🧠 MNIST Digit Classifier (K-Nearest Neighbors + Grid Search)

This project is an end-to-end machine learning pipeline for handwritten digit classification using the MNIST dataset.

It demonstrates a complete ML workflow including:

• Problem framing and dataset loading
• Visualization of sample digits
• Train-test splitting with stratification
• Model training with K-Nearest Neighbors (KNN)
• Hyperparameter tuning using Grid Search with cross-validation
• Final model evaluation using accuracy, confusion matrix, precision, recall, and F1-score

🚀 Technologies Used:

• Python 3.x
• Scikit-learn
• NumPy
• Matplotlib
• Seaborn

📈 Dataset:

MNIST Handwritten Digits (from fetch_openml)

📊 Performance Metrics:

• Accuracy
• Confusion Matrix
• Precision, Recall, F1-Score

---

This project is designed as a foundational step for building more advanced ML models and is ideal for those learning about classification tasks and hyperparameter optimization.