non hierarchical process stopping

Home Forums PATN and Pattern Analysis PATN Discussion non hierarchical process stopping

  • This topic is empty.
Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
    Posts
  • #396
    brownt
    Member

    Hi Lee and all,

    I am running a non-H classification on 300 000 objects to get 10 final groups. The process starts ok, takes about 3 minutes to get to about half way through (the process bar in the dialogue box is half full) and then suddenly finishes as if the classification had been completed successfully. All objects are allocated a group but the output groups dont really make any sense (I get very unnatural patterns in my maps). In my previous experience, the process takes a little longer and I can watch the process bar until it is full and the classification finishes. Could this be because of not enough processing space on my pc re: large dataset being analysed?

    Cheers,
    Tiff.

    #454
    lee
    Keymaster

    Hi Tiffany

    Sounds strange. A test of PATN generated 300,00 by 20 dataset and 10 groups with Gower Metric worked fine. Random data willbe slow to convergence. Your 3 minutes seems too fast to me, even on a fast PC. Even after a few iterations, the groups should be ok.

    It would be best to send me the dataset as csv file (you can export rom PATN if you don’t have a csv file) and zipped up. That way I can better test your problem.

    Lee

    #455
    brownt
    Member

    Hi lee,

    I have re-calculated and compiled the data in the csv table to be imported into patn and have re-run the non-H classification using this table with great success! There must have been a problem within the data somewhere.

    Thanks,
    Tiff.

    #486
    lee
    Keymaster

    Hi Tif

    I was looking over the Discussion Forum and noticed that no one had responded to this post. Have you solved it? If not, can you tell me more? It seems like an odd situation.

    Cheers,

    Lee

Viewing 4 posts - 1 through 4 (of 4 total)
  • You must be logged in to reply to this topic.