split set to spanning tree by default as well the fe_ratio to 1. Fix the...

split set to spanning tree by default as well the fe_ratio to 1. Fix the spatial graph generator. Change requirements.txt

evalNE_script.py

@@ -41,9 +41,9 @@ log("Building link prediction dataset...")
 # Create an evaluator and generate train/test edge split
 traintest_split = LPEvalSplit()
 try:
-    traintest_split.compute_splits(G,split_alg="fast",train_frac=0.6,fe_ratio=1)
+    traintest_split.compute_splits(G, split_alg="spanning_tree", train_frac=0.9, fe_ratio=1)
 except ValueError:
-    traintest_split.compute_splits(G, split_alg="spanning_tree", train_frac=0.6, fe_ratio=1)
+    traintest_split.compute_splits(G, split_alg="fast", train_frac=0.9, fe_ratio=1)
 nee = LPEvaluator(traintest_split)
 
 log("Dataset Built !")
@@ -63,7 +63,7 @@ methods = ['random_prediction',
     "spatial_link_prediction"
            ]
 
-# Evaluate baselines
+# Evaluate heristics
 pbar = tqdm(methods,disable= (not args.verbose))
 for method in pbar:
     pbar.set_description("Evaluate "+method)

generate_random_graph.py

@@ -37,7 +37,7 @@ for i in range(args.n): # For a number of graph
     for size in args.dimensions: # Per size
         test = sample_with_pandas(df,size) # sample edges using the normalised FB social interconnectedness indew
         G = nx.from_pandas_edgelist(test, source="user_loc",target="fr_loc", edge_attr="weight", create_using=nx.Graph())
-        nx.write_gexf(G,args.output_dir + "/fb_country_country_sample_{0}_size{1}.gexf".format(i, size))
+        nx.write_gml(G,args.output_dir + "/fb_country_country_sample_{0}_size{1}.gml".format(i, size))
         #output_df = to_edgelist(test,encoder,weight=True) # Parse to edgelist format
         #output_df.to_csv(args.output_dir + "/fb_country_country_sample_{0}_size{1}.txt".format(i,size),index=False,header= False,sep=",") # Save the output
 

generate_theoric_random_graph.py

@@ -19,6 +19,7 @@ args = parser.parse_args()
 
 GRAPH_SIZE = [80,800]
 EDGE_SIZE = [2,3]
+sample_per_params  = 1
 
 OUTPUT_DIR = args.output_dir
 if not os.path.exists(OUTPUT_DIR):
@@ -50,29 +51,24 @@ parameters = {
 }
 
 
-#getattr(nx,"geographical_threshold_graph")(**dict(n=20,theta=0.4))
-
-
-
 def get_params(inp):
     return (dict(zip(inp.keys(), values)) for values in itertools.product(*inp.values()))
 
-
-
 pbar = tqdm(parameters.items(),total=len(parameters))
 for method,args in pbar:
     pbar.set_description("Generating graphs using : " + method)
     list_of_params = get_params(parameters[method])
     func = getattr(ra,method)
     for ix,params in enumerate(list_of_params):
-        params["nb_edges"] = params["nb_edges"]*params["nb_nodes"]
-        print(params)
-        try:
-            G = func(**params)
-            G.graph.update(params)
-            nx.write_gml(G, OUTPUT_DIR+"/graph_{method}_{ix}.gml".format(method=method,ix=ix),stringizer=str)
-        except Exception as e:
-            print(e)
-            print("Can't generate graphs using these parameters")
+        params["nb_edges"] = params["nb_edges"] * params["nb_nodes"]
+        print("Gen graph using the following parameters : ",params)
+        for sp_id in range(sample_per_params):
+            try:
+                G = func(**params)
+                G.graph.update(params)
+                nx.write_gml(G, OUTPUT_DIR+"/graph_{method}_{ix}{sp_id}.gml".format(method=method,ix=ix,sp_id=sp_id),stringizer=str)
+            except Exception as e:
+                print(e)
+                print("Can't generate graphs using these parameters")
 
 

lib/random.py

@@ -186,7 +186,7 @@ def spatial_graph(nb_nodes, nb_edges, coords="country", dist_func=lambda a, b: n
         for j in range(nb_nodes):
             if i == j and not self_link:
                 continue
-            data.append([i, j, 1/(1+(dist_func(coords[i], coords[j])**2))])
+            data.append([i, j, 1/((1+dist_func(coords[i], coords[j])**4))])
     df = pd.DataFrame(data, columns="src tar weight".split()).astype({"src": int, "tar": int})
     df["hash"] = df.apply(lambda x: "_".join(sorted([str(int(x.src)), str(int(x.tar))])), axis=1)
     df = df.drop_duplicates(subset="hash")

requirements.txt

@@ -2,3 +2,5 @@ pandas
 numpy
 sklearn
 seaborn
+haversine
+geopandas