🌸 Project_2_Iris-Flower-Classification

---

📖 Project Overview

This project is a Machine Learning classification system that predicts the species of an Iris flower based on its physical measurements.

The model is trained using the K-Nearest Neighbors (KNN) algorithm and follows a complete machine learning pipeline including:

• Data Exploration
• Data Visualization
• Data Preprocessing
• Train-Test Split
• Feature Scaling
• Model Training
• Prediction
• Model Evaluation
• Hyperparameter Tuning
• Cross Validation
• Model Saving

This project was developed as part of an AI/ML Internship to demonstrate the complete workflow of building a supervised Machine Learning model.

---

📂 Dataset

Dataset Used:

Iris Flower Dataset

The dataset contains 150 flower samples from three different Iris species.

Features

• Sepal Length
• Sepal Width
• Petal Length
• Petal Width

Target Classes

• 🌸 Setosa
• 🌸 Versicolor
• 🌸 Virginica

---

🧠 Machine Learning Workflow

Load Dataset
      │
      ▼
Exploratory Data Analysis
      │
      ▼
Data Visualization
      │
      ▼
Train-Test Split
      │
      ▼
Feature Scaling
      │
      ▼
Train KNN Model
      │
      ▼
Predictions
      │
      ▼
Model Evaluation
      │
      ▼
Hyperparameter Tuning
      │
      ▼
5-Fold Cross Validation
      │
      ▼
Save Trained Model

---

✨ Features

✅ Exploratory Data Analysis

✅ Statistical Summary

✅ Data Visualization

✅ Pair Plot

✅ Species Count Plot

✅ Train-Test Split

✅ Feature Scaling using StandardScaler

✅ K-Nearest Neighbors Classifier

✅ Model Prediction

✅ Accuracy Score

✅ Confusion Matrix

✅ Classification Report

✅ Confusion Matrix Heatmap

✅ Custom Flower Prediction

✅ Save Trained Model (.pkl)

✅ Hyperparameter Tuning

✅ Accuracy vs K Graph

✅ 5-Fold Cross Validation

---

🛠 Technologies Used

Technology	Purpose
Python	Programming Language
Pandas	Data Handling
NumPy	Numerical Computing
Matplotlib	Data Visualization
Seaborn	Statistical Visualization
Scikit-Learn	Machine Learning
Joblib	Model Saving

---

📊 Model Performance

Test Accuracy

93%

Cross Validation

5-Fold Cross Validation

The model was evaluated using 5-Fold Cross Validation to obtain a more reliable estimate of its performance.

Best K Value

K = 5

---

📸 Project Screenshots

🌸 Pair Plot

The pair plot visualizes the relationship between all four features of the Iris dataset. It clearly shows that Setosa is linearly separable, while Versicolor and Virginica have slight overlap.

---

📊 Class Distribution

The dataset contains an equal number of samples (50 each) for all three flower species, making it a perfectly balanced dataset.

---

🔥 Confusion Matrix

The confusion matrix shows that the trained KNN model correctly classifies almost every sample, with only a few misclassifications between Versicolor and Virginica.

---

📈 Accuracy vs K

Cross-validation was used to evaluate different values of K. The best performing model was selected based on the highest average validation accuracy.

📁 Project Structure

Project_2_Iris-Flower-Classification/
│
├── models/
│   ├── knn_iris_model.pkl
│   └── scaler.pkl
│
├── screenshots/
│   ├── countplot.png
│   ├── pairplot.png
│   ├── confusion_matrix_heatmap.png
│   └── accuracy_vs_k.png
│
├── main.py
├── requirements.txt
└── README.md

---

🚀 Installation

Clone Repository

git clone https://github.com/iabhishek765/Iris-Flower-Classification_Project_2.git

Go to Project Folder

cd Iris-Flower-Classification_Project_2

Install Dependencies

pip install -r requirements.txt

Run Project

python main.py

---

📈 Output

The project performs:

• Dataset Exploration
• Statistical Analysis
• Visualization
• Data Preprocessing
• Model Training
• Model Prediction
• Performance Evaluation
• Hyperparameter Tuning
• Cross Validation
• Saves the trained model for future use

---

🔮 Future Improvements

• Deploy using Streamlit
• Build a Flask API
• Add user input interface
• Compare multiple ML algorithms
• Perform GridSearchCV
• Deploy on Hugging Face Spaces

---

👨‍💻 Author

Abhishek Singh

AI & ML Enthusiast

GitHub:

https://github.com/iabhishek765

---

⭐ If you found this project useful, consider giving it a star!