A Machine Learning predictive project which analyzes diverse laptop specifications to accurately estimate laptop prices using ensemble learning methods.
Feel free to explore the details in the Jupyter Notebook and interact with the deployed model on our website.
This is a learning project which was built along with a youtube video showing the basics of an ML project.It delves into the complex interplay of features, brand dynamics, and technical specifications to provide a comprehensive exploration of laptop pricing.
You can find the deployed model here.
- Dataset imported and cleaned.
- Features engineered and insights gained using EDA.
- Relevant festures used for modelling and ML models employed to predict laptop prices.
- Ensemble methods like Random Forest and Voting Regressor demonstrated superior accuracy.
- Model Deployed using
pickleand Streamlit used for creating UI. - Website deployed using Render.
Find all the code in the laptop-price-predictor.ipynb file.
-
Clone the project
-
Navigate into the project folder
-
To install dependencies run
pip install -r requirements.txt
-
To serve on localhost run
streamlit run app.py
