Optimize#

class tpcp.optimize.Optimize(pipeline: OptimizablePipelineT, *, safe_optimize: bool = True, optimize_with_info: bool = True)[source]#

Run a generic self-optimization on the pipeline.

This is a simple wrapper for pipelines that already implement a self_optimize method. This wrapper can be used to ensure that these algorithms can be optimized with the same interface as other optimization methods and can hence be used in methods like tpcp.validate.cross_validate.

Optimize will never modify the original pipeline, but will store a copy of the optimized pipeline as optimized_pipeline_.

If safe_optimize is True, the wrapper applies the same runtime checks as provided by make_optimize_safe.

Parameters:

pipeline: The pipeline to optimize. The pipeline must implement self_optimize to optimize its own input parameters.
safe_optimize: If True, we add additional checks to make sure the self_optimize method of the pipeline is correctly implemented. See make_optimize_safe for more info.
optimize_with_info: If True, Optimize will try to call self_optimize_with_info by default and will fall back to self_optimize. If you want to force optimize to use self_optimize, even if an implementation of self_optimize_with_info exists, set this parameter to False.

Other Parameters:

dataset: The dataset used for optimization.

Attributes:

optimized_pipeline_: The optimized version of the pipeline. That is a copy of the input pipeline with modified params.
optimization_info_: If the optimized pipeline implements a self_optimize_with_info method, this parameter contains the additional information provided as second return value from this method.

Methods

`clone`()	Create a new instance of the class with all parameters copied over.
`get_params`([deep])	Get parameters for this algorithm.
`optimize`(dataset, **optimize_params)	Run the self-optimization defined by the pipeline.
`run`(datapoint)	Run the optimized pipeline.
`safe_run`(datapoint)	Run the optimized pipeline.
`score`(datapoint)	Run score of the optimized pipeline.
`set_params`(**params)	Set the parameters of this Algorithm.

__init__(pipeline: OptimizablePipelineT, *, safe_optimize: bool = True, optimize_with_info: bool = True) → None[source]#

clone() → Self[source]#

Create a new instance of the class with all parameters copied over.

This will create a new instance of the class itself and all nested objects

get_params(deep: bool = True) → dict[str, Any][source]#

Get parameters for this algorithm.

Parameters:

deep: Only relevant if object contains nested algorithm objects. If this is the case and deep is True, the params of these nested objects are included in the output using a prefix like nested_object_name__ (Note the two “_” at the end)

Returns:

params: Parameter names mapped to their values.

optimize(dataset: DatasetT, **optimize_params: Any) → Self[source]#

Run the self-optimization defined by the pipeline.

The optimized version of the pipeline is stored as self.optimized_pipeline_.

Parameters:

dataset: An instance of a Dataset containing one or multiple data points that can be used for optimization. The structure of the data and the available reference information will depend on the dataset.
optimize_params: Additional parameter for the optimization process. They are forwarded to pipeline.self_optimize.

Returns: