🌡️ Apparent Temperature Prediction System

📌 Overview

This project presents a machine learning-based approach to predict apparent temperature using meteorological data such as humidity, wind speed, visibility, and pressure. The goal is to develop an accurate prediction model using different machine learning techniques.

📊 Dataset

• Source: Kaggle – Weather History Dataset
• Features: Temperature, Humidity, Wind Speed, Wind Bearing, Visibility, Pressure, etc.
• Target: Apparent Temperature (Celsius)

🧠 Models Implemented

• Linear Regression
• Random Forest Regressor
• XGBoost Regressor
• Support Vector Regressor (SVR)

📈 Key Findings

• Random Forest yielded the best performance with near-perfect R² scores.
• XGBoost was highly competitive, delivering consistent and accurate predictions.
• Feature analysis confirmed Temperature as the most important variable.

📁 Folder Structure

Apparent-Temperature-Prediction/
├── src/                     # Python source code
├── notebooks/              # Jupyter Notebook
├── report/                 # Final project report
├── results/                # Visual outputs (optional)
├── data/                   # Dataset folder (excluded from repo)
├── README.md               # Project overview
├── .gitignore              # Ignore temp and system files
└── requirements.txt        # Dependencies

🚀 How to Run

pip install -r requirements.txt
python src/apparenttemperature.py

Or run the analysis notebook:

jupyter notebook notebooks/ApparentTemperature.ipynb

👤 Author

Harshith Penmetsa

Master’s Student – Information Systems, Northern Illinois University
Python Project - Python Programming for Business

📄 License

This project is licensed under the MIT License.