Naive-Bayes

Naive Bayes Classifier | 10-Fold Cross-Validation | ROC Curve Analysis | Machine Learning | Python

Overview

This repo contains a Jupyter Notebook that implements the Gaussian Naïve Bayes algorithm from scratch to perform binary classification on the famous Iris dataset 🌸. The dataset consists of three types of iris flowers: Setosa, Versicolor, and Virginica.

Table of Contents

• File Structure 📂
• Requirements
• Installation Guide 🛠
• Dataset Information
• Naïve Bayes Algorithm
• Display 📷
• Key Findings 📈
• Contributing 🚀

📦 Naive-Bayes repo
|-- 📜 Img 
|    |-- 📜 1.png
|    |-- 📜 2.png
|    |-- 📜 3.png
│-- 📜 Naive_Bayes.ipynb       # Jupyter Notebook with implementation
│-- 📜 requirements.txt        # List of dependencies
│-- 📜 iris.csv                # Dataset (Iris Flower Dataset)
│-- 📜 README.md               # Project documentation

Requirements

• Python Version: 3.10 or higher
• External Dependencies: Managed through requirements.txt
• Jupter Notebook for the web framework
• Numpy
• Panda

Installation Guide 🛠

Follow the steps below to set up and run the project:

1️⃣ Clone the Repository

git clone https://github.com/adexoxo13/Naive-Bayes.git
cd Naive-Bayes

2️⃣ Create a Virtual Environment (Optional but Recommended)

conda create --name <my-env>
# When conda asks you to proceed, type y:
proceed ([y]/n)?  

#Verify that the new environment was installed correctly:
conda env list

#Activate the new environment:
conda activate myenv

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Launch Jupyter Notebook

jupyter notebook

Open Naive_Bayes.ipynb in Jupyter and run the cells to see the model in action.

---

Dataset Information 📊

The Iris Dataset consists of 150 samples, with the following attributes:

Feature	Description
Sepal Length	Length of the sepal (cm)
Sepal Width	Width of the sepal (cm)
Petal Length	Length of the petal (cm)
Petal Width	Width of the petal (cm)
Species	Type of Iris Flower (Target)

---

Naïve Bayes Algorithm 🧠

Naïve Bayes is a probabilistic classifier based on Bayes' Theorem. It is widely used for text classification, spam filtering, and medical diagnosis. Given an input feature set, it calculates the probability of each class and selects the one with the highest probability.

Bayes' Theorem:

• P(A|B) = (P(B|A) * P(A)) / P(B)

---

Display 📷

📌 Data Visualization:

# Example Plot
import seaborn as sns
import matplotlib.pyplot as plt
sns.pairplot(data, hue="species")
plt.show()

This will generate scatter plots of the Iris dataset.

---

Key Findings 📈

1. Best Performance:

   Setosa vs Versicolor classifications show near-perfect separation

   

   Setosa vsVirginica classifications show near-perfect separation

   

   Setosa vsVirginica classifications show near-perfect separation

   

2. Most Challenging:

   Versicolor vs Virginica classification demonstrates overlap

3. Model Accuracy:

   Average AUC of 1 for Setosa vs Versicolor and Setosa vs Virginica

   Consistent performance across cross-validation folds

   Average AUC of 0.97 ± 0.03 for Versicolor vs Virginica

Limitations

Currently implements Gaussian Naive Bayes only

Assumes feature independence (naive assumption)

Limited to binary classification scenarios

Future Improvements 🚀

Add multiclass classification support

Implement different probability distributions

Include feature correlation handling

Add hyperparameter tuning capabilities

Expand to other datasets

---

Contributing 🚀

Contributions are welcome! Feel free to fork the repository and submit a pull request.

Contact 📬

Feel free to reach out or connect with me:

• 📧 Email: adenabrehama@gmail.com
• 💼 LinkedIn: linkedin.com/in/aden
• 🎨 CodePen: codepen.io/adexoxo

📌 Star this repository if you found it useful! ⭐