Exploratory Data Analysis & Prediction on IRIS Dataset

A comprehensive repository exploring, analysing the Iris data set and predicting the Iris flower species based on the given features.

Table of Contents

• General overview
• Project Structure
• Environment
• Libraries & Packages
• ML models used
• Evaluation Metrics
• Results
• Setup
• Acknowledgement

General Overview

This project explores and analyses the Iris data set. The data set contains 3 classes such as Setosa, Versicolor, and Virginica of 50 instances each, making a total of 150 observations where each class refers to a type of iris plant. The number of features is 4 such as Sepal Length (cm), Sepal Width (cm), Petal Length (cm), and Petal Width (cm). It further explores relationship between the features using different kinds of plots. It further develops the model and assesses the predictive performance of 6 Machine learning classifiers based on evaluation metrics such as accuracy,recall, f1-score and precision. All the classifiers showed very good performance in classifying the species of Iris flowers based on their features.

Project Structure

This project contains Python file-

• Predictive Modeling File: It includes both exploratory data analysis and machine learning model development.

Environment

The project was executed using Google Colab.

Libraries & Packages

• Seaborn: For data visualization
• NumPy: For numerical operations
• Matplotlib: For plotting graphs
• Pandas: For data manipulation and analysis
• Scikit-learn (sklearn): For machine learning model development and evaluation

ML models used

The predictive performance of the following six classifiers was assessed:

• Random Forest
• Support Vector Machine (SVM)
• Decision Tree
• K-Nearest Neighbors (K-NN)
• Logistic Regression
• Gradient Boosting

Evaluation Metrics

The models were evaluated using the following metrics:

• Accuracy
• Recall
• F1-score
• Precision

Results

All classifiers performed well in classifying the Iris flower species based on the given features. The project successfully demonstrated the application of machine learning in a well-known dataset and provided insights into feature relationships through visualization techniques.

Setup

• Open Google Colab
• Upload the notebook or open it directly from Google Drive
• Ensure all required packages are installed
• Run the cells sequentially to execute the analysis

Acknowledgement

Available at: https://gist.github.com/curran/a08a1080b88344b0c8a7

Originally Published at: https://archive.ics.uci.edu/dataset/53/iris