error in Node2Vec_LayerSelect.py", line 47, in node2vec_walk if len(cur_nbrs) > 0: about mne

[panda0881]

That is because you are using a different version of networkx. But you should be able to solve the problem easily by following this link:
pgmpy/pgmpy#927

Hongming

[Sandy4321]

great thanks for soon answer
sorry but this not helping, my guess they use iterators in version, so code crushes when cur_nbrs become empty
there is an error now

File "e:\graphs ML\code\MNE_28May_removed_LINE_NX_bugfix\MNE-master\MNE_May28_changed_main.py", line 537, in <module>
  performance_1, performance_2, performance_3 = Evaluate_PMNE_methods(merged_networks)
File "e:\graphs ML\code\MNE_28May_removed_LINE_NX_bugfix\MNE-master\MNE_May28_changed_main.py", line 412, in Evaluate_PMNE_methods
  MK_walks = MK_G.simulate_walks(args.num_walks, args.walk_length)
File "e:\graphs ML\code\MNE_28May_removed_LINE_NX_bugfix\MNE-master\Node2Vec_LayerSelect.py", line 78, in simulate_walks
  walks.append(self.node2vec_walk(walk_length=walk_length, start_node=node, G=G))
File "e:\graphs ML\code\MNE_28May_removed_LINE_NX_bugfix\MNE-master\Node2Vec_LayerSelect.py", line 50, in node2vec_walk
  walk.append(cur_nbrs[alias_draw(alias_nodes_list[G][cur][0], alias_nodes_list[G][cur][1])])

builtins.TypeError: 'dict_keyiterator' object is not subscriptable

variables involved have this values

alias_nodes_list[G][cur][0]
array([0, 0, 0, 0])
alias_nodes_list[G][cur][1]
array([1., 1., 1., 1.])
list(cur_nbrs) 
[]
len(  list(cur_nbrs)  ) > 0
False
len(walk)
1
cur_nbrs
<dict_keyiterator object at 0x0000027B34021318>

hopefully, you will be able to fix the code
thanks

[Sandy4321]

ok I changed code in Node2Vec_LayerSelect.py
like this

            #if len(cur_nbrs) > 0:  # original
            if len(  list(cur_nbrs)  ) > 0:  # May28
                # if len(walk) == 1: # original
                if (len(walk) == 1):
                    if len(  list(cur_nbrs)  ) ==0 : # May28
                        break
                    walk.append(cur_nbrs[alias_draw(alias_nodes_list[G][cur][0], alias_nodes_list[G][cur][1])])
                else:
                    if len(  list(cur_nbrs)  ) == 0 : # May28
                        break                    
                    prev = walk[-2]
                    if (prev, cur) not in alias_edges_list[G].keys():
                        prev = cur_nbrs[alias_draw(alias_nodes_list[G][cur][0], alias_nodes_list[G][cur][1])]
                    next = cur_nbrs[
                        alias_draw(alias_edges_list[G][(prev, cur)][0], alias_edges_list[G][(prev, cur)][1])]
                    walk.append(next)
                    # print("ending graph", graphs.index(G))
            else:
                break

        return walk

now it runs till end
results are

Performance of PMNE method three: 0.5070752895752896
Overall MRNE AUC: [0.85530911 0.89128434 0.85494857 0.88142803 0.87209294]
Overall node2Vec AUC: [0.79673615 0.78516926 0.79151336 0.79038582 0.80425014]
Overall Deepwalk AUC: [0.79673615 0.78516926 0.79151336 0.79038582 0.80425014]
Overall Common neighbor AUC: [0.79341216 0.77095724 0.81174762 0.79144072 0.82143098]
Overall Jaccard AUC: [0.78594836 0.7573275  0.77645476 0.76385326 0.80092905]
Overall AA AUC: [0.79861245 0.77773324 0.81499524 0.79813168 0.82742278]
Overall PMNE 1 AUC: [0.8383639  0.80039359 0.81269524 0.79948008 0.82573359]
Overall PMNE 2 AUC: [0.82370174 0.85150146 0.8312381  0.84353256 0.86548263]
Overall PMNE 3 AUC: [0.50269788 0.51138484 0.5002     0.5231827  0.50707529]



Overall MRNE AUC: 0.87101259684976
Overall node2Vec AUC: 0.7936109460183672
Overall Deepwalk AUC: 0.7936109460183672
Overall Common neighbor AUC: 0.7977977449898879
Overall Jaccard AUC: 0.7769025866099335
Overall AA AUC: 0.8033790774301999
Overall PMNE 1 AUC: 0.8153332784387887
Overall PMNE 2 AUC: 0.84309129435558
Overall PMNE 3 AUC: 0.5089081414650802



Overall MRNE std: 0.014319526236232036
Overall node2Vec std: 0.0064656437019227605
Overall Deepwalk std: 0.0064656437019227605
Overall Common neighbor std: 0.017511064039483683
Overall Jaccard std: 0.015574123699654446
Overall AA std: 0.016858231700063453
Overall PMNE 1 std: 0.014966987984306158
Overall PMNE 2 std: 0.01475635805702641
Overall PMNE 3 std: 0.008095129002580756
end

is it correct?

[Sandy4321]

which one of results is for MNE as stated in a paper fro Vickers in Table 2

MNE 0.871 (0.014)

[Sandy4321]

node2Vec and Deepwalk are identical even for std , in paper std is different

Overall node2Vec AUC: [0.79673615 0.78516926 0.79151336 0.79038582 0.80425014]
Overall Deepwalk AUC: [0.79673615 0.78516926 0.79151336 0.79038582 0.80425014]
Overall node2Vec AUC: 0.7936109460183672
Overall Deepwalk AUC: 0.7936109460183672
Overall node2Vec std: 0.0064656437019227605
Overall Deepwalk std: 0.0064656437019227605

[panda0881]

As we are conducting 5-fold cross-validation, the first group reports all of the performance, the second group reports the average, and the last group reports the std.

For the identical question, it is normal, because this sample network is very small (only 29 nodes). I checked and tested the code on my pc, the code is correct. If you try a larger network, that should be different.

By the way, I double-check the paper, the performance of Deepwalk and Node2vec are the same (including std) on small networks but different on the large network.

Hongming

[Sandy4321]

I see thanks
is output
Overall MRNE AUC: 0.87101259684976
stands for performance from Table 2
MNE 0.871 (0.014)
??

[panda0881]

yes Sandy4321 <[email protected]> 于 2018年5月29日周二 下午11:03写道：

…

I see thanks is output Overall MRNE AUC: 0.87101259684976 stands for performance from Table 2 MNE 0.871 (0.014) ?? — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#4 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AM7XSAg9fVysPtefsiNBwAeR9D5qCavAks5t3WNEgaJpZM4UPQuT> .

[Sandy4321]

great thanks for soon answer