partykit: A Modular Toolkit for Recursive Partytioning in R

Authors: Torsten Hothorn, Achim Zeileis

JMLR 2015 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental As an example for the visualizations, Figure 1 shows two different trees fitted to the well-known data on survival of passengers on the ill-fated maiden voyage of the RMS Titanic: The left panel shows a CART tree with constant fits learned by rpart and converted to partykit. The right panel shows a MOB tree learned with partykit with a logistic regression for treatment effects in the terminal nodes.
Researcher Affiliation Academia Torsten Hothorn EMAIL Institut f ur Epidemiologie, Biostatistik und Pr avention, Universit at Z urich Achim Zeileis EMAIL Institut f ur Statistik, Universit at Innsbruck
Pseudocode No The paper describes the design and functionality of the partykit R package using prose and bullet points, but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes The partykit package is an add-on package for the R system for statistical computing. It is available from the Comprehensive R Archive Network (CRAN) at http://CRAN.R-project.org/package=partykit and can be installed from within R, e.g., using install.packages.
Open Datasets No The paper mentions using 'well-known data on survival of passengers on the ill-fated maiden voyage of the RMS Titanic' for illustrative purposes in Figure 1, but it does not provide concrete access information such as a specific link, DOI, repository, or formal citation for this dataset.
Dataset Splits No The paper mentions fitting models to the Titanic dataset but does not provide any specific information regarding dataset splits (e.g., training, test, or validation percentages or counts).
Hardware Specification No The paper focuses on describing the 'partykit' R package and its functionalities; it does not provide any specific details about the hardware (e.g., GPU/CPU models, memory specifications) used for development or illustration purposes.
Software Dependencies Yes It depends on R (at least 2.15.0) as well as the base packages graphics, grid, stats, and the recommended survival.
Experiment Setup No The paper describes the 'partykit' R package and uses the Titanic dataset for an illustrative visualization. It does not provide specific experimental setup details such as hyperparameter values, optimizer settings, or training configurations for these demonstrations.