diff --git a/generate_theoric_random_graph.py b/generate_theoric_random_graph.py
index fbe8868da8df16f69007226a8e762ce1af535b02..39ec3dc6f76f6dff80e0b767f5b073bee10cc69a 100644
--- a/generate_theoric_random_graph.py
+++ b/generate_theoric_random_graph.py
@@ -41,9 +41,9 @@ parameters = {
"exponent":[2,3]
},
"spatial_graph":{
- "nb_nodes":GRAPH_SIZE,
+ "nb_nodes":[100,150],
"nb_edges":EDGE_SIZE,
- "coords":["random"],
+ "coords":["random","country"],
}
}
diff --git a/lib/random.py b/lib/random.py
index 196c67005c8f8466c0fd58366f7e321adbd31585..58dd6c61d95e2a419e0ee253dae0c6ad8578cf39 100644
--- a/lib/random.py
+++ b/lib/random.py
@@ -4,7 +4,7 @@ from collections import Iterable
import numpy as np
import networkx as nx
import pandas as pd
-
+from networkx.generators.degree_seq import _to_stublist
import random
@@ -75,7 +75,33 @@ def get_countries_coords():
return np.asarray(gdf.centroid.apply(lambda x: [x.x, x.y]).values.tolist())
-def powerlaw_graph(nb_nodes, nb_edges, exponent=2, tries=100, min_deg=1):
+def _conf_model(degree_seq):
+ stubs_list = _to_stublist(degree_seq)
+ random.shuffle(stubs_list)
+ register = set()
+ edges = []
+ hash_func = lambda x, y: "_".join(sorted([str(x), str(y)]))
+ tries = 0
+ while len(stubs_list) > 0 and tries < 100:
+ to_del = set([])
+ for i in range(0, len(stubs_list) - 2, 2):
+ u, v = stubs_list[i], stubs_list[i + 1]
+ hash_ = hash_func(u, v)
+ if hash_ in register:
+ continue
+ else:
+ register.add(hash_)
+ edges.append([u, v])
+ to_del.add(i)
+ to_del.add(i + 1)
+ stubs_list = [stubs_list[i] for i in range(len(stubs_list)) if not i in to_del]
+ random.shuffle(stubs_list)
+ tries += 1
+ G = nx.from_edgelist(edges)
+ return G
+
+
+def powerlaw_graph(nb_nodes, nb_edges, exponent=2, tries=1000, min_deg=1):
"""
Generate a graph with a definied number of vertices, edges, and a degree distribution that fit the power law.
Parameters
@@ -91,8 +117,36 @@ def powerlaw_graph(nb_nodes, nb_edges, exponent=2, tries=100, min_deg=1):
nx.Graph
generated graph
"""
- seq = powerlaw(nb_nodes, nb_edges, exponent, tries, min_deg)
- return nx.configuration_model(seq.astype(int))
+ G = _conf_model(powerlaw(nb_nodes, nb_edges, exponent, tries, min_deg).astype(int))
+ tries_ = 0
+ while len(G) != nb_nodes and tries_ <tries:
+ G = _conf_model(powerlaw(nb_nodes, nb_edges, exponent, tries, min_deg).astype(int))
+ tries_ += 1
+ if len(G) != nb_nodes:
+ print(nb_nodes,nb_edges,exponent)
+ raise Exception("Cant compute configuration model based on parameters")
+
+ if G.size() != nb_edges:
+ diff = abs(G.size() - nb_edges)
+ signe = 1 if G.size() - nb_edges < 0 else -1
+ if signe:
+ for n in list(G.nodes()):
+ if G.size() == nb_edges:
+ break
+ for n2 in list(G.nodes()):
+ if not G.has_edge(n, n2): G.add_edge(n, n2)
+ if G.size() == nb_edges:
+ break
+ else:
+ edges_ = list(G.edges())
+ random.shuffle(edges_)
+ i = diff
+ for ed in edges_:
+ u, v = ed[0], ed[1]
+ if G.degree(u) > 1 and G.degree(v) > 1:
+ G.remove_edge(u, v)
+ i -= 1
+ return G
def spatial_graph(nb_nodes, nb_edges, coords="country", dist_func=lambda a, b: np.linalg.norm(a - b), self_link=False):
@@ -132,11 +186,32 @@ def spatial_graph(nb_nodes, nb_edges, coords="country", dist_func=lambda a, b: n
if i == j and not self_link:
continue
data.append([i, j, dist_func(coords[i], coords[j])])
- df = pd.DataFrame(data, columns="src tar weight".split())
- df["hash"] = df.apply(lambda x: "_".join(sorted([str(x.src), str(x.tar)])), axis=1)
- df = df.drop_duplicates(subset=["hash"])
- df = df.sample(nb_edges, weights="weight")
- G = nx.from_pandas_edgelist(df, source="src", target="tar", edge_attr="weight")
+ 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")
+
+ register = set([])
+
+ def add_register(hashes):
+ for hash_ in hashes:
+ register.add(hash_)
+
+ def in_register(hashes):
+ return np.array([True if hash_ in register else False for hash_ in hashes])
+
+ nodes = np.arange(nb_nodes).astype(int)
+ sizes = [len(x) for x in np.array_split(np.arange(nb_edges), nb_nodes)]
+ new_df = df[(df.src == nodes[0]) | (df.tar == nodes[0])].sample(n=sizes[0], weights="weight").copy()
+ add_register(new_df.hash.values)
+ df = df[~in_register(df.hash.values)]
+
+ for ix, node in enumerate(nodes[1:]):
+ sample = df[(df.src == node) | (df.tar == node)].sample(n=sizes[ix + 1], weights="weight").copy()
+ new_df = pd.concat((new_df, sample))
+ add_register(new_df.hash.values)
+ df = df[~in_register(df.hash.values)]
+
+ G = nx.from_pandas_edgelist(new_df, source="src", target="tar", edge_attr="weight")
for n in list(G.nodes()): G.nodes[n]["pos"] = coords[n]
return G
@@ -254,7 +329,7 @@ def equilibrate(G, nb_nodes, percentage_edge_betw, percentage_edge_within, inter
def draw_(array, register, hash_func=lambda x, y: "_".join(sorted([str(x), str(y)]))):
tries = 0
- while tries <1000:
+ while tries < 1000:
index_array = np.random.choice(np.arange(len(array)), 1)
res = array[index_array]
res = res[0]
@@ -262,7 +337,7 @@ def equilibrate(G, nb_nodes, percentage_edge_betw, percentage_edge_within, inter
if not hash_ in register:
register.add(hash_)
return index_array
- tries +=1
+ tries += 1
raise Exception("Error ! (TODO)")
# Draw new edges
diff --git a/run_eval.py b/run_eval.py
index c4a739b792cf9df17a05c7c47582d40038192720..6567a89735e0f7166a98c8674b85c7933d38f83a 100644
--- a/run_eval.py
+++ b/run_eval.py
@@ -42,7 +42,7 @@ for fn in pbar:
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["nb_edge"] = G.size()
df_results["transitivity"] = nx.transitivity(G)
df_results["density"] = nx.density(G)
df_results["top10_node"] = "|".join(top10node)