What it is? ๐ก It's a resume from Machine Learning Specialization Course from Stanford, the Jovian Course Machine Learning with Scikit-Learn: Zero to GBMs and the Deep Learning with PyTorch: Zero to GANs. Why did you build this project? ๐ก It was partly a bootcamp project to achieve the highest possible score in the E-commerce dataset. But I'll use it as a kaggle notebook repository.
What was my motivation? ๐ก I know Python very well, but I'd like to have a solid foundation in supervise and unsupervise learning. On the other hand, it is a good starting point for Deep Learning and AI. What did you learn? ๐ก Libraries such as Pandas, Scikit-Learn, and PyTorch; Machine Learning supervised learning, unsupervised learning, recommender systems, and reinforcement learning. Best practices for Jupyter notebooks. However, the gem of this repo is practical advice for using learning algorithms.
- Datathon
- Project Description
- Table of Contents
- Datasets
- All machine learning models explained or learned
- 1. Linear regression (/ML-Models-Learned/Linear-Regression.ipynb)
- 2. Logistic regression (/ML-Models-Learned/Logistic-Regression.ipynb)
- 3. Decision trees (/ML-Models-Learned/Decision-Tree.ipynb)
- 4. Random forests
- 5. Gradient boosting
- 5. Gradient descent
- 5. Multilayer neural networks
- 5. Convolutional neural network
- How to run
- + Info
- Licence GNU GPLv3
1. From Kaggle.
- You'll need to fork and clone the repo.
- Create a env with
python3 -m venv ./venv
We can also use Conda. - Let's install the requirements as follows
pip install -r requeriments/dev.txt
. - To activate venv
source venv/bin/activate
. - Run jupyter
jupyter-notebook
orjupyter-lab
. - To deactivate
deactivate
.