Intellihack_TechSpark_01

🌧️ Weather Forecasting with Machine Learning

🌱 IntelliHack 5.0 – Team TechSpark

This repository contains our solution to the Weather Forecasting Machine Learning Task for IntelliHack 5.0.

---

📌 Problem Statement

Farmers depend on precise weather forecasts for irrigation, planting, and harvesting decisions. Traditional weather forecasts often lack accuracy for hyper-local conditions. Our goal is to leverage historical weather data to predict daily rainfall probabilities accurately, assisting farmers in making informed decisions.

---

🗂️ Project Structure

• weather_forecasting.ipynb:
  Clearly structured notebook covering data preprocessing, exploratory analysis, feature engineering, model training, hyperparameter tuning, and final rainfall predictions.

• Reports:

  • Report_Part1.pdf: Detailed documentation of our approach, findings, and modeling process.
  • Report_Part2.pdf: System design diagram and MLOps component descriptions.

---

🛠️ Technologies & Libraries Used

• Python
• Pandas, NumPy
• Matplotlib, Seaborn (Data visualization)
• Scikit-learn, XGBoost (ML modeling)

---

🚀 Getting Started (Reproducing Results)

Follow these steps to reproduce the results:

Step 1: Clone the Repository

git clone <https://github.com/VishwaJaya01/Intellihack_TechSpark_01.git>
cd <Intellihack_TechSpark_01>

Step 2: Install Required Libraries

pip install pandas numpy matplotlib seaborn scikit-learn xgboost

Step 3: Run the Notebook

jupyter notebook weather_forecasting.ipynb

---

📊 Results Overview

• Final optimized model: XGBoost Classifier
• Achieved accuracy: 67%
• Provided clear rainfall probability predictions to assist farming decisions.