model.py

import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns

def main():
    print("Loading the Iris dataset...")
    # 1. Load and understand a dataset
    iris = load_iris()
    X = pd.DataFrame(iris.data, columns=iris.feature_names)
    y = pd.Series(iris.target, name="target")
    
    print("\nDataset Features Head:")
    print(X.head())
    print(f"\nTotal samples: {len(X)}")
    
    # 2. Split data into training and testing sets
    print("\nSplitting the dataset into 80% training and 20% testing sets...")
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
    print(f"Training samples: {len(X_train)}")
    print(f"Testing samples: {len(X_test)}")
    
    # 3. Apply classification algorithms and compare
    print("\nTraining and comparing multiple algorithms...")
    models = {
        "Random Forest": RandomForestClassifier(n_estimators=100, random_state=42),
        "Logistic Regression": LogisticRegression(max_iter=200, random_state=42),
        "Support Vector Machine": SVC(random_state=42)
    }
    
    best_model_name = ""
    best_accuracy = 0
    best_y_pred = None
    accuracies = {}
    
    for name, model in models.items():
        model.fit(X_train, y_train)
        y_pred = model.predict(X_test)
        acc = accuracy_score(y_test, y_pred)
        accuracies[name] = acc * 100
        print(f" - {name} Accuracy: {acc * 100:.2f}%")
        
        if acc > best_accuracy:
            best_accuracy = acc
            best_model_name = name
            best_y_pred = y_pred

    print(f"\nBest Model: {best_model_name} with {best_accuracy * 100:.2f}% accuracy")
    
    # Plotting algorithm comparison
    print("Generating Algorithm Comparison bar chart...")
    plt.figure(figsize=(10, 6))
    sns.barplot(x=list(accuracies.keys()), y=list(accuracies.values()), palette='viridis')
    plt.title('Algorithm Comparison - Testing Accuracy')
    plt.ylabel('Accuracy (%)')
    plt.ylim(0, 110) # Set y-axis to a bit above 100 for visual headroom
    for index, value in enumerate(accuracies.values()):
        plt.text(index, value + 2, f'{value:.2f}%', ha='center')
    
    comp_filename = 'algorithm_comparison.png'
    plt.savefig(comp_filename)
    print(f"Algorithm comparison chart saved as {comp_filename}")
    
    # Evaluate the best model in detail
    print(f"\nDetailed Classification Report for {best_model_name}:")
    print(classification_report(y_test, best_y_pred, target_names=iris.target_names))
    
    # Plotting confusion matrix for the best model
    print(f"Generating Confusion Matrix plot for {best_model_name}...")
    cm = confusion_matrix(y_test, best_y_pred)
    plt.figure(figsize=(8, 6))
    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=iris.target_names, yticklabels=iris.target_names)
    plt.title(f'Confusion Matrix - {best_model_name}')
    plt.xlabel('Predicted')
    plt.ylabel('Actual')
    
    # Save the plot
    cm_filename = 'confusion_matrix.png'
    plt.savefig(cm_filename)
    print(f"Confusion matrix saved as {cm_filename}")

if __name__ == "__main__":
    main()