seljukgulcan / comparing-trajectory-clustering-methods Goto Github PK

hi, Shathra
I download the code zip, but i don't know how to run it for my own GPS trajectory data, could you help me to analyze my data? My data include track ID, longitude, latitude and timestamp.
If here is not convenient answer, you can contact me with [email protected].
look forward and really thanks for your help!

Hi Shathra,

I run your demo, fantastic! If i want to plot the picture for every single cluster, such as plot the picture which the cluster is 1, how to change the code? Also, in DBSCAN, how to remove the noisy trajectory?

thanks!

When I tested the kmedios clustering method with my own dataset, I called the silhouette method to evaluate the clustering effect, but why the results of the same data are not the same each time？
This is how I call the method：silhoutte_score = metrics.silhouette_score(D, labels)，Where D denotes distance matrix, labels denotes labels corresponding to each track。When I do the calculation with the same k value, I get different results.

When i am running merger.py ,some error like this: FileNotFoundError: [Errno 2] No such file or directory: '0.traj'

I have readed your other Issues ,can you show some example of 0.traj file ,please .

Thank you very mach

Could you please send me the data zip, my email is [email protected]. Thanks very much!

Hi!

Many thanks for your sharing!
I'm testing your codes. In the codes the files such as 'dense.dat', '1_traj_seg.dt', 'distance1.npz' and 'gaussian_representation.dat' are loaded and they are missing here. Could you please upload them? Many thanks!

Cheers!

The link of the data doesn't works