Update

evalNE_script.py

@@ -3,27 +3,48 @@ from evalne.evaluation.split import EvalSplit as LPEvalSplit
 from evalne.evaluation.score import Scoresheet
 from evalne.utils import preprocess as pp
 import networkx as nx
+from tqdm import tqdm
 
 from lib.utils import load_edgelist
 
 import argparse
 
 parser = argparse.ArgumentParser()
-parser.add_argument("edgelist_graph_filename")
-parser.add_argument("--ne","--network-embedding",action="store_true",help="If you want to use neural network embedding for link prediction")
+parser.add_argument("graph_filename")
+parser.add_argument("-n","--network-embedding",action="store_true",help="If you want to use neural network embedding for link prediction")
 parser.add_argument("-v","--verbose",action="store_true")
+parser.add_argument("-f","--format",default="gexf",choices=["gexf","gml","txt"])
 
-args = parser.parse_args()#("data/fb_country_country_sample_6_size1000.txt".split())
+args = parser.parse_args()
+
+def log(x):
+    if args.verbose:
+        print(x)
 
 # Load and preprocess the network
-G = nx.read_gexf(args.edgelist_graph_filename)#load_edgelist(args.edgelist_graph_filename,is_directed=True,weighted=True)
-G, _ = pp.prep_graph(G,maincc=True)
+log("Load Input Graph...")
+G = None
+if args.format == "txt":
+    G = load_edgelist(path=args.graph_filename,weighted=True)
+elif args.format == "gml":
+    G = nx.read_gml(args.graph_filename)
+else:
+    G = nx.read_gexf(args.graph_filename)
 
+G, _ = pp.prep_graph(G,maincc=True)
+log("Graph Loaded !")
+log("Size "+str(len(G)))
+log("Nb of Edges "+str(len(list(G.edges()))))
+log("Density "+ str(len(G)/len(list(G.edges()))))
 
+log("Building link prediction dataset...")
 # Create an evaluator and generate train/test edge split
 traintest_split = LPEvalSplit()
 traintest_split.compute_splits(G,split_alg="spanning_tree",train_frac=0.8,fe_ratio=1)
 nee = LPEvaluator(traintest_split)
+
+log("Dataset Built !")
+
 # Create a Scoresheet to store the results
 scoresheet = Scoresheet()
 
@@ -40,7 +61,9 @@ methods = ['random_prediction',
            ]
 
 # Evaluate baselines
-for method in methods:
+pbar = tqdm(methods,disable= (not args.verbose))
+for method in pbar:
+    pbar.set_description("Evaluate "+method)
     result = nee.evaluate_baseline(method=method, )
     scoresheet.log_results(result)
 
@@ -63,7 +86,9 @@ if args.network_embedding:
         edge_emb = ['average', 'hadamard']
 
         # Evaluate embedding methods
-        for i in range(len(methods)):
+        pbar = tqdm(enumerate(methods), disable=(not args.verbose))
+        for i,method in pbar:
+            pbar.set_description("Evaluate "+method)
             command = commands[i] + " --input {} --output {} --representation-size {}"
             results = nee.evaluate_cmd(method_name=methods[i], method_type='ne', command=command,
                                        edge_embedding_methods=edge_emb, input_delim=' ', output_delim=' ',  verbose=args.verbose)
@@ -76,4 +101,6 @@ if args.network_embedding:
 # Get output
 if args.verbose:
     scoresheet.print_tabular()
-scoresheet.write_all(args.edgelist_graph_filename+"_results_lp")
\ No newline at end of file
+log("Saving Output in " + args.graph_filename + "_results_lp")
+scoresheet.write_all(args.graph_filename+"_results_lp")
+log("Output Saved !")
\ No newline at end of file

generate_theoric_random_graph.py

@@ -19,13 +19,13 @@ def generate_sbm_prob_matrix(nb_of_blocks,prob_btw_block=0.1):
             M[j,i] = prob_btw_block
     return M
 
-GRAPH_SIZE = [50,100,200,500]
-OUTPUT_DIR = "test_dataset/"
+GRAPH_SIZE = [50,75,100]
+OUTPUT_DIR = "data/theoric_graph_1/"
 
 parameters = {
     "planted_partition_graph": {
         "l": [3,5,8],
-        "k": [10,20,30],
+        "k": [10,20],
         "p_in": [0.2,0.5,0.7],
         "p_out": [0.1,0.2,0.3]
     },
@@ -52,7 +52,7 @@ parameters = {
     },
     "geographical_threshold_graph": {
         "n": GRAPH_SIZE,
-        "theta": [0.1,0.2,0.4,0.6]
+        "theta": [0.1,0.2,0.3]
     },
 }
 # Generating transition matrices for stochastic block model

run_eval.py

@@ -14,22 +14,32 @@ import argparse
 parser = argparse.ArgumentParser()
 parser.add_argument("dataset_dir")
 parser.add_argument("output_filename")
+parser.add_argument("-f", "--format", default="gexf", choices=["gexf", "gml", "txt"])
 
 args = parser.parse_args()
-fns = glob.glob(args.dataset_dir + "/*.gexf")
+fns = glob.glob(args.dataset_dir + "/*." + args.format)
 
 all_res = []
-for fn in tqdm(fns):
-    print("run eval on ", fn)
-    command = "python evalNE_script.py {0} -v".format(fn).split()
+pbar = tqdm(fns)
+for fn in pbar:
+    pbar.set_description("run eval on "+ fn)
+    command = "python evalNE_script.py {0} -f {1} -n".format(fn, args.format).split()
     output = subprocess.run(command)
     if not output.returncode == 0:
         print("Error! for the command :", " ".join(command))
         continue
     df_results = parse_evalne_output(open(fn + "_results_lp").read())
     name = os.path.basename(fn)
-    G  = nx.read_gexf(fn)
-    top10node = pd.DataFrame(list(G.degree()), columns="node degree".split()).sort_values("degree",ascending=False).head(10).node.values
+    G = None
+    if args.format == "edgelist":
+        G = load_edgelist(path=fn)
+    elif args.format == "gml":
+        G = nx.read_gml(fn)
+    else:
+        G = nx.read_gexf(fn)
+
+    top10node = pd.DataFrame(list(G.degree()), columns="node degree".split()).sort_values("degree",
+                                                                                          ascending=False).head(10).node.values
     df_results["nb_edge"] = len(list(G.edges()))
     df_results["transitivity"] = nx.transitivity(G)
     df_results["density"] = nx.density(G)
@@ -38,4 +48,4 @@ for fn in tqdm(fns):
     df_results["filename"] = name
     all_res.append(df_results)
 
-pd.concat(all_res).to_csv(args.output_filename,sep="\t",index=None)
\ No newline at end of file
+pd.concat(all_res).to_csv(args.output_filename, sep="\t", index=False)