tscf-eval

User Guide

  • Installation
    • Requirements
    • From PyPI
    • Optional Dependencies
    • From Source
    • Verifying Installation
  • Quick Start Guide
    • Loading Data
      • From the UCR Archive
      • From NumPy Arrays
    • Basic Usage
      • Evaluating Counterfactuals
      • Using a Classifier
    • Available Metrics
    • Next Steps
  • Examples
    • Generating Counterfactuals
      • Using NativeGuide
      • Using COMTE
      • Using TSEvo
      • Using Glacier
      • Using SETS and CELS
    • Evaluating Counterfactuals
      • Basic Evaluation
      • Using Model-Dependent Metrics
      • Using Distribution Metrics
      • Measuring Efficiency
      • Full Evaluation with All Metrics
    • Running Benchmarks
      • Single-Dataset Benchmark
      • Multi-Dataset Benchmark
    • Analyzing Results
      • Pareto Analysis
      • Visualizing Pareto Fronts
      • Weighted Scalarization
      • Statistical Testing
    • Extending TSCFEval
      • Custom Counterfactual Method
      • Custom Evaluation Metric
    • Complete Workflow

API Reference

  • Evaluator Module
    • Evaluator Class
      • Evaluator
        • Evaluator.metrics
        • Evaluator.__init__()
        • Evaluator.evaluate()
    • Metric Base Class
      • Metric
        • Metric.direction
        • Metric.name()
        • Metric.compute()
    • Built-in Metrics
      • Validity
        • Validity
      • Proximity
        • Proximity
      • Sparsity
        • Sparsity
      • Plausibility
        • Plausibility
      • Diversity
        • Diversity
      • Controllability
        • Controllability
      • Confidence
        • Confidence
      • Composition
        • Composition
      • Contiguity
        • Contiguity
      • Robustness
        • Robustness
      • Efficiency
        • Efficiency
    • References
  • Counterfactuals Module
    • Base Class
      • Counterfactual
        • Counterfactual.explain()
        • Counterfactual.explain_k()
    • Implementations
      • CELS
        • CELS
      • CoMTE
        • COMTE
      • NativeGuide
        • NativeGuide
      • SETS
        • SETS
      • TSEvo
        • TSEvo
      • Glacier
        • Glacier
      • LatentCF++
        • LatentCF
    • References
  • Data Loader Module
    • TSCData Container
      • TSCData
        • TSCData.name
        • TSCData.split
        • TSCData.X
        • TSCData.y
        • TSCData.from_arrays()
        • TSCData.from_dataframe()
        • TSCData.n_instances
        • TSCData.series_length
        • TSCData.n_dims
        • TSCData.n_classes
        • TSCData.is_univariate
        • TSCData.describe()
        • TSCData.to_dataframe()
        • TSCData.map_labels()
        • TSCData.select_classes()
        • TSCData.save()
        • TSCData.load()
        • TSCData.__init__()
    • Data Loaders
      • Base Class
        • DataLoader
      • UCR Loader
        • UCRLoader
      • File Loader
        • FileLoader
    • References
  • Benchmark Module
    • Features
    • BenchmarkRunner
      • BenchmarkRunner
        • BenchmarkRunner.datasets
        • BenchmarkRunner.models
        • BenchmarkRunner.explainers
        • BenchmarkRunner.evaluator
        • BenchmarkRunner.n_instances
        • BenchmarkRunner.instance_selection
        • BenchmarkRunner.n_jobs
        • BenchmarkRunner.verbose
        • BenchmarkRunner.random_state
        • BenchmarkRunner.__post_init__()
        • BenchmarkRunner.run()
        • BenchmarkRunner.__init__()
    • Instance Selection
      • SelectionStrategy
        • SelectionStrategy
      • select_instances
        • select_instances()
    • Configuration Classes
      • ExplainerConfig
        • ExplainerConfig
      • DatasetConfig
        • DatasetConfig
      • ModelConfig
        • ModelConfig
    • Result Classes
      • ExplainerResult
        • ExplainerResult
      • BenchmarkResults
        • BenchmarkResults
    • Pareto Analysis
      • ParetoAnalyzer
        • ParetoAnalyzer
        • Visualization and Analysis Methods
    • Weighted Scalarization
      • WeightedScalarizer
        • WeightedScalarizer
    • Statistical Testing
      • friedman_test
        • friedman_test()
      • FriedmanResult
    • LaTeX Table Generation
      • format_latex_table()

Development

  • Contributing
    • Contributing to TSCF-Eval
      • Table of Contents
      • Code of Conduct
      • Getting Started
      • Development Setup
        • Prerequisites
        • Installation
        • Verify Setup
      • Making Changes
        • Branch Naming
        • Workflow
      • Code Style
        • Formatting
        • Linting
        • Type Hints
        • Docstrings
      • Testing
        • Running Tests
        • Writing Tests
      • Documentation
        • Building Docs
        • Docstring Coverage
      • Submitting Changes
        • Pull Request Process
        • PR Checklist
        • Review Process
      • Release Process
        • Version Bumping
      • Adding New Features
        • Adding a New Metric
        • Adding a New Counterfactual Method
      • Questions?
  • Changelog
    • Changelog
      • 1.0.0 - 2026-03-06
        • Added
tscf-eval
  • Search

© Copyright 2026, Bruna Zamith Santos.

Built with Sphinx using a theme provided by Read the Docs.