Data Pipeline and Analysis Code for paper "Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities" (MeTS-10)
This is a github repo to share code for the MeTS-10 Dataset Paper (pre-print, submitted for review).
The major parts of the speed classification pipeline are provided as a series of scripts that allow to generate a road graph and derive speed classifications from available traffic movies end-to-end.
The following diagram gives an overview:
Find the technical data description in README_DATA_SPECIFICATION.md.
This part contains code to generate the figures in the paper.
conda env update -f environment.yaml
conda activate mets-10
python data_pipeline/dp01_movie_aggregation.py --help
Jupytext
Generate a Jupyter config, if you don’t have one yet, with jupyter notebook --generate-config
edit .jupyter/jupyter_notebook_config.py and append the following:
c.NotebookApp.contents_manager_class="jupytext.TextFileContentsManager"
c.ContentsManager.default_jupytext_formats = ".ipynb,_nb.py"
and restart Jupyter, i.e. run
jupyter notebook
Note: .jupyter is mostly present in your home directory.
See also this post.
For the data pipeline, we run formatter and linter using pre-commit (https://pre-commit.com/), see
configuration .pre-commit-config.yaml:
pre-commit install # first time only
pre-commit run --all
See https://blog.mphomphego.co.za/blog/2019/10/03/Why-you-need-to-stop-using-Git-Hooks.html
In order to temporarily skip running pre-commit, run git commit -n.
Please cite this repo along with the pre-print:
@misc{https://doi.org/10.48550/arxiv.2302.08761,
doi = {10.48550/ARXIV.2302.08761},
url = {https://arxiv.org/abs/2302.08761},
author = {Neun, Moritz and Eichenberger, Christian and Xin, Yanan and Fu, Cheng and Wiedemann, Nina and Martin, Henry and Tomko, Martin and Ambühl, Lukas and Hermes, Luca and Kopp, Michael},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities},
publisher = {arXiv},
year = {2023},
copyright = {arXiv.org perpetual, non-exclusive license}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent