Git Product home page Git Product logo

Comments (6)

dleyan avatar dleyan commented on July 18, 2024

The NYC dataset is provided by https://www.microsoft.com/en-us/research/publication/detecting-collective-anomalies-from-multiple-spatio-temporal-datasets-across-different-domains/. And the BAY dataset is collected from https://pems.dot.ca.gov/. I will update the BAY dataset used in our work to GitHub as soon as possible.
If you just need data for traffic flow prediction, you can refer to the following works.

  1. https://github.com/guoshnBJTU/ASTGNN
  2. https://github.com/p0llx/DeepST-ResNet/tree/master/data/TaxiBJ
  3. https://github.com/liyaguang/DCRNN

from stgan.

zhiyu1998 avatar zhiyu1998 commented on July 18, 2024

I have another question. On your work( load_data.py ), you use the
graph_path = opt['data_path'] + '/node_subgraph.npy' # (num_node, n, n), the subgraph of each node adj_path = opt['data_path'] + '/node_adjacent.txt' # (num_node, n), the adjacent of each node
how can I translate the datasets (node_subgraph.npy、node_adjacent.txt) or download the datasets?
(ps. I have downloaded the datasets that you listed 11 days ago, but I haven't seen the datasets that I mention above. I am really sorry to have incommoded you. T_T) @dleyan

from stgan.

dleyan avatar dleyan commented on July 18, 2024

I have uploaded the two datasets to Github. The node_subgraph.npy and node_adjacent.txt for NYC dataset are translated according to the data_description.pdf and NYC_862.txt provided by (https://www.microsoft.com/en-us/research/publication/detecting-collective-anomalies-from-multiple-spatio-temporal-datasets-across-different-domains/). And the two files for PeMS dataset are translated according to the locations of sensors.

from stgan.

zhiyu1998 avatar zhiyu1998 commented on July 18, 2024

thx a lot, bro. I could close the issue finally~ lol @dleyan

from stgan.

zhiyu1998 avatar zhiyu1998 commented on July 18, 2024

oops, I find a data file that you did not upload it maybe. Just in load_data.py, I have run the code.
dists = torch.tensor(np.loadtxt(self.opt['data_path'] + '/node_dist.txt'), dtype=torch.float) ( in function weight )
I can't find ' node_dist.txt ' that describes two datasets are available at Google Drive in your README.md. I'm really sorry to bother you again.

from stgan.

dleyan avatar dleyan commented on July 18, 2024

I have updated these two datasets.

from stgan.

Related Issues (4)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.