Jakob Bossek

Jakob Bossek

16 packages on CRAN

cmaesr

cran
99.99th

Percentile

Pure R implementation of the Covariance Matrix Adaptation - Evolution Strategy (CMA-ES) with optional restarts (IPOP-CMA-ES).

ecr

cran
99.99th

Percentile

Framework for building evolutionary algorithms for both single- and multi-objective continuous or discrete optimization problems. A set of predefined evolutionary building blocks and operators is included. Moreover, the user can easily set up custom objective functions, operators, building blocks and representations sticking to few conventions. The package allows both a black-box approach for standard tasks (plug-and-play style) and a much more flexible white-box approach where the evolutionary cycle is written by hand.

99.99th

Percentile

Set of functions for step-wise generation of (weighted) graphs. Aimed for research in the field of single- and multi-objective combinatorial optimization. Graphs are generated adding nodes, edges and weights. Each step may be repeated multiple times with different predefined and custom generators resulting in high flexibility regarding the graph topology and structure of edge weights.

mcMST

cran
99.99th

Percentile

Algorithms to approximate the Pareto-front of multi-criteria minimum spanning tree problems. Additionally, a modular toolbox for the generation of multi-objective benchmark graph problems is included.

netgen

cran
99.99th

Percentile

Methods for the generation of a wide range of network geographies, e.g., grid networks or clustered networks. Useful for the generation of benchmarking instances for the investigation of, e.g., Vehicle-Routing-Problems or Travelling Salesperson Problems.

rpn

cran
99.99th

Percentile

Pure R implementation of a simple (Reverse) Polish Notation (RPN) interpreter and converter.

rscimark

cran
99.99th

Percentile

The SciMark 2.0 benchmark was originally developed in Java as a benchmark for numerical and scientific computational performance. It measures the performance of several computational kernels which are frequently occurring in scientific applications. This package is a simple wrapper around the ANSI C implementation of the benchmark.

smoof

cran
99.99th

Percentile

Provides generators for a high number of both single- and multi- objective test functions which are frequently used for the benchmarking of (numerical) optimization algorithms. Moreover, it offers a set of convenient functions to generate, plot and work with objective functions.

BBmisc

cran
99.99th

Percentile

Miscellaneous helper functions for and from B. Bischl and some other guys at TU Dortmund, mainly for package development.

farff

cran
99.99th

Percentile

Reads and writes 'ARFF' files. 'ARFF' (Attribute-Relation File Format) files are like 'CSV' files, with a little bit of added meta information in a header and standardized NA values. They are quite often used for machine learning data sets and were introduced for the 'WEKA' machine learning 'Java' toolbox. See <http://weka.wikispaces.com/ARFF> for further info on 'ARFF' and for <http://www.cs.waikato.ac.nz/ml/weka/> for more info on 'WEKA'. 'farff' gets rid of the 'Java' dependency that 'RWeka' enforces, and it is at least a faster reader (for bigger files). It uses 'readr' as parser back-end for the data section of the 'ARFF' file. Consistency with 'RWeka' is tested on 'Github' and 'Travis CI' with hundreds of 'ARFF' files from 'OpenML'. Note that the 'OpenML' package is currently only available from 'Github' at: <https://github.com/openml/openml-r>.

mlr

cran
99.99th

Percentile

Interface to a large number of classification and regression techniques, including machine-readable parameter descriptions. There is also an experimental extension for survival analysis, clustering and general, example-specific cost-sensitive learning. Generic resampling, including cross-validation, bootstrapping and subsampling. Hyperparameter tuning with modern optimization techniques, for single- and multi-objective problems. Filter and wrapper methods for feature selection. Extension of basic learners with additional operations common in machine learning, also allowing for easy nested resampling. Most operations can be parallelized.

mlrMBO

cran
99.99th

Percentile

Flexible and comprehensive R toolbox for model-based optimization ('MBO'), also known as Bayesian optimization. It implements the Efficient Global Optimization Algorithm and is designed for both single- and multi- objective optimization with mixed continuous, categorical and conditional parameters. The machine learning toolbox 'mlr' provide dozens of regression learners to model the performance of the target algorithm with respect to the parameter settings. It provides many different infill criteria to guide the search process. Additional features include multi-point batch proposal, parallel execution as well as visualization and sophisticated logging mechanisms, which is especially useful for teaching and understanding of algorithm behavior. 'mlrMBO' is implemented in a modular fashion, such that single components can be easily replaced or adapted by the user for specific use cases.

OpenML

cran
99.99th

Percentile

We provide an R interface to 'OpenML.org' which is an online machine learning platform where researchers can access open data, download and upload data sets, share their machine learning tasks and experiments and organize them online to work and collaborate with other researchers. The R interface allows to query for data sets with specific properties, and allows the downloading and uploading of data sets, tasks, flows and runs. See <https://www.openml.org/guide/api> for more information.

99.99th

Percentile

Functions for parameter descriptions and operations in black-box optimization, tuning and machine learning. Parameters can be described (type, constraints, defaults, etc.), combined to parameter sets and can in general be programmed on. A useful OptPath object (archive) to log function evaluations is also provided.

soobench

cran
99.99th

Percentile

Collection of different single objective test functions useful for benchmarks and algorithm development.

tspmeta

cran
99.99th

Percentile

Instance feature calculation and evolutionary instance generation for the traveling salesman problem. Also contains code to "morph" two TSP instances into each other. And the possibility to conveniently run a couple of solvers on TSP instances.