.	required

Returns:

Type	Description
dict	Combined stage report containing metrics from both reports.

generate_report(reset=True, corr_id=None)

Generate the report and optionally reset the current report state.

Parameters:

Name	Type	Description	Default
reset	bool	Whether to reset the report state after generating the report, default is True.	True
corr_id	Optional[str]	Correlation ID for the report, default is None.	None

Returns:

Type	Description
RoheReportModel	The generated report.

Notes

• Adds metadata such as client configuration, timestamp, and runtime to the report.
• Builds the execution graph and deep copies the current state of the report before optionally resetting it.

import_report_from_file(file_path)

Import a report from a specified file path.

Parameters:

Name	Type	Description	Default
file_path	str	The path to the file containing the report data.	required

Notes

• The imported report updates the current inference report and execution graph.

observe_inference(inference_value)

Observe and record inference data.

Parameters:

Name	Type	Description	Default
inference_value	Any	The value of the inference to be recorded.	required

Notes

• If an inference endpoint already exists, the prediction value is updated.
• Otherwise, a new inference endpoint is created in the inference report.

observe_inference_metric(metric)

Observe and record an inference-specific metric.

Parameters:

Name	Type	Description	Default
metric	Metric	The inference-specific metric to be recorded.	required

Notes

• If an inference endpoint already exists, the metric is appended to the existing metrics.
• Otherwise, a new inference endpoint is created and the metric is added to it.

observe_metric(report_type, stage, metric)

Observe and record a metric.

Parameters:

Name	Type	Description	Default
report_type	ReportTypeEnum	The type of report being generated.	required
stage	str	The stage of the process in which the metric is recorded.	required
metric	Metric	The metric to be recorded.	required

Raises:

Type	Description
ValueError	If the stage name is empty or the report type is not handled.

process_previous_report(previous_report_dict)

Process and incorporate a previous report.

Parameters:

Name	Type	Description	Default
previous_report_dict	dict	Dictionary representation of a previous report.	required

Notes

• Raises a ValueError if the previous report is empty.
• Service quality, data quality, ML-specific quality reports, and execution graphs are combined with the current report.

reset()

Reset the report to an initial state.

Notes

• This method initializes a new report model and clears the list of previous reports.
• It also resets the inference report, execution graph, and execution instance.

Functions