ML Evaluation Module for DL Gold Standard

A framework to evaluate knowledge graph embeddings on description logics test cases. You can generate or download the gold standard using this project.

Usage Notes

Minimal Python Example

from dl_evaluation_framework.evaluation_manager import EvaluationManager, VectorTuple

# provide the path to the test case directory
test_directory = ""

# provide vector_name and vector_path
vlist = [VectorTuple(vector_name="", vector_path="")]

# run
em = EvaluationManager(test_directory=test_directory)
em.evaluate(vector_names_and_files=vlist)

Developer Notes

This project is tested with Python [3.8, 3.9, 3.10] on macOS and Linux.

• Testing framework: pytest
• Docstring format: NumPy/SciPy
• Code formatting: black