I watched some of your videos, and I want to say thank you for your interesting job! One question: regarding modularity, do you know how can I feed my customized modularity label to the network and do coloring, partitioning, etc., using those values?
Yep, just make a spreadsheet with two columns. The first should have the Node ID and have the heading "Id" with that capitalization. The second can have your modularity label. Save that as a CSV. Then go to the data laboratory, select import spreadsheet, select that as your nodes file, and then merge it with the existing workspace. After that, your labels will be available as a color coding option under partitioning.
Hi dear jengolbeck, I have two questions that maybe you could enlighten me about the interpretation of modularity. The value of modularity that ranges between 0 to 0.999 what does it mean? and does it mean something that one group with more nodes could be assigned with 0 o 100 as modularity group? I dont find exact information about that, if you could share a paper about the interpretation in one context, I would be happy. Have a good day.
Hey there! Thank you for the video, I wonder whether the approach Gephi takes for community detection is exactly the one of the Newman's paper "Modularity and community structure in networks." In this case how would you interpret the resolution parameter? Thanks
At the bottom of the HTML report that comes up when you run the modularity algorithm, Gephi lists the citations of the algorithms they use, including for resolution: Algorithm: Vincent D Blondel, Jean-Loup Guillaume, Renaud Lambiotte, Etienne Lefebvre, Fast unfolding of communities in large networks, in Journal of Statistical Mechanics: Theory and Experiment 2008 (10), P1000 Resolution: R. Lambiotte, J.-C. Delvenne, M. Barahona Laplacian Dynamics and Multiscale Modular Structure in Networks 2009
This video has been a frequently used reference of mine. Thanks a lot!
Thanks @jengolbeck for these tutorials. Is there a way to simulate information propagation or SI, SIR, SIS models in Gephi?
How did you filter out the nodes that aren't part of the giant component? Manually or is there an automated filter for this?
right sidebar -> Filters -> Attribute/Partition/Component ID -> drag it to Queries -> choose the first component
Your videos are amazing! Thank you so much!
Is there a way to get metrics on these clusters?
thanks! that was super clear
I watched some of your videos, and I want to say thank you for your interesting job!
One question: regarding modularity, do you know how can I feed my customized modularity label to the network and do coloring, partitioning, etc., using those values?
Yep, just make a spreadsheet with two columns. The first should have the Node ID and have the heading "Id" with that capitalization. The second can have your modularity label. Save that as a CSV. Then go to the data laboratory, select import spreadsheet, select that as your nodes file, and then merge it with the existing workspace. After that, your labels will be available as a color coding option under partitioning.
Hi dear jengolbeck, I have two questions that maybe you could enlighten me about the interpretation of modularity. The value of modularity that ranges between 0 to 0.999 what does it mean? and does it mean something that one group with more nodes could be assigned with 0 o 100 as modularity group? I dont find exact information about that, if you could share a paper about the interpretation in one context, I would be happy. Have a good day.
Hey there! Thank you for the video, I wonder whether the approach Gephi takes for community detection is exactly the one of the Newman's paper "Modularity and community structure in networks." In this case how would you interpret the resolution parameter? Thanks
At the bottom of the HTML report that comes up when you run the modularity algorithm, Gephi lists the citations of the algorithms they use, including for resolution:
Algorithm:
Vincent D Blondel, Jean-Loup Guillaume, Renaud Lambiotte, Etienne Lefebvre, Fast unfolding of communities in large networks, in Journal of Statistical Mechanics: Theory and Experiment 2008 (10), P1000
Resolution:
R. Lambiotte, J.-C. Delvenne, M. Barahona Laplacian Dynamics and Multiscale Modular Structure in Networks 2009
Thanks a lot
can you add a legend to a gephi graph output?
+Lelo Nxumalo I'm not aware of gephi having that capability.
+jengolbeck thanks for getting back to me. Your tutorials are really helpful.
спасибо, но я вижу только пиксели
Video quality is not good.