Visualization of Public Transit Users' Patterns

This repository aims to develop effective visualization technique for public transit users' patterns Based on Unfolded, spatiotemporal movements of transit users' are represented with their estimated qualitative attributes (e.g., trip purposes and socioeconomic factors)

Overview

Spatiotemporal patterns of transit users' trips according to activity duration and trip purposes are visualized. Trip purposes of smart card data are esitimated using CGAN-DF

Getting Started

Dependencies

• Python 3.6.10, Jupyter lab 3.3.0

Components

Dataset

• 'Data' contains the sampled smart card data with trip purposes 'ActivityPattern.csv'
• Other dataset is used to generate the 'ActivityPattern.csv' using 'DataPreprocesing.ipynb' and 'DF-CGAN-Output.ipynb'. More details are provided in CGAN-DF

Visualization_Unfolded.ipynb

• Step-by-step implementation of visualization using unfolded
• Spatial and time-line analysis are presented
• Need to be updated...

'DataPreprocesing.ipynb' and 'DF-CGAN-Output.ipynb'

• This code generates the 'ActivityPattern.csv'. Please refer CGAN-DF

Authors

@Eui-Jin Kim

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

• CGAN-DF
• Unfolded