Skip to content

darthvader58/Machine_Learning_From_Scratch

Repository files navigation

Machine Learning from Scratch

This project folder contains SVM, K-Means, Mean-Shift and Neural Networks Models made from Scratch using Numpy and Python, with a small portion using Pandas and Scikit-Learn's sklearn.preprocessing for Data Cleaning. The purpose of this project folder was to delve deeper into the foundation of Supervised and Unsupervised Learning concepts as well as understand the mathematical and algorithmic complexity of the solutions.

Datasets

Iris Flower Classification


The data consists of 150 rows of Iris flower samples with 50 instances for each category - `Iris setosa`, `Iris versicolor`, and `Iris virginica`. It consists of 5 variables aka 5 columns with `petal-length`, `petal-width`, `sepal-length` and `sepal-width` as features and `class` as the output label.

Heart Disease Samples


The data contains 303 instances of patient samples with 13 features determining the presence of a heart diease. Experiments have concentrated on simply attempting to distinguish presence (values 1,2,3,4) from absence (value 0), however due to the usage on a clustering model, only 2 clusters for 0 (absence) and 1(presence) was used.

Portuguese Bank Marketing Campaigns


About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages