How yashpandey474/salary-prediction-using-machine-learning works
Project type and purpose
• This is a full-stack machine-learning web application for predicting developer salaries from survey inputs.
• It comprises a Streamlit front end (Python Files/app.py), a prediction engine (predictor.py + model_final.py), and pre-trained model artifacts (Model/*.pkl). Notebooks illustrate the model development pipeline and the Datasets folder contains raw data used during training.
File structure
• Top-level folders
• Datasets: raw CSV and survey PDF used for feature engineering and training
• Notebooks: Jupyter notebooks for experimentation and model iteration
• Model: serialized model objects (model.pkl etc.) and a test C file (test.c)
• Python Files: application entry point (app.py), model runner (model_final.py), and helper (predictor.py)
• Configuration files
• requirements.txt: lists Streamlit, pandas, scikit-learn, etc.
• README.md: basic usage instructions
• Presentation Images & GUI Images: static assets shown in slides or in the UI
README for additional insights
• The app runs via streamlit run app.py
• Users choose input values via Streamlit widgets, then click “Predict Salary”
• No external APIs or databases—everything runs locally