
mlr3pipelines - Preprocessing Operators and Pipelines for 'mlr3'
Dataflow programming toolkit that enriches 'mlr3' with a diverse set of pipelining operators ('PipeOps') that can be composed into graphs. Operations exist for data preprocessing, model fitting, and ensemble learning. Graphs can themselves be treated as 'mlr3' 'Learners' and can therefore be resampled, benchmarked, and tuned.
Last updated 8 days ago
baggingdata-sciencedataflow-programmingensemble-learningmachine-learningmlr3pipelinespreprocessingstacking
12.36 score 141 stars 7 dependents 448 scripts 5.0k downloadsparadox - Define and Work with Parameter Spaces for Complex Algorithms
Define parameter spaces, constraints and dependencies for arbitrary algorithms, to program on such spaces. Also includes statistical designs and random samplers. Objects are implemented as 'R6' classes.
Last updated 8 months ago
experimental-designhyperparametersmlr3transformations
11.56 score 29 stars 38 dependents 316 scripts 7.2k downloadsmlrintermbo - Model-Based Optimization for 'mlr3' Through 'mlrMBO'
The 'mlrMBO' package can ordinarily not be used for optimization within 'mlr3', because of incompatibilities of their respective class systems. 'mlrintermbo' offers a compatibility interface that provides 'mlrMBO' as an 'mlr3tuning' 'Tuner' object, for tuning of machine learning algorithms within 'mlr3', as well as a 'bbotk' 'Optimizer' object for optimization of general objective functions using the 'bbotk' black box optimization framework. The control parameters of 'mlrMBO' are faithfully reproduced as a 'paradox' 'ParamSet'.
Last updated 5 months ago
4.08 score 4 stars 12 scripts 634 downloads