benedekrozemberczki / graphwavemachine Goto Github PK

For certain graphs, the ordering of the output embeddings may not be consistent with the node labels. It seems that this can be fixed through the addition of the following near the bottom of the transform_and_save_embedding function:

self.real_and_imaginary.index = self.index
self.real_and_imaginary.index = self.real_and_imaginary.index.astype(self.settings.index_type)
self.real_and_imaginary = self.real_and_imaginary.sort_index()

where self.settings.index_type' is set by the user to a simple python type, eg int, string, or float, etc. and self.index=G.nodes()is set in the__init__` function of the class.

Additionally adding the index column to the csv file generated would allow for embeddings to be linked to named, rather than numbered, nodes.
This would be done through changing the bottom line in the transform_and_save_embedding_function to the following: self.real_and_imaginary.to_csv(self.settings.output)

Note, this was tested using a slightly modified read_graph() function as the csv version resulted in a very different graph to the nx.read_edgelist version:

def read_graph(path):
    graph = nx.read_edgelist(path)
    return graph

Also would there be any plans to move towards the nx.read_edgelist implementation as it seems more elegant of a solution?

I don't currently have the time to create a pull request with a fully tested solution to these issues, but the changes suggested should solve most of it (except the user-defined index type).

I already test the package for an edge list and the error showed up.
here's the edge list sample:

_0 C۰۲F 
_0 B۰۱D 
C C۰۲ 
C C۱۲ 
C C۰۵ 

is it because of str data type of the edge list elements?

hello @benedekrozemberczki
when i run the code with python src/main.py for a try. it tells me that module parser do not have parameter_parser.
I am now using python 3.7.3. As far as I know, Python3 itself has the module with the name parser. I changed the file name of parser.py to some other names, and then it works. Hope to change the name.

this is a screenshot (sorry, this is another repo's)

and this is the description of that.

change the name of the file, and then it works. (no GPU version is running...)

? I guess that you are using Python 2.7, instead of Python 3. (sorry, i am now using Microsoft Windows for example, I remembered that when I use Ubuntu to run the same code several months ago, I have met the same problem... (I also use Python 3 in Ubuntu)
And I hope ALL THE parser names can be changed.

yours sincerely,
@WMF1997.

Hello,

Can this implementation replicate the result in the original paper? How about the speed?

Thank you!

why use my data to text ,the whole node embedding output the same result?

Hello, thank you for contributing GraphWave code. I run this code and notice that this is only the process of learning the node representations, and does not evaluate performance. However, I try to do this task following the previous work, and I do not achieve. Thus, I hope that you can do this task about this code. If you can, I will thank you very much.

Hi how do I install the package. I was not able to install it via pip. I tried cloning the repo into a folder but when I import graphwave it is having issues importing.