PricePilot (Django + ML pipeline)

A ready-to-run Django web app with a training script that:

• reads data/Housedata.csv
• trains a strong gradient-boosted regressor (XGBoost) on price
• saves a single joblib artifact (ml_artifacts/model.joblib)
• writes metrics + a plot into ml_artifacts/

Quickstart

1) Create venv and install deps

python -m venv venv
# Windows:
venv\Scripts\activate
# macOS/Linux:
source venv/bin/activate

pip install -r requirements.txt

2) Train the model

python ml/train.py --data data/Housedata.csv

Or via Django:

python manage.py train_model --data data/Housedata.csv

3) Run Django

python manage.py migrate
python manage.py createsuperuser
python manage.py runserver

Open: http://127.0.0.1:8000

Notes

• If you retrain, the UI automatically uses the newest artifact in ml_artifacts/model.joblib.
• The dashboard stores prediction history per user.