Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gimseng/99-ML-Learning-Projects
A list of 99 machine learning projects for anyone interested to learn from coding and building projects
https://github.com/gimseng/99-ML-Learning-Projects
hacktoberfest
Last synced: about 2 months ago
JSON representation
A list of 99 machine learning projects for anyone interested to learn from coding and building projects
- Host: GitHub
- URL: https://github.com/gimseng/99-ML-Learning-Projects
- Owner: gimseng
- License: mit
- Created: 2020-07-11T12:19:26.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2024-02-13T17:26:28.000Z (10 months ago)
- Last Synced: 2024-04-23T17:22:07.875Z (8 months ago)
- Topics: hacktoberfest
- Language: Jupyter Notebook
- Homepage:
- Size: 19.7 MB
- Stars: 559
- Watchers: 23
- Forks: 170
- Open Issues: 110
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
- awesome-ai-data-github-repos - 99 Machine Learning Projects
- awesome-ai-data-github-repos - 99 Machine Learning Projects
README
# 99-ML-Learning-Projects
A list of 99 machine learning projects for anyone interested to learn machine learning from coding and building projects.
Our working philosophy is to provide a curated repo for anyone to contribute a cool/fun exercise and solution that is useful for anyone (including themselves) in their journey of learning machine learning.
## Getting Started
The format is roughly the following:
1. Propose an exercise by creating an issue ticket and write what you think is an useful coding exercise for certain concepts.
2. If enough people are interested in that issue ticket, hopefully either you or someone else will write the exercise statement properly similar to the style of a lab exercise/homework question.
3. Then someone will fork the repo, write up their solution, with a bit of polish and documentation, submit a pull request. Please see [general contribution guidelines](CONTRIBUTING.md) for more details on how to contribute solutions.
4. Some of us will scrutinize the codes, review, make suggestions and eventually include (merge) them into the main project repo.
5. At anytime, someone can repeat suggest improvements/changes to 3-4 above for a particular exercise. This is done by creating an issue ticket for improvement/enhancement. One can then repeat 3-4.
6. Finally, repeat 1-5 indefinitely till we hit 99/99 projects.
Please abide by [code of conduct guidelines](CODE_OF_CONDUCT.md) to have an open and friendly open source collaboration.
### Goal: 99 Projects
### Current: 10 Projects
## Table of Contents
#### General-Purpose Machine Learning
- [Linear Regression [Beginner]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/002/exercise)
- [Titanic Survival Prediction [Beginner]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/001/exercise)
- [kNN from Scratch[Beginner]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/010/exercise)
- [kNN from Sklearn [Beginner]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/009/exercise)
- [Bagging and boosting ensemble methods [Intermediate]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/006/exercise)
#### Computer Vision
- [MNIST Handwriting Digit Recognition [Intermediate]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/003/exercise)
#### Natural Language Processing
- [Sentiment analysis [Intermediate]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/005/exercise)
- [Text-generation neural network model (with LSTM) [Advanced]](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/004/exercise)
#### Bayesian
- [Naive Bayes Classification](https://github.com/gimseng/99-ML-Learning-Projects/blob/master/008/exercise)
#### Misc/Mix Models
- [Employee Attrition & Performance](https://github.com/gimseng/99-ML-Learning-Projects/tree/master/007)
## Refreshers/Cheatsheets
- [Numpy](https://github.com/gimseng/99-ML-Learning-Projects/blob/master/Resources/Numpy/NumPy%20Tutorial.ipynb)
- [Pandas](https://github.com/gimseng/99-ML-Learning-Projects/blob/master/Resources/Pandas/Pandas%20Tutorial.ipynb)
## Dependencies
Some of the libraries (and their versions) we are using:
- Python (>= 3.6)
- NumPy (>= 1.18.5)
- Pandas (>= 1.0.5)
- Matplotlib (>= 3.2.2)
- Seaborn (>= 0.10.1)
- Scikit-learn (>= 0.22.2)
- Tensorflow (>= 2.2.0)
- PyTorch (>= 1.5.1)
## Help and Support
If you want to get in touch with us, say hi on our discord/gitter chatroom:
- Discord: https://discord.gg/VVDg6P4
- Gitter: https://gitter.im/99-ML-Learning-Projects/community
## Recent Contributors
[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/0)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/1)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/2)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/3)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/4)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/5)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/6)[](https://sourcerer.io/fame/gimseng/gimseng/99-ML-Learning-Projects/links/7)
## Credit:
This project is inspired by Unnit Metaliya’s answer on quora: https://qr.ae/pNK0FW
For credits, these are the two repos (one for C and one for React) where I got the idea from:
- https://github.com/truedl/c-for-beginners
- https://github.com/UnnitMetaliya/99-reactjs-project-ideas
## License
This repo is covered under [The MIT License](LICENSE).