benedekrozemberczki / splitter Goto Github PK

A Pytorch implementation of "Splitter: Learning Node Representations that Capture Multiple Social Contexts" (WWW 2019).

License: GNU General Public License v3.0

Python 100.00%

deepwalk pytorch node2vec gensim ego-splitting machine-learning word2vec factorization implicit-factorization deep-learning

splitter's People

Contributors

Stargazers

Watchers

Forkers

vseledkin sandy4321 afcarl matic0209 tonydeep panda4us agatan dantodor ersawant johndpope youjin-c codeaudit hunglethanh9 onyukang jisungyoon namerspace seongl ariacheng science4fun batermj mosaddek-hossain peisenli papachristoumarios shouhengtuo belvo xw-jia mathildasu rjcc 1oscar qianrenjian aneeshks wangludewdrop joskid trendingtechnology hengd-ccnu hugmatj jamal-dev patisu01 ctspencer alirezabayatmk ertpl adasken 18504764619 xhmy

splitter's Issues

`community` module not found

Hi, I'm trying to test the splitter embedding and encountered this issue of not being able to find the community module, which is being imported in ego_splittying.py. And I think I've installed all the required packages.

Splitter/src/ego_splitting.py

Line 3 in b5b330f

import community

Abnormal results of embedding

When i run this model in different datasets (e.g blogcatalog), Some of the dimensions of the vector are greater than or less than negative 1, for example, (1.0,-7.087762355804443,-26.554523468017578,4.721840858459473, ...)

blogcatalog.zip

IndexError: index ... is out of bounds for axis 0 with size ...

I'm getting the same error.

Traceback (most recent call last):
  File "/home/shady/Projects/GML/SPLITTER/Splitter/src/main.py", line 24, in <module>
    main()
  File "/home/shady/Projects/GML/SPLITTER/Splitter/src/main.py", line 19, in main
    trainer.fit()
  File "/home/shady/Projects/GML/SPLITTER/Splitter/src/splitter.py", line 229, in fit
    self.setup_model()
  File "/home/shady/Projects/GML/SPLITTER/Splitter/src/splitter.py", line 159, in setup_model
    self.egonet_splitter.personality_map)
  File "/home/shady/Projects/GML/SPLITTER/Splitter/src/splitter.py", line 52, in initialize_weights
    persona_embedding = np.array([base_node_embedding[n] for _, n in mapping.items()])
  File "/home/shady/Projects/GML/SPLITTER/Splitter/src/splitter.py", line 52, in <listcomp>
    persona_embedding = np.array([base_node_embedding[n] for _, n in mapping.items()])
IndexError: index 8637 is out of bounds for axis 0 with size 8637

The dataset is sorted and also IDs start from zero with no index and header. Also, it just happens on the CA-HepTh dataset and not others which is strange.

ImportError: cannot import name 'parameter_parser'

To solve this issue just rename the parser file, it detects it as the python's parser.

AttributeError: module 'networkx' has no attribute 'selfloop_edges'

Hello, I followed the instruction to install all the required python packages but when I ran 'python3 src/main.py', I got the following error. Could you please let me know how I can fix it? Thank you!

Traceback (most recent call last):
File "src/main.py", line 24, in
main()
File "src/main.py", line 17, in main
graph = graph_reader(args.edge_path)
File "/Users/machunyu/KoslickiLab/Splitter/src/utils.py", line 26, in graph_reader
graph.remove_edges_from(nx.selfloop_edges(graph))
AttributeError: module 'networkx' has no attribute 'selfloop_edges'

an unexpected keyword argument 'iter' in walker?

Hello! I am new in this work ,but when I try to run the code , the error "an unexpected keyword argument 'iter" occured in the function def learn_base_embedding(self) in walkers.py. It seems that the parameter 'iter' in
model = Word2Vec(self.paths, size=self.args.dimensions, window=self.args.window_size, min_count=1, sg=1, workers=self.args.workers, iter=1) is wrong ?

an error in walker maybe?

I dont know much about this work in details. however, while implementing i am running into sample larger than population. I think in src/walker.py it should be

def small_walk(self, start_node):
        """
        Doing a truncated random walk.
        :param start_node: Start node for random walk.
        :return walk: Truncated random walk with fixed maximal length.
        """
        walk = [start_node]
        while len(walk) < self.args.walk_length:
            if len(nx.neighbors(self.graph,walk[-1])) ==0:
                break
            walk = walk + [random.sample(nx.neighbors(self.graph,walk[-1]),1)[0]]
        return walk

Instead of

def small_walk(self, start_node):
        """
        Doing a truncated random walk.
        :param start_node: Start node for random walk.
        :return walk: Truncated random walk with fixed maximal length.
        """
        walk = [start_node]
        while len(walk) < self.args.walk_length:
            walk = walk + [random.sample(nx.neighbors(self.graph,walk[-1]),1)[0]]
            if len(nx.neighbors(self.graph,walk[-1])) ==0:
                break
        return walk

Index Error

I'm getting this error while running your code:

File "C:\Users\ANJALI\environments\splitter\src\splitter.py", line 41, in <listcomp>
persona_embedding = np.array([base_node_embedding[original_node] for node, original_node in mapping.items()])
IndexError: index 599 is out of bounds for axis 0 with size 599

The number of nodes in my graph are 599. What is the cause for this error?

benedekrozemberczki / splitter Goto Github PK

splitter's People

Contributors

Stargazers

Watchers

Forkers

splitter's Issues

`community` module not found

Abnormal results of embedding

IndexError: index ... is out of bounds for axis 0 with size ...

ImportError: cannot import name 'parameter_parser'

AttributeError: module 'networkx' has no attribute 'selfloop_edges'

an unexpected keyword argument 'iter' in walker?

an error in walker maybe?

Index Error

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent