README.md

metadata

title: Digit Recognizer RF
emoji: 🔢
colorFrom: blue
colorTo: indigo
sdk: streamlit
sdk_version: 1.31.0
app_file: app.py
pinned: false
license: mit
python_version: '3.10'

Digit Recognizer - Random Forest

This project is part of my journey to complete 20 Kaggle competitions. It uses a Random Forest Classifier trained on the MNIST dataset to recognize hand-drawn digits.

Project Aim

The goal is to map high-dimensional pixel data into ten distinct numerical categories. The target is to achieve high accuracy while maintaining a computationally efficient pipeline.

Dataset

• Source: Kaggle Digit Recognizer Competition
• Format: 28x28 grayscale images (flattened to 784 pixels)
• Classes: 0-9

Tech Stack

• Model: Random Forest Classifier (Scikit-Learn)
• Deployment: Streamlit & Hugging Face Spaces
• Environment: Python 3.10