Not able to load x, tx files

[Atif-ub]

I am trying to load x, tx files but they are not loading, no error but not loading either. can you suggest what can be the issue.. I Am using python 3.7.

2nd question.. I want to run the same GCN on my own data.. is there any steps how to create dataset for GCN inputs ( both supervised and unsupervised learning). Means how exactly I can create graph, x, tx, graph files.. what data is in it which is then converted into categorical data.

[tkipf]

In terms of loading the .x/.tx files, maybe try python 2.7.

In terms of loading your own data: you don't need to provide .x/.tx files, but instead you can provide a node feature matrix X and graph adjacency matrix A directly. Have a look at the load_data function here for an example: https://github.com/tkipf/pygcn/blob/master/pygcn/utils.py

On Wed, May 8, 2019 at 7:56 PM aubutt [email protected] wrote:

I am trying to load x, tx files but they are not loading, no error but not loading either. can you suggest what can be the issue.. I Am using python 3.7.

2nd question.. I want to run the same GCN on my own data.. is there any steps how to create dataset for GCN inputs ( both supervised and unsupervised learning). Means how exactly I can create graph, x, tx, graph files.. what data is in it which is then converted into categorical data.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/tkipf/gcn/issues/113, or mute the thread https://github.com/notifications/unsubscribe-auth/ABYBYYARMI2KB7BMASX5IY3PUMH57ANCNFSM4HLT4ICQ .

[HeWenxuan1994]

In terms of loading the .x/.tx files, maybe try python 2.7. In terms of loading your own data: you don't need to provide .x/.tx files, but instead you can provide a node feature matrix X and graph adjacency matrix A directly. Have a look at the load_data function here for an example: https://github.com/tkipf/pygcn/blob/master/pygcn/utils.py … On Wed, May 8, 2019 at 7:56 PM aubutt @.***> wrote: I am trying to load x, tx files but they are not loading, no error but not loading either. can you suggest what can be the issue.. I Am using python 3.7. 2nd question.. I want to run the same GCN on my own data.. is there any steps how to create dataset for GCN inputs ( both supervised and unsupervised learning). Means how exactly I can create graph, x, tx, graph files.. what data is in it which is then converted into categorical data. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#113>, or mute the thread https://github.com/notifications/unsubscribe-auth/ABYBYYARMI2KB7BMASX5IY3PUMH57ANCNFSM4HLT4ICQ .

Thanks a lot

[Atif-ub]

This is where I am getting confused. I have node+edge graph with me.

how to create node feature matrix , and graph adjacency matrix A from it. which is comparable to input for GCN.

[Atif-ub]

not loading using Python 2.7.15 as well :(

I figured out how graph matrix(from these variables. x, y, tx, ty, allx, ally, graph) but rest seems processed data from some categorical fields, what are these fields used in those files? (black box for me at the moment)

[tkipf]

This is strange. Maybe try the data loader in https://github.com/tkipf/pygcn -- note, however, that the dataset splits here are different.

On Sat, May 11, 2019 at 10:39 AM aubutt [email protected] wrote:

not loading using Python 2.7.15 as well :(

I figured out how graph matrix(from these variables. x, y, tx, ty, allx, ally, graph) but rest seems processed data from some categorical fields, what are these fields used in those files? (black box for me at the moment)

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/tkipf/gcn/issues/113#issuecomment-491492178, or mute the thread https://github.com/notifications/unsubscribe-auth/ABYBYYC3QT45ODRXRZTZR23PU2A3LANCNFSM4HLT4ICQ .

[DM0815]

This is strange. Maybe try the data loader in https://github.com/tkipf/pygcn -- note, however, that the dataset splits here are different. … On Sat, May 11, 2019 at 10:39 AM aubutt @.***> wrote: not loading using Python 2.7.15 as well :( I figured out how graph matrix(from these variables. x, y, tx, ty, allx, ally, graph) but rest seems processed data from some categorical fields, what are these fields used in those files? (black box for me at the moment) — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#113 (comment)>, or mute the thread https://github.com/notifications/unsubscribe-auth/ABYBYYC3QT45ODRXRZTZR23PU2A3LANCNFSM4HLT4ICQ .

I want to know the dataset why split as follows:

idx_train = range(140)
idx_val = range(200, 500)
idx_test = range(500, 1500)

I cannot understand it,because the normal split ratio is 6:2:2 in smaller dataset. Can you help me or explain it in detail. I'm sorry to bother you