/Laptop-Price-Prediction

This project aims to help consumers estimate laptop prices based on features, addressing the challenge of choosing the right laptop for work, education, or entertainment. The goal is to provide a useful tool for consumers to predict laptop prices more accurately.

Primary LanguageJupyter Notebook

Laptop Price Prediction Website

This project provides a comprehensive guide on building a website for predicting laptop prices based on various features. It includes data collection, preprocessing, model building, Flask server development, and website creation.

lap

image

Project Overview

The project aims to build a website where users can predict the price of a laptop based on features such as brand, RAM, weight, operating system, GPU, etc.

Project Phases

  1. Data Collection and Preprocessing:

    • Dataset collected from Kaggle.
    • Data cleaning and preprocessing steps performed.

  2. Model Building and Evaluation:

    • Various regression models evaluated.
    • Random Forest model selected with 88% accuracy.

  3. Development of Flask Server:

    • Python Flask used to create an HTTP server.
    • Server serves predictions using the saved model.

  4. Website Development:

    • Website built using HTML, CSS, and JavaScript.
    • Integration with Flask server to retrieve predicted price.

Features of Dataset

  • Brand
  • Laptop Type
  • RAM
  • Weight
  • Operating System
  • GPU
  • Touchscreen Availability
  • IPS Display
  • Hard Drive Capacity
  • SSD Capacity
  • Screen Size
  • Screen Resolution
  • Processor

Technology and Tools Used

  1. Python
  2. Numpy and Pandas
  3. Matplotlib
  4. Scikit-learn
  5. Flask
  6. HTML/CSS/JavaScript
  7. Jupyter Notebook and Visual Studio
  8. NGINX webserver
  9. AWS EC2

Project Flow

  1. Data Collection and Cleaning
  2. Model Building
  3. Flask Server Development
  4. Website Deployment

Conclusion

This project covers a wide range of data science concepts and technologies, from data cleaning and preprocessing to model building, evaluation, and web development. It provides a hands-on learning experience for anyone interested in building predictive models and deploying them as web applications.