HashSlap-Summer-of-Code/ml-core

Implement a Cross-Domain ML Benchmark Suite

Aperta

#10 aperta il 18 giu 2025

 (0 commenti) (0 reazioni) (0 assegnatari)Jupyter Notebook (11 fork)auto 404
Intermediateenhancementhacktoberfesthssoc

Metriche repository

Star
 (3 stelle)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

Description:
Create a benchmark script to run and compare ML models from different folders on a shared dataset. Helps understand model performance across implementations.

Expected Tasks:

  • Choose or create a simple classification dataset (e.g., .csv).
  • Write a script (e.g., benchmark.py) to:
    • Import models like Perceptron, Linear Regression, etc.
    • Train and evaluate on the same dataset.
    • Output metrics like accuracy or F1 score.
  • Store benchmark results in a benchmarks/ folder.
  • Include summary output to console and optionally .csv.

Stretch Goal:

  • Add timing or memory comparisons.
  • Plot results using matplotlib or seaborn.

Guida contributor