ZTM - Complete Machine Learning and Data Science
Code repository for Udemy course
Explore the docs »
View Demo
·
Report a Bug
·
Request Feature
Table of Contents
About The Project
The repository contains my code for the Complete Machine Learning and Data Science: Zero to Mastery Udemy course.
See the original course materials by Daniel Bourke.
You can read my thoughts, lecture notes, and observations on my blog:
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 01)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 02)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 03)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 04)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 05)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 06)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 07)
- A Walkthrough of the “Complete Machine Learning and Data Science: Zero to Mastery” Course (Part 08)
The project setup with Docker and docker-compose is heavily influenced by the Data Science Docker Template by Binal Patel.
Built With
- Docker and docker-compose
- Python
- Jupyter Notebooks
Getting Started
To get a local copy up and running follow these steps:
Prerequisites
You'll need Docker and docker-compose:
- Docker
docker --version
> Docker version 19.03.5-ce
- docker-compose
docker-compose -v
> docker-compose version 1.25.3
Installation
- Clone the repo
git clone https://github.com/sophiabrandt/ZTM-Complete-Machine-Learning-Data-Science.git
- Create
.env_dev
file with the following format:
# credentials and database information
db_username=test_username
db_password=test_password
db_host=test_host
db_port=test_port
db_name=test
# disables lag in stdout/stderr output
PYTHONUNBUFFERED=1
PYTHONDONTWRITEBYTECODE=1
# random seed
random_seed=42
- Build and run container
docker-compose up --build -d
Usage
Note: The Jupyter Notebook uses Vim key mappings for development. See Dockerfile-dev. Delete relevant lines in the Dockerfile if needed.
-
Go to http://localhost:8888 for JupyterLab. Enter access token:
local_dev
. -
Develop and save any notebooks into
/notebooks
. Save final artifacts/models needed for production in/code
. -
Save final version of code and any models the code relies upon into
/code
.
Roadmap
See the open issues for a list of proposed features (and known issues).
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
License
Distributed under the MIT License. See LICENSE
for more information.
Original code by Andreie Neagoie, Daniel Bourke. Original Docker setup by Binal Patel.
Contact
Sophia Brandt - @hisophiabrandt
Project Link: https://github.com/sophiabrandt/ZTM-Complete-Machine-Learning-Data-Science
Acknowledgements
- Complete Machine Learning and Data Science: Zero to Mastery by Andrei Neagoie & Daniel Bourke
- Data Science Docker Template by Binal Patel