Repository files navigation

Machine Learning algorithm implementations from scratch.

You can find Tutorials with the math and code explanations on my channel:Here

• KNN
• Linear Regression
• Logistic Regression
• Naive Bayes
• Perceptron
• SVM
• Decision Tree
• Random Forest
• Principal Component Analysis (PCA)
• K-Means
• AdaBoost
• Linear Discriminant Analysis (LDA)

This project has 2 dependencies.

• numpy for the maths implementation and writing the algorithms
• Scikit-learn for the data generation and testing.
• Matplotlib for the plotting.
• Pandas for loading data.

NOTE: Do note that, Onlynumpy is used for the implementations. Othershelp in the testing of code, and making it easy for us, instead of writing thattoo from scratch.

You can install these using the command below!

# Linux or MacOSpip3 install -r requirements.txt# Windowspip install -r requirements.txt

You can run the files as following.

python -m mlfromscratch.<algorithm-file>

with<algorithm-file> being the valid filename of the algorithm without the extension.

For example, If I want to run the Linear regression example, I would dopython -m mlfromscratch.linear_regression