This project series provides a step-by-step guide on building a real estate price prediction website. We will start by constructing a model using scikit-learn and linear regression, utilizing the Bangalore home prices dataset from Kaggle.com. The subsequent steps involve creating a Python Flask server that employs the saved model to serve HTTP requests. Additionally, we will build a website using HTML, CSS, and JavaScript, enabling users to input home square footage, bedrooms, and other parameters to retrieve the predicted price by invoking the Python Flask server.
Throughout the model building process, we will cover various data science concepts, including data loading and cleaning, outlier detection and removal, feature engineering, dimensionality reduction, grid search CV for hyperparameter tuning, and k-fold cross-validation. The project employs the following technologies and tools:
Python
NumPy and Pandas for data cleaning
Matplotlib for data visualization
Scikit-learn for model building
Jupyter Notebook, Visual Studio Code, and PyCharm as IDEs
Python Flask for the HTTP server
HTML/CSS/JavaScript for the user interface
