Handling dictionary generator from graph calculus with Networkx

Question

Here my probleme :

Assuming this graph :

import networkx as nx
import pandas as pd

user_network_G = user_trust_cardinality_network.subgraph([30,40,71,145,638,783,893])

nan_edge = [(u, v) for (u, v, d) in user_network_G.edges(data=True) if math.isnan(d["Trust"])]
real_edge = [(u, v) for (u, v, d) in user_network_G.edges(data=True) if math.isnan(d["Trust"]) == False]

pos = nx.kamada_kawai_layout(user_network_G) 

# nodes
nx.draw_networkx_nodes(user_network_G, pos, node_size=700)

# edges
nx.draw_networkx_edges(user_network_G, pos, edgelist = real_edge, width=2)
nx.draw_networkx_edges(user_network_G, pos, edgelist = nan_edge, width=2, style="dashed")

# labels
nx.draw_networkx_labels(user_network_G, pos, font_size=12, font_family="sans-serif")
nx.draw_networkx_edge_labels(user_network_G, pos, edge_labels = nx.get_edge_attributes(user_network_G,'Trust') , font_size=10, font_family='sans-serif', label_pos = 0.6)
nx.draw_networkx_edge_labels(user_network_G, pos, edge_labels = nx.get_edge_attributes(user_network_G,'Intersection') , font_size=10, font_family='sans-serif', label_pos = 0.4)


plt.axis("off")

plt.show()

Giving :

Where :

• The integers on the edges are the cardinality of products set in common between two users (the nodes)
• The decimals on the edges are the truth score between two nodes (i.e two users)

Now i want to compute the edge value of non existing edges between two nodes (for example between node 30 and node 40).

To achieve this i firstly create my graph (the one depicted above) :

user_trust_cardinality_network = nx.from_pandas_edgelist(user_local_trust_computation(normalized_user_rating_matrix)[1].reset_index(level = ['User_U','User_V']), 'User_U', 'User_V', ['Trust', 'Intersection', 'Pondered_Trust'])
#Creation of the graph from a table containing for each existing paire of nodes the Trust Score, the Cardinality and the Pondered_Trust_Score

user_trust_cardinality_network.remove_edges_from(nx.selfloop_edges(user_trust_cardinality_network))
#Remove selfloop edges

edges_to_predict = [(u, v) for (u, v, d) in user_trust_cardinality_network.edges(data=True) if math.isnan(d["Trust"]) == True]
#Storing the set of edges to predict (edges where trust is NaN)

edges_to_predict_sub = [(u, v) for (u, v, d) in user_trust_cardinality_network.subgraph([30,40,71,145,638,783,893]).edges(data=True) if math.isnan(d["Trust"]) == True]
#Edges to predict on my subgraph (for quick example computation)

user_trust_cardinality_network.remove_edges_from([(u, v) for (u, v, d) in user_trust_cardinality_network.edges(data=True) if math.isnan(d["Trust"]) == True])
#Remove edges to predict, to add them after with the newly computed score

Then i compute the score of the removed edges with :

def short_path_trust (graph, edges_to_predict,cutoff) :

    short_path_trust_dict = {}
    
    for (u,v) in edges_to_predict :
        for edges_path in nx.all_simple_edge_paths(graph, u, v, cutoff):
            pondered_trust = [d['Pondered_Trust'] for (x,y,d) in graph.edges.data() if (x,y) in edges_path or (y,x) in edges_path]
            intersection = [d['Intersection'] for (x,y,d) in graph.edges.data() if (x,y) in edges_path or (y,x) in edges_path]
            short_path_trust_dict = {'Path%s' % [u,v] : sum(pondered_trust)/sum(intersection)}
            print(short_path_trust_dict)

Giving me this :

short_path_trust(user_trust_cardinality_network.subgraph([30,40,71,145,638,783,893]), edges_to_predict_sub, 2)

{'Path[40, 30]': 0.08499999999999999}
{'Path[40, 30]': 0.16333333333333333}
{'Path[40, 638]': 0.07833333333333332}
{'Path[40, 638]': 0.10333333333333333}
{'Path[40, 638]': 0.1572}
{'Path[145, 30]': 0.075}
{'Path[145, 30]': 0.05444444444444444}
{'Path[30, 638]': 0.017499999999999998}
{'Path[30, 638]': 0.01}
{'Path[30, 893]': 0.16555555555555557}
{'Path[30, 893]': 0.19486486486486487}
{'Path[893, 638]': 0.1581578947368421}
{'Path[893, 638]': 0.062}
{'Path[893, 638]': 0.19}

My problem is that the result seems to be a dictionary generator, hence a set of independent dictionnaries. It's not a dictionary of dictionary (i already invegasting this possibility), here the proof :

def short_path_trust (graph, edges_to_predict,cutoff) :

    short_path_trust_dict = {}
    
    for (u,v) in edges_to_predict :
        for edges_path in nx.all_simple_edge_paths(graph, u, v, cutoff):
            pondered_trust = [d['Pondered_Trust'] for (x,y,d) in graph.edges.data() if (x,y) in edges_path or (y,x) in edges_path]
            intersection = [d['Intersection'] for (x,y,d) in graph.edges.data() if (x,y) in edges_path or (y,x) in edges_path]
            short_path_trust_dict = {'Path%s' % [u,v] : sum(pondered_trust)/sum(intersection)}
            print(type(short_path_trust_dict))

Return :

short_path_trust(user_trust_cardinality_network.subgraph([30,40,71,145,638,783,893]), edges_to_predict_sub, 2)

<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>
<class 'dict'>

Here is my main problem, if i call for creating a database :

def short_path_trust (graph, edges_to_predict,cutoff) :

    short_path_trust_dict = []
    
    for (u,v) in edges_to_predict :
        for edges_path in nx.all_simple_edge_paths(graph, u, v, cutoff):
            pondered_trust = [d['Pondered_Trust'] for (x,y,d) in graph.edges.data() if (x,y) in edges_path or (y,x) in edges_path]
            intersection = [d['Intersection'] for (x,y,d) in graph.edges.data() if (x,y) in edges_path or (y,x) in edges_path]
            short_path_trust = [((u,v), sum(pondered_trust)/sum(intersection))]
            short_path_trust_df = pd.DataFrame(short_path_trust, columns= ['Nodes','Path_Trust'])
            print(short_path_trust_df)

I get :

short_path_trust(user_trust_cardinality_network.subgraph([30,40,71,145,638,783,893]), edges_to_predict_sub, 2)

     Nodes  Path_Trust
0  (40, 30)       0.085
      Nodes  Path_Trust
0  (40, 30)    0.163333
       Nodes  Path_Trust
0  (40, 638)    0.078333
       Nodes  Path_Trust
0  (40, 638)    0.103333
       Nodes  Path_Trust
0  (40, 638)      0.1572
       Nodes  Path_Trust
0  (145, 30)       0.075
       Nodes  Path_Trust
0  (145, 30)    0.054444
       Nodes  Path_Trust
0  (30, 638)      0.0175
       Nodes  Path_Trust
0  (30, 638)        0.01
       Nodes  Path_Trust
0  (30, 893)    0.165556
       Nodes  Path_Trust
0  (30, 893)    0.194865
        Nodes  Path_Trust
0  (893, 638)    0.158158
        Nodes  Path_Trust
0  (893, 638)       0.062
        Nodes  Path_Trust
0  (893, 638)        0.19

Yet, my goal is to get one DataFrame like this :

   Nodes     Path_Trust
0  (40, 30)       0.085
1  (40, 30)    0.163333
2  (40, 638)   0.078333
3  (40, 638)   0.103333
4  (40, 638)     0.1572
5  (145, 30)      0.075
6  (145, 30)   0.054444
7  (30, 638)     0.0175
8  (30, 638)       0.01
9  (30, 893)   0.165556
10 (30, 893)   0.194865
11 (893, 638)  0.158158
12 (893, 638)     0.062
13 (893, 638)      0.19

Or, better :

  Node1 Node 2     Trust
0  40    30        0.085
1  40    30     0.163333
2  40    638    0.078333
3  40    638    0.103333
4  40    638      0.1572
5  145   30        0.075
6  145   30     0.054444
7  30    638      0.0175
8  30    638        0.01
9  30    893    0.165556
10 30    893    0.194865
11 893   638    0.158158
12 893   638       0.062
13 893   638        0.19

I hope i well explained my problem. If you need more informations i'll do my best to provide them. Thanks for helping :)