## On this page

  

 

 # CreateSimpleTrainingPlan Class Reference

 Last update: 16.07.2025 

This class is used to create training plans for the [ScalarMOP](struct_scalar_m_o_p.xhtml "This is only a sketch of the possible ScalarMOPApproximate API Implementation shall be refined if mor...") competition. It sets up data according to an sample analysis to allow efficient training of the samples. It provides functions to access and cleanup the prepared data. [More...](class_create_simple_training_plan.xhtml#details)

## <a name="pub-methods"></a>Public Member Functions

 [cleanup](class_create_simple_training_plan.xhtml#aee46840a9742d1ef1acbcbc0a0558d6a) (data\_handler::DataHandlerBase datahandler, std::vector&lt; uint64\_t &gt; output\_map) Clean-up the datahandler once the data is not needed anymore. [More...](#aee46840a9742d1ef1acbcbc0a0558d6a)  
 [SimpleTrainingPlan](struct_simple_training_plan.xhtml) [compute](class_create_simple_training_plan.xhtml#a21378382fcea59d7dac4cc95d221b79a) (data\_handler::DataHandlerBase datahandler, std::vector&lt; uint64\_t &gt; output\_map, bool use\_incompletes=true, bool subspace\_filtering=true, bool input\_correlation\_filter=true, number maximum\_input\_correlation=0.9) Generates a [SimpleTrainingPlan](struct_simple_training_plan.xhtml "TrainingPlan assigns a in a set of sample each sample a status on how the sample is to be treated dur...") from the classes settings Instances of this class have the ability to cache adapted data inside the datahandler such that the resulting training plan can be used in an efficient way. This is triggered by the outputs for the training. [More...](#a21378382fcea59d7dac4cc95d221b79a)  
 <a id="adf28cf2efd51b035883ceb37db728a71"></a> [CreateSimpleTrainingPlan](class_create_simple_training_plan.xhtml#adf28cf2efd51b035883ceb37db728a71) () Constructor.   
 [Matrix](class_matrix.xhtml) [getInputs](class_create_simple_training_plan.xhtml#a3a0b3b5d7b78bf28baeb3687819720c3) (data\_handler::DataHandlerBase datahandler, std::vector&lt; uint64\_t &gt; output\_map) Return the input matrix used by the training plan [CreateSimpleTrainingPlan::compute](class_create_simple_training_plan.xhtml#a21378382fcea59d7dac4cc95d221b79a "Generates a SimpleTrainingPlan from the classes settings Instances of this class have the ability to ...") may cache efficient input matrices for the given outputs. This function provides access to the input matrices used for the given outputs. [More...](#a3a0b3b5d7b78bf28baeb3687819720c3)  
 <a id="aee74475a8bc2fdc6d1a0fed306f683b7"></a> [initialize](class_create_simple_training_plan.xhtml#aee74475a8bc2fdc6d1a0fed306f683b7) (data\_handler::DataHandlerBase datahandler) Initializes and precalculates the cached plan.   
 IndexVector [unusedSamples](class_create_simple_training_plan.xhtml#a6d765744e1b403aacd8ece89b42de38a) (std::vector&lt; uint64\_t &gt; output\_map, bool use\_incompletes) Returns the indices of samples that were left out of the training process for the given output\_map. [More...](#a6d765744e1b403aacd8ece89b42de38a)  
 ## <a name="pub-attribs"></a>Public Attributes

<a id="afff2ed8fc84ff999a9ff1b187dc4fe8a"></a>ParameterImportanceVector [input\_importances](class_create_simple_training_plan.xhtml#afff2ed8fc84ff999a9ff1b187dc4fe8a) The importances for the mops input variables.   
 <a id="a226a6b2dab6b0562cf399a3a1a0c9b9c"></a>string **mop\_ident** <a id="ae29a97cfbae42dc37b7a9be964b5d266"></a>int [number\_of\_folds](class_create_simple_training_plan.xhtml#ae29a97cfbae42dc37b7a9be964b5d266) The number of folds for a k-fold training.   
 <a id="a874a26feda81485f63f6bc9d791c8c86"></a>[TrainingPlanType](group__common.xhtml#ga8f73c0a2225e425c9ffeecb046034a43) [training](class_create_simple_training_plan.xhtml#a874a26feda81485f63f6bc9d791c8c86) The type of training plan to generate.   
 <a id="details" name="details"></a>## Detailed Description

This class is used to create training plans for the [ScalarMOP](struct_scalar_m_o_p.xhtml "This is only a sketch of the possible ScalarMOPApproximate API Implementation shall be refined if mor...") competition. It sets up data according to an sample analysis to allow efficient training of the samples. It provides functions to access and cleanup the prepared data.



## Member Function Documentation

<a id="aee46840a9742d1ef1acbcbc0a0558d6a"></a>## [◆ ](#aee46840a9742d1ef1acbcbc0a0558d6a)cleanup()

 cleanup  ( data\_handler::DataHandlerBase  *datahandler*,    std::vector&lt; uint64\_t &gt;  *output\_map*   ) 

Clean-up the datahandler once the data is not needed anymore.

Parameters datahandlerThe datahandler that keeps the data output\_mapThe outputs the datahandler keeps additional data for 



<a id="a21378382fcea59d7dac4cc95d221b79a"></a>## [◆ ](#a21378382fcea59d7dac4cc95d221b79a)compute()

 [SimpleTrainingPlan](struct_simple_training_plan.xhtml) compute  ( data\_handler::DataHandlerBase  *datahandler*,    std::vector&lt; uint64\_t &gt;  *output\_map*,    bool  *use\_incompletes* = `true`,    bool  *subspace\_filtering* = `true`,    bool  *input\_correlation\_filter* = `true`,    number  *maximum\_input\_correlation* = `0.9`   ) 

Generates a [SimpleTrainingPlan](struct_simple_training_plan.xhtml "TrainingPlan assigns a in a set of sample each sample a status on how the sample is to be treated dur...") from the classes settings Instances of this class have the ability to cache adapted data inside the datahandler such that the resulting training plan can be used in an efficient way. This is triggered by the outputs for the training.

Parameters datahandlerThe Datahandler that stores the input/output matrices. output\_mapThe output to create the training plan for use\_incompletesThe setting if incomplete designs should be used subspace\_filteringOptional subspace filtering input\_correlation\_filterOptional input correlation filtering maximum\_input\_correlationMaximum input correlation for optional filtering ReturnsA training plan 



<a id="a3a0b3b5d7b78bf28baeb3687819720c3"></a>## [◆ ](#a3a0b3b5d7b78bf28baeb3687819720c3)getInputs()

 [Matrix](class_matrix.xhtml) getInputs  ( data\_handler::DataHandlerBase  *datahandler*,    std::vector&lt; uint64\_t &gt;  *output\_map*   ) 

Return the input matrix used by the training plan [CreateSimpleTrainingPlan::compute](class_create_simple_training_plan.xhtml#a21378382fcea59d7dac4cc95d221b79a "Generates a SimpleTrainingPlan from the classes settings Instances of this class have the ability to ...") may cache efficient input matrices for the given outputs. This function provides access to the input matrices used for the given outputs.

Parameters datahandlerThe datahandler where the data is located output\_mapThe output\_map used ReturnsA reference to the input matrix for the given output\_map 



<a id="a6d765744e1b403aacd8ece89b42de38a"></a>## [◆ ](#a6d765744e1b403aacd8ece89b42de38a)unusedSamples()

 IndexVector unusedSamples  ( std::vector&lt; uint64\_t &gt;  *output\_map*,    bool  *use\_incompletes*   ) 

Returns the indices of samples that were left out of the training process for the given output\_map.

Parameters output\_mapThe outputs in question for the training use\_incompletesThe setting if incomplete designs should be used ReturnsAn ordered vector of indices of samples that were omitted during training.