Assessment modules¶
Benchmark Assessments definition¶
-
class
orion.benchmark.assessment.
BaseAssess
(task_num, **kwargs)[source]¶ Base class describing what an assessment can do.
Parameters: - task_num : int
Number of experiment the assessment ask to run the corresponding task
- kwargs : dict
Configurable parameters of the assessment, a particular assessment implementation can have its own parameters.
Attributes: configuration
Return the configuration of the assessment.
task_num
Return the task number to run for this assessment
Methods
analysis
(task, experiments)Generate a plotly.graph_objects.Figure
to display the performance analysis based on the assessment purpose.-
analysis
(task, experiments)[source]¶ Generate a
plotly.graph_objects.Figure
to display the performance analysis based on the assessment purpose.- task: str
- Name of the task
- experiments: list
- A list of (task_index, experiment), where task_index is the index of task to run for
this assessment, and experiment is an instance of
orion.core.worker.experiment
.
-
configuration
¶ Return the configuration of the assessment.
-
task_num
¶ Return the task number to run for this assessment
-
class
orion.benchmark.assessment.
AverageRank
(task_num=1)[source]¶ Evaluate the average performance (objective value) between different search algorithms from the rank perspective at different time steps (trial number). The performance (objective value) used for a trial will the best result until the trial.
Methods
analysis
(task, experiments)Generate a plotly.graph_objects.Figure
to display average rankings between different search algorithms.-
analysis
(task, experiments)[source]¶ Generate a
plotly.graph_objects.Figure
to display average rankings between different search algorithms.- task: str
- Name of the task
- experiments: list
- A list of (task_index, experiment), where task_index is the index of task to run for
this assessment, and experiment is an instance of
orion.core.worker.experiment
.
-
-
class
orion.benchmark.assessment.
AverageResult
(task_num=1)[source]¶ Evaluate the average performance (objective value) for each search algorithm at different time steps (trial number). The performance (objective value) used for a trial will the best result until the trial.
Methods
analysis
(task, experiments)Generate a plotly.graph_objects.Figure
to display average performance for each search algorithm.-
analysis
(task, experiments)[source]¶ Generate a
plotly.graph_objects.Figure
to display average performance for each search algorithm.- task: str
- Name of the task
- experiments: list
- A list of (task_index, experiment), where task_index is the index of task to run for
this assessment, and experiment is an instance of
orion.core.worker.experiment
.
-