https://housepricemlm.streamlit.app/
This project is a Streamlit-based web application using machine learning models to predict house prices. It allows users to select different models (e.g., Linear Regression, Random Forest), input house features, and visualize the importance of each feature in predicting prices.
🚀 Features
- Machine Learning Models: Supports Linear Regression and Random Forest models for predictions.
- Interactive Inputs: Users can enter house details like square footage, number of bedrooms, and bathrooms to get price predictions.
- Feature Importance Visualization: Provides insights into how each feature impacts the prediction.
- Model Selection: Compare performance across different models.
- User-Friendly Interface: Built with Streamlit for simplicity and accessibility.
I preprocessed the data (handling missing values, encoding categorical features), split it into training and testing sets, and trained models like Linear Regression, Random Forest, Decision Tree, and Neural Network, saving them with joblib for deployment.
This displays the training of the model for linear regression found in the Jupiter notebook
Displays the weightage of each factor that was trained during the model to predict house prices
📦 Dependencies
- streamlit
- pandas
- joblib
- matplotlib
- scikit-learn
Ensure all dependencies are listed in the requirements.txt file for proper installation.