neuralnet - Training of Neural Networks

Training of neural networks using backpropagation, resilient backpropagation with (Riedmiller, 1994) or without weight backtracking (Riedmiller and Braun, 1993) or the modified globally convergent version by Anastasiadis et al. (2005). The package allows flexible settings through custom-choice of error and activation function. Furthermore, the calculation of generalized weights (Intrator O & Intrator N, 1993) is implemented.

Last updated

11.23 score 35 stars 41 dependents 4.2k scripts 19k downloads

innsight - Get the Insights of Your Neural Network

Interpretation methods for analyzing the behavior and individual predictions of modern neural networks in a three-step procedure: Converting the model, running the interpretation method, and visualizing the results. Implemented methods are, e.g., 'Connection Weights' described by Olden et al. (2004) <doi:10.1016/j.ecolmodel.2004.03.013>, layer-wise relevance propagation ('LRP') described by Bach et al. (2015) <doi:10.1371/journal.pone.0130140>, deep learning important features ('DeepLIFT') described by Shrikumar et al. (2017) <doi:10.48550/arXiv.1704.02685> and gradient-based methods like 'SmoothGrad' described by Smilkov et al. (2017) <doi:10.48550/arXiv.1706.03825>, 'Gradient x Input' or 'Vanilla Gradient'. Details can be found in the accompanying scientific paper: Koenen & Wright (2024, Journal of Statistical Software, <doi:10.18637/jss.v111.i08>).

Last updated

7.39 score 31 stars 1 dependents 35 scripts 911 downloads

arf - Adversarial Random Forests

Adversarial random forests (ARFs) recursively partition data into fully factorized leaves, where features are jointly independent. The procedure is iterative, with alternating rounds of generation and discrimination. Data becomes increasingly realistic at each round, until original and synthetic samples can no longer be reliably distinguished. This is useful for several unsupervised learning tasks, such as density estimation and data synthesis. Methods for both are implemented in this package. ARFs naturally handle unstructured data with mixed continuous and categorical covariates. They inherit many of the benefits of random forests, including speed, flexibility, and solid performance with default parameters. For details, see Watson et al. (2023) <https://proceedings.mlr.press/v206/watson23a.html>.

Last updated

6.36 score 16 stars 36 scripts 295 downloads

cpi - Conditional Predictive Impact

A general test for conditional independence in supervised learning algorithms as proposed by Watson & Wright (2021) <doi:10.1007/s10994-021-06030-6>. Implements a conditional variable importance measure which can be applied to any supervised learning algorithm and loss function. Provides statistical inference procedures without parametric assumptions and applies equally well to continuous and categorical predictors and outcomes.

Last updated

5.24 score 12 stars 29 scripts 203 downloads

blockForest - Block Forests: Random Forests for Blocks of Clinical and Omics Covariate Data

A random forest variant 'block forest' ('BlockForest') tailored to the prediction of binary, survival and continuous outcomes using block-structured covariate data, for example, clinical covariates plus measurements of a certain omics data type or multi-omics data, that is, data for which measurements of different types of omics data and/or clinical data for each patient exist. Examples of different omics data types include gene expression measurements, mutation data and copy number variation measurements. Block forest are presented in Hornung & Wright (2019). The package includes four other random forest variants for multi-omics data: 'RandomBlock', 'BlockVarSel', 'VarProb', and 'SplitWeights'. These were also considered in Hornung & Wright (2019), but performed worse than block forest in their comparison study based on 20 real multi-omics data sets. Therefore, we recommend to use block forest ('BlockForest') in applications. The other random forest variants can, however, be consulted for academic purposes, for example, in the context of further methodological developments. Reference: Hornung, R. & Wright, M. N. (2019) Block Forests: random forests for blocks of clinical and omics covariate data. BMC Bioinformatics 20:358. <doi:10.1186/s12859-019-2942-y>.

Last updated

cpp

4.62 score 7 stars 59 scripts 623 downloads

HMMpa - Analysing Accelerometer Data Using Hidden Markov Models

Analysing time-series accelerometer data to quantify length and intensity of physical activity using hidden Markov models. It also contains the traditional cut-off point method. Witowski V, Foraita R, Pitsiladis Y, Pigeot I, Wirsik N (2014). <doi:10.1371/journal.pone.0114089>.

Last updated

accelerometer-datahidden-markov-modeltime-series

3.99 score 1 dependents 65 scripts 309 downloads

tpc - Tiered PC Algorithm

Constraint-based causal discovery using the PC algorithm while accounting for a partial node ordering, for example a partial temporal ordering when the data were collected in different waves of a cohort study. Andrews RM, Foraita R, Didelez V, Witte J (2021) <arXiv:2108.13395> provide a guide how to use tpc to analyse cohort data.

Last updated

causal-discoverycohort-analysisgraphical-models

3.90 score 8 stars 20 scripts 205 downloads

micd - Multiple Imputation in Causal Graph Discovery

Modified functions of the package 'pcalg' and some additional functions to run the PC and the FCI (Fast Causal Inference) algorithm for constraint-based causal discovery in incomplete and multiply imputed datasets. Foraita R, Friemel J, Günther K, Behrens T, Bullerdiek J, Nimzyk R, Ahrens W, Didelez V (2020) <doi:10.1111/rssa.12565>; Andrews RM, Bang CW, Didelez V, Witte J, Foraita R (2021) <doi:10.1093/ije/dyae113>; Witte J, Foraita R, Didelez V (2022) <doi:10.1002/sim.9535>.

Last updated

causal-discoverygraphical-modelsmultiple-imputation

3.86 score 6 stars 24 scripts 321 downloads

pvm - PharmacoVigilance Methods

A collection of methods used in the field of pharmacovigilance for the dectection of 'interesting' drug-adverse event pairs from spontaneous reporting data.

Last updated

pharmacovigilancecpp

3.72 score 33 stars 16 scripts

ggiraphAlluvial - Interactive Alluvial Geoms for 'ggplot2' Using 'ggiraph'

Provides interactive extensions of alluvial geoms from the 'ggalluvial' package for use with 'ggiraph'. The package enables tooltips, hover effects, and clickable elements for alluvial plots created with 'ggplot2', making it easier to explore categorical flow data in interactive visualizations.

Last updated

3.00 score 2 scripts

SRSim - Spontaneous Reporting Simulator (SRSim)

A package for simulating spontaneous reporting data as used in the field of pharmacovigilance.

Last updated

binary-datapharmacovigilancesimulatorcpp

2.70 score 5 stars 4 scripts

CVN - Covariate-Varying Networks

Inferring high-dimensional Gaussian graphical networks that change with multiple discrete covariates. Louis Dijkstra, Arne Godt, Ronja Foraita (2024) <doi:10.48550/arXiv.2407.19978>.

Last updated

graphical-modelshigh-dimensional-statisticsnetwork-analysiscpp

2.60 score 8 scripts

survinng - Gradient-Based Feature Attribution for Survival Neural Networks

This package implements model-specific, gradient-based feature attribution methods for deep survival neural networks, including DeepHit, CoxTime, and DeepSurv. It accompanies the ICML 2025 paper "Gradient-based Explanations for Deep Learning Survival Models".

Last updated

2.38 score 1 stars 16 scripts

expard - Drug 'EXPosures' and 'ADRs'

An R package for fitting complex drug exposure and adverse drug reaction ('ADR') relationships. It can additionally be used to simulate electronic healthcare record ('EHR') data of patients observed across multiple timepoints.

Last updated

2.30 score 2 stars 7 scripts

dsDashboard - Dashboard Framework for DataSHIELD Applications

Provides a framework for building interactive dashboards in R. The package is designed to support data analysis both on local data and on data on a DataSHIELD server.

Last updated

2.30 score 1 scripts

IDEFICS.scalc - Scoring Tools for Anthropometric and Metabolic Parameters in Children

Provides tools to compute standardized percentiles and z-scores for anthropometric and metabolic parameters in children, based on age-, sex-, and height-specific reference data from the IDEFICS study. Supports computation of a composite Metabolic Syndrome (MetS) score and associated action levels for child health monitoring.

Last updated

2.00 score 1 stars 1 scripts

wflsa - Weighted Fused LASSO Signal Approximator ('wFLSA')

A package for computing the Weighted Fused LASSO Signal Approximator (wFLSA).

Last updated

fused-lassolassolasso-regressioncpp

2.00 score 3 scripts

survnet - Artificial neural networks for survival analysis

Artificial neural networks for survival analysis

Last updated

1.70 score 1 stars 9 scripts

batchlasso - BatchLASSO

A package for using the LASSO for ranking response-exposure pairs on the basis of the highest lambda for which they first appear in the active set

Last updated

1.70 score