ashish7129 / graph_sampling Goto Github PK

Graph Sampling is a python package containing various approaches which samples the original graph according to different sample sizes.

License: MIT License

Python 100.00%

data-mining big-data big-data-analytics social-network-analysis sampling sample network-analysis network-science random-walk graphs

graph_sampling's People

Contributors

Stargazers

Watchers

Forkers

kirtijain25 rmatam alexmruch minsu-daniel-kim ferplascencia shivamgera jiongweilua xingdu1991 nehachy patrickgsheng shuuwook abhi-neo junhaowang tara-morovatdar rocky-ma joanlenczuk yiwuzhong cwf818 aslandery gitstude jyotirm0y alessi0x zlou melody1235813 serea hsouporto milkigit blacnk-0 yuanhaoliu xinxinniannian318 maithatnj fonylew aaronhd soumbane qwzhong1988 sunnerzs hangzhang10 esince ammuaj ajax4sec sjunhao xgong95 davidlanz chim3ywangmo aries107 sutiliza-org chaogaoucr

graph_sampling's Issues

Confusion with the probability in MHRW

In the implementation of MHRW

        while(len(self.G1.nodes()) < size):
            if(len(node_list) > 0):
                child_node = node_list.pop()
                p =  round(random.uniform(0,1),4)
                if(child_node not in dictt):
                    related_listt = list(G.neighbors(child_node))
                    degree_c = G.degree(child_node)
                    dictt[child_node] = child_node
                    if(p <= min(1,degree_p/degree_c) and child_node in list(G.neighbors(parent_node))):
                        self.G1.add_edge(parent_node,child_node)
                        parent_node = child_node
                        degree_p = degree_c
                        node_list.clear()
                        node_list.update(related_listt)
                    else:
                        del dictt[child_node]

The probability of walking from parent_node to child_node seems to be min(1,degree_p/degree_c) but in the paper the probability should be parent_node.deg() * min(1,degree_p/degree_c), which is not consistent

pip install failed

Installation failed
I followed your instructions:

git clone https://github.com/Ashish7129/Graph-Sampling.git
cd Sampling
pip install -e
See error:

I tried the second way
1.download the zip file and move to its directory.
2.pip install Sampling
3.See error:

--macOS python2.7

The value of the returned edge is not the real value

complete_graph.nodes[n]['id'] = n ? why?

sampled_graph.add_node(chosen_node)
sampled_graph.add_edge(curr_node, chosen_node)

The 'chosen_node' and 'curr_node' are both 'id' and not real values.

Cause the RW to walk according to the id of the node, not the true value of the node.

Confusion with the probability in MHRW

Is your Improvement Request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like
A clear and concise description of what you want to happen.

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context
Add any other context or screenshots about the feature request here.

ashish7129 / graph_sampling Goto Github PK

graph_sampling's People

Contributors

Stargazers

Watchers

Forkers

graph_sampling's Issues

Confusion with the probability in MHRW

pip install failed

The value of the returned edge is not the real value

Confusion with the probability in MHRW

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