Iris Flower dataset - Machine Learning methods

The Iris Flower dataset is a built-in dataset in Scikit learn and contains data on Sepal Length, Sepal Width, Petal Length and Petal Width for 3 different types of irises’ (Setosa, Versicolour, and Virginica). In this project 5 different machine learning methods (Decision Tree, Support Vector Machine, Random Forest, Naive Bayes and K-nearest neighbour) are compared using Scikit-learn built in methods. In addition, Gaussian Mixture Model and K-means algorithm are implemented from scratch. This project was created as a homework assignment in a course in Machine Learning at National University of Singapore (NUS).

Scikit-learn methods

In ModelComparison.py the built-in scikit-learn libraries for five different machine learning methods are implemented and compared, these are:

• Decision Tree
• Support Vector Machine
• Random Forest
• Naive Bayes
• K-nearest neighbour

ML-algorithms built from scratch

In addition to the five pre-defined algorithms in Scikit-learn, two of them are built from scratch, these are:

• Gaussian Mixture Model EM Algorithm
• K-means Clustering

Gaussian Mixture Model

Gaussian Mixture Model

K-means algorithm

K-means clustering

Source

Iris Flower Dataset