HashSlap-Summer-of-Code/ml-core

Implement a Cross-Domain ML Benchmark Suite

Open

#10 opened on Jun 18, 2025

View on GitHubContributor guide
 (0 comments) (0 reactions) (0 assignees)Jupyter Notebook (11 forks)auto 404
Intermediateenhancementhacktoberfesthssoc

Repository metrics

Stars
 (3 stars)
PR merge metrics
 (PR metrics pending)

Description

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.

Contributor guide

Research direction
Select a simple classification dataset (e.g., Iris or a CSV). Write a script `benchmark.py` that imports models like Perceptron and Linear Regression from scikit learn, trains them on the same data, evaluates accuracy/F1, and saves results to `benchmarks/`. Optionally add timing and plotting with matplotlib/seaborn.
Tech stack
pythonscikit learnpandas
Domain
machine learningdata
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Pythonscikit learnpandas
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80