🌦️ Weather Disease Prediction System (98.56% Accuracy)

A Machine Learning system that predicts potential diseases by analyzing the correlation between local weather conditions and clinical symptoms.

📖 Overview

This project leverages a Random Forest Classifier to bridge the gap between meteorology and health. By combining environmental data (Temperature, Humidity, Wind) with patient symptoms, the model provides an early diagnosis prediction with high accuracy. It includes a fully interactive GUI for real-time simulation.

✨ Key Features

• 🩺 Hybrid Intelligence: Integrates weather metrics with biological data for precise predictions.
• 🎛️ Interactive GUI: Built-in dashboard (using ipywidgets) allowing users to input data via sliders and checkboxes.
• 🤖 Robust Model: Uses Random Forest algorithm to handle mixed data types effectively.
• 📊 Full Pipeline: Complete workflow from data cleaning, label encoding, to confusion matrix evaluation.

🛠️ Tech Stack

Category	Tools
Core	Python 3.x
ML & Data	Scikit-Learn, Pandas, NumPy
Visualization	Matplotlib, Seaborn
Interface	Ipywidgets

🚀 How to Run

1. Clone/Download this repository.
2. Open the .ipynb file in Google Colab.
3. Upload the dataset: Weather-related disease prediction.csv to the Colab files area.
4. Select Runtime > Run all.
5. Scroll to the bottom to access the Interactive Prediction Tool.

📂 Dataset Snapshot

The model analyzes variables including:

• Weather: Temperature (°C), Humidity (%), Wind Speed (km/h).
• Patient: Age, Gender, Pre-existing conditions.
• Symptoms: Fever, Fatigue, Joint Pain, etc.

🏆 Model Performance

The system successfully classifies weather-correlated diseases such as:

• ✅ Dengue
• ✅ Malaria
• ✅ Respiratory Infections (Asthma/Flu)
• ✅ Heat-related Heart Conditions

---

made with love by HERZBAY for this life