Exploring the correlation between public transport stops and rental prices in Nuremberg to provide insights for optimizing transportation networks and housing accessibility. Utilizes datasets on Nuremberg Stops and Immoscout24 listings, employing data analysis and visualization techniques.
This project is associated with the "AMSE/SAKI 2023 Project" under the "AI Systems and Applications" pillar, part of the Master of Science in Artificial Intelligence degree at Friedrich-Alexander-Universität Erlangen-Nürnberg and FAU Open-Source Software. Check out the original coursework/project at AMSE Repo
pipeline.py
: The main executable script that processes data and generates the SQLite database.LatLngExtractor.py
: Script to extract latitude and longitude data for the analysis.exploratory_data_analysis.ipynb
: Jupyter notebook containing the exploratory data analysis.report.ipynb
: Jupyter notebook with a comprehensive report of the findings.nuremberg_stops_immoscout.sqlite
: The SQLite database generated bypipeline.py
.driver.sh
: Shell script to run the pipeline and lat/lng extraction process.requirements.txt
: File containing all the dependencies to be installed.- Visualizations:
frequency_map.html
: Interactive map showing the frequency of apartment listings by town.rental_map.html
: Interactive map indicating rental prices across Nuremberg.listing_pie.png
: Pie chart visualization of apartment listing frequencies.listing_bar.png
: Bar chart visualization of apartment listing frequencies.
- Clone the repository:
git clone https://github.com/gmMustafa/NurembergTransitRentAnalysis
- Navigate to the cloned repository directory.
- Install dependencies:
pip install -r requirements.txt
- Run the data pipeline:
This will generate the
python pipeline.py
nuremberg_stops_immoscout.sqlite
database. - To perform the exploratory data analysis, run the
LatLngExtractor.py
script first:python LatLngExtractor.py
- Open and review the
exploratory_data_analysis.ipynb
notebook for preliminary analysis. - For a detailed analysis, open and review the
report.ipynb
notebook.
The repository includes interactive maps (frequency_map.html
and rental_map.html
) that provide a visual representation of the dataset's geographical information.
Additionally, the pie and bar chart images (`listing_pie.png` and `listing_bar.png`) offer a clear distribution of apartments based on their location in Nuremberg.
For a complete walkthrough of the analysis process and findings, refer to the Jupyter notebooks included in the repository. or For a detailed exploration of the project's methodology, evaluation, and insights, refer to the presentation slides in the repo.
Feel free to fork the repository, submit pull requests, or suggest improvements by opening an issue.
This project is licensed under the MIT License - see LICENSE for details.