💼 Employee Salary Prediction Web App

This project is a machine learning-powered web application built using Streamlit that predicts the salary of an employee based on their experience and skillset. The app is designed for ease of use and can be accessed both locally and publicly using ngrok.

📌 Table of Contents

• 📊 Features
• 🧠 Tech Stack
• 📁 Project Structure
• ⚙️ Installation & Setup
• 🚀 How to Use
• 🔍 Model Details
• 🌐 Deployment
• 🖼️ Screenshots
• 🧑‍💻 Author
• 📜 License

📊 Features

• ✅ Predict employee salary based on experience and other features
• 🧠 ML model trained on real-world data using regression
• 🧾 Interactive and user-friendly UI using Streamlit
• 📈 Live display of predicted results
• 🌐 Accessible from anywhere using ngrok tunneling
• 🛠️ Easy to deploy and extend for more features (e.g. role, skills)

🧠 Tech Stack

Component	Technology
UI	Streamlit
Backend	Python
Machine Learning	Scikit-learn
Model Storage	Joblib (.pkl model)
Deployment	ngrok (local → public)

📁 Project Structure:

employee-salary-predictor/

├── app.py
├── model/

│ └── salary_model.pkl
├── data/

│ └── salary_data.csv
├── README.md
├── requirements.txt
└── .gitignore

⚙️ Installation & Setup:

🔹 Step 1: Clone the repository

git clone https://github.com/yourusername/employee-salary-prediction.git cd employee-salary-prediction

🔹 Step 2: Install dependencies

pip install -r requirements.txt Or manually: pip install streamlit scikit-learn pandas joblib pyngrok

🔹 Step 3: Train the model (if not already trained) python train_model.py This generates a model.pkl file.

🔹 Step 4: Run the Streamlit app streamlit run app.py

🚀 How to Use:

• Open the app in your browser (usually at http://localhost:8501)
• Input the employee's experience (in years) and other fields
• Click Predict Salary
• View the estimated salary output instantly

🔍 Model Details:

• Algorithm: Linear Regression
• Input Features:
• Years of Experience
• (Optional) Job Title, Skills, Degree (can be extended)
• Output: Predicted annual salary in INR/USD
• Training: Scikit-learn pipeline with preprocessing and model fitting
• Storage: Saved using joblib as model.pkl

🌐 Deployment:

To make the app publicly accessible using ngrok:

🔸 Install ngrok pip install pyngrok

🔸 Start Streamlit app (Terminal 1) streamlit run app.py

🔸 Start ngrok tunnel (Terminal 2) ngrok http 8501 Copy the generated HTTPS link to access the app publicly.

🖼️ Screenshots:

📌 Future Enhancements:

Add support for job title, domain, and location Use more advanced ML models like Random Forest or XGBoost Deploy on platforms like Streamlit Cloud, Render, or Heroku Add data visualizations using Plotly/Altair

🧑‍💻 Author:

Soundarya 🎓 Computer Science and Engineering Specialization in Artificial Intelligence and Machine Learning, Sarala Birla University 🌐 LinkedIn: https://www.linkedin.com/in/soundarya-60b330288/ | GitHub

📜 License:

This project is licensed under the MIT License.