imdb-sentiment-ci-cd

IMDB Sentiment Neural Network with GitHub CI/CD

This project trains a simple neural network sentiment classifier for IMDB movie reviews.

The model uses:

• imdb_top_500.csv
• TF-IDF text features
• A feedforward PyTorch neural network
• GitHub Actions CI/CD
• Hugging Face Hub upload

Project Structure

data/
  imdb_top_500.csv
model/
  model.pt
  vectorizer.pkl
  config.json
  metrics.json
train.py
predict.py
requirements.txt
.github/workflows/train-and-upload.yml

Local Training

pip install -r requirements.txt
python train.py
python predict.py

GitHub Actions Setup

Create a Hugging Face access token, then add it to your GitHub repository:

Settings -> Secrets and variables -> Actions -> New repository secret
Name: HF_TOKEN
Value: your Hugging Face token

Edit .github/workflows/train-and-upload.yml and replace:

YOUR_HF_USERNAME/imdb-sentiment-ci-cd

with your real Hugging Face username and model repository name.

After pushing to main, GitHub Actions will:

1. Install dependencies
2. Run python train.py
3. Save model artifacts
4. Upload artifacts to Hugging Face Hub

Final Deliverables

Send these two URLs to the WeChat group:

• GitHub repository URL
• Hugging Face model repository URL