Skip to content

auckland-cosmo/flowstock

Repository files navigation

flowstock

Estimate flows of people from snapshots using the method of [Akagi2018].

There are two parts to this package

  • a fake data generator
  • an estimator

A couple IPython notebooks are included as demonstrations. One of these generates fake data and attempts to recover the underlying parameters. It is most useful for demonstration and testing.

Another is designed to run on real world data. It requires the user to supply additional data: counts of people in New Zealand SA2 regions and properties of those regions. The later information is available from StatsNZ:

We have assumed that the centroid-to-centroid distance separating regions is an appropriate metric. In principle, the user can specify an arbitrary distance measure on the space, allowing distances to be set by actual driving time, non-local travel via airports, or even asymmetry during commutes.

There are still some rough edges and there may be more corner cases to be taken care of.

Installation

pip

The package is available on pypi.org.

pip install flowstock
pytest

To run tests during the install process,

pip install --install-option test flowstock

source

A conda environment specification is included. This environment has been tested on Linux and OS X.

conda env create -f environment.yml
conda activate flowstock
pip install -e .
pytest
[Akagi2018]
  1. Akagi, T. Nishimura, T. Kurashima, and H. Toda, “A Fast and Accurate Method for Estimating People Flow from Spatiotemporal Population Data,” in Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden, Jul. 2018, pp. 3293–3300, doi: 10.24963/ijcai.2018/457.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •