Walid Benzineb
data_cleaning.py
): Preprocesses the raw data, handling missing values and outliers.exploratory_data_analysis.py
): Performs initial data visualization and statistical analysis to understand the dataset's characteristics.feature_engineering.py
): Creates new features and transforms existing ones to improve model performance.feature_exploratory_data_analysis.py
): Analyzes the engineered features, providing insights into their relationships and potential impact on the target variable.refined_model.py
): Trains the XGBoost model using the preprocessed and engineered features.streamlit_app.py
): Provides a user-friendly interface for interacting with the trained model and visualizing results.data/
directory of the project before running the scripts.calendar.csv
: Contains availability and pricing informationlistings.csv
: Detailed information about each Airbnb listingreviews.csv
: User reviews for the listingslistings.csv
file as it contained the most relevant information for price prediction.data/raw/
directory (see Data section)pip install -r requirements.txt
python src/data_cleaning.py
python src/feature_engineering.py
python src/refined_model.py
streamlit run streamlit_app.py