GitHub - Surya-dcode/scikit-learn-Issue-Labeling-using-encoder-models

Name		Name	Last commit message	Last commit date
Latest commit History 25 Commits
data		data
models		models
notebooks		notebooks
results		results
README.md		README.md
analyze_results.py		analyze_results.py
collect_data.py		collect_data.py
optimized_evaluation.py		optimized_evaluation.py
process_data.py		process_data.py
requirements.txt		requirements.txt
train_deberta.py		train_deberta.py
train_distilbert.py		train_distilbert.py
train_roberta.py		train_roberta.py

Repository files navigation

Run the setup script: ./setup.sh
Activate virtual environment: source venv/bin/activate
Copy .env.template to .env and add your API keys
Run data collection: python collect_data.py

Project Structure

data/ - Collected datasets
notebooks/ - Jupyter notebooks for analysis
src/ - Source code modules
results/ - Model outputs and evaluation results
logs/ - Log files

API Keys Needed

GitHub Token: For API rate limiting (optional but recommended)
OpenAI API Key: For LLM classification
Anthropic API Key: Alternative LLM option

Get GitHub token: https://github.com/settings/tokens Get OpenAI key: https://platform.openai.com/api-keys Get Anthropic key: https://console.anthropic.com/

About

No description, website, or topics provided.

Report repository

Releases

No releases published

Packages

No packages published

Languages