LIR Python Likelihood Ratio Toolkit

Toolkit for developing, optimising and evaluating Likelihood Ratio (LR) systems. This allows benchmarking of LR systems on different datasets, investigating impact of different sampling schemes or techniques, and doing case-based validation and computation of case LRs.

LIR was first released in 2020 and redesigned from scratch in 2025, replacing the previous repository.

References

• LiR documentation: comprehensive overview, terminology and more on developing LR systems
• Practitioner Guide (branch | paper | notebook): case study using LiR to develop an LR system using LiR
• Quick Start: selecting / designing the proper LR system based on your data

Installation

LIR is compatible with Python 3.12 / 3.13/ 3.14. The easiest way to install LIR is to use pip:

pip install lir

Usage

This repository offers both a Python API and a command-line interface.

Lir uses matplotlib for plotting, with the Agg backend as default. If you want to use a different backend, you can set the MPLBACKEND environment variable to your preferred backend. For example, to use the TkAgg backend, you can run:

export MPLBACKEND=TkAgg

Command-line interface

LiR can be launched from the command line as follows:

lir --help

Or, alternatively:

python -m lir

Evaluate an LR system using the command-line interface as follows:

1. define your data, LR system and experiments in a YAML file;
2. run lir <yaml file>.

The examples folder may be a good starting point for setting up an experiment.

The elements of the experiment configuration YAML are looked up in the registry. The following lists all available elements in the registry.

lir --list-registry

Setting up the validation schema

A schema that validates lir configuration yaml files is available, namely lir/resources/config-schema.json. This schema can be used to validate a specific yaml file by using

lir --validate your_experiment.yaml

Next to this, most modern IDEs support JSON/YAML schema validation.

PyCharm

To specify the schema in PyCharm, see this official documentation entry.

Visual Studio Code

1. Install RedHat's YAML extension.
2. Point the extension to the validation schema. This can be done in two ways:

   1. Add

        "yaml.schemas": {
            "lir/resources/config-schema.json": "*.yaml"
        }
      

      to settings.json.

   2. Open settings (ctrl + ,), find the Yaml: Schemas settings and create an entry with lir/resources/config-schema.json as item and *.yaml as value.

Contributing / Development

Contributions are highly welcomed. If you'd like to contribute to the LiR package, please follow the steps as described in the CONTRIBUTING.md file.