Project: End to end Machine Learning Deployment
Learn how to complete machine learning project for deployment!
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
What things you need to install the software and how to install them.
Create a Git repo and virtual env.
A step by step series of examples that tell you how to get a development env running. To create the virtual environment
conda create -p venv python==3.9 -y
conda activate <path/to/folder>/venv
And then clone your git repo
git init
git add README.md
git commit -m "first commit"
git push -u origin main
Also, add .gitignore then:
git pull origin main
touch setup.py
touch requirements.txt
mkdir src
touch src/__init__.py
mkdir src/components
touch src/components/__init__.py
touch src/components/data_ingestion.py
touch src/components/data_validation.py
touch src/components/data_transformation.py
touch src/components/model_trainer.py
mkdir src/pipeline
touch src/pipeline/train_pipeline.py
touch src/pipeline/predict_pipeline.py
touch src/pipeline/__init__.py
touch src/logger.py
touch src/exceptions.py
touch src/utils.py
Example of getting some data out of the system for a little demo.
To run the code after activating the venv and following the code line by line run:
python src/components/data_ingestion.py
Apply all possible regression model and find/keep the best performing model for predicitng the math_score.
python src/components/data_ingestion.py
Got r2_score of near 0.87
Pick the best performing model for your project objective.
Above code can be used and tested with the command shared above.
- Keep learning & hustling!