Skip to content

2 GUI

Jump to bottom
agudys edited this page Apr 22, 2025 · 1 revision

In contrast to RuleKit 1, where the graphical user interface was provided by the RapidMiner plug-in, the second revision includes a browser application wrapping RuleKit-python. This made configuration of algorithms' parameters and defining expert knowledge more intuitive. New functionalities like visualization of survival function estimates were also added.

The RuleKit 2 GUI is available at https://rulekit-gui.fly.dev/

Example

In the following subsection we show an example train-test analysis with a use of RuleKit 2 GUI. The investigated dataset is named bone-marrow and describes survival of pediatric patients with several hematologic diseases, who were subject to the unmanipulated allogeneic unrelated donor hematopoietic stem cell transplantation. The set in the CSV format required by GUI can be downloaded from (here).

The analysis consists of several steps performed on consecutive tabs:

  • Dataset - loading dataset,
  • Model - setting model parameters and, optionally, expert's knowledge,
  • Rules - investigating resulting rules,
  • Evaluation - model evaluation on training and testing sets.

The screenshots of the analysis performed step-by-step was shown below.

Table of contents

Home

  1. Batch interface
    1. General information
    2. Parameter set definition
    3. Dataset definition
    4. Example
  2. Graphical user interface
  3. Python package
  4. Quality and evaluation
    1. Rule quality
    2. Model characteristics
    3. Performance metrices
  5. Output files
    1. Training report
    2. Prediction performance report
  6. User-guided induction
    1. Defining user's knowledge
    2. Examples from GuideR paper
  7. Contrast set mining
  8. Library API
  9. Empirical results
Clone this wiki locally