def _calc_motif3(self):
raw_ftr = GraphFeatures(self._graph,
{"motif3": FeatureMeta(nth_nodes_motif(3, gpu=self._gpu, device=self._device), {"m3"})},
dir_path=self._dir_path)
raw_ftr.build(should_dump=True)
feature = raw_ftr['motif3']._features
if type(feature) == dict:
motif_matrix = self._to_matrix(feature)
else:
motif_matrix = feature
normed_matrix = self._log_norm(motif_matrix)
if self._motif_choice == "All_Motifs":
mp = MotifProbability(self._params['vertices'], self._params['probability'],
self._params['subgraph_size'], self._params['directed'])
clique_motifs = mp.get_3_clique_motifs(3)
return normed_matrix[:, clique_motifs]
else:
return normed_matrix
def _calc_motif4(self):
raw_ftr = GraphFeatures(self._graph,
{"motif4": FeatureMeta(nth_nodes_motif(4, gpu=self._gpu, device=self._device), {"m4"})},
dir_path=self._dir_path)
raw_ftr.build(should_dump=True)
feature = raw_ftr['motif4']._features
if type(feature) == dict:
motif_matrix = self._to_matrix(feature)
else:
motif_matrix = feature
normed_matrix = self._log_norm(motif_matrix)
if self._motif_choice == "All_Motifs":
mp = MotifProbability(self._params['vertices'], self._params['probability'],
self._params['subgraph_size'], self._params['directed'])
motif3_count = 1 + mp.get_3_clique_motifs(3)[-1] # The full 3 clique is the last motif 3.
clique_motifs = [m - motif3_count for m in mp.get_3_clique_motifs(4)]
return normed_matrix[:, clique_motifs]
else:
return normed_matrix
def _calc_additional_features(self):
# MUST BE AFTER CALCULATING MOTIFS
if "Motif_3" not in self._features:
raise KeyError(
"Motifs must be calculated prior to the additional features")
else:
motif_index_in_features = self._features.index("Motif_3")
motif_matrix = self._feature_matrix[motif_index_in_features]
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['subgraph_size'],
self._params['directed'])
motif3_count = 1 + mp.get_3_clique_motifs(3)[
-1] # The full 3 clique is the last motif 3.
add_ftrs = AdditionalFeatures(self._params,
self._graph,
motif_matrix,
motifs=list(range(motif3_count)))
return self._log_norm(add_ftrs.calculate_extra_ftrs())
def _calc_motif4(self):
# FOR NOW, NO GPU FOR US
if os.path.exists(os.path.join(self._dir_path, "motif4.pkl")):
pkl4 = pickle.load(
open(os.path.join(self._dir_path, "motif4.pkl"), "rb"))
if type(pkl4) == dict:
motif4 = self._to_matrix(pkl4)
elif type(pkl4) == MotifsNodeCalculator:
motif4 = np.array(pkl4._features)
else:
motif4 = np.array(pkl4)
if self._motif_choice == "All_Motifs":
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
motif3_count = 1 + mp.get_3_clique_motifs(3)[
-1] # The full 3 clique is the last motif 3.
clique_motifs = [
m - motif3_count for m in mp.get_3_clique_motifs(4)
]
return motif4[:, clique_motifs]
else:
return motif4
raw_ftr = GraphFeatures(self._graph, {
"motif4":
FeatureMeta(nth_nodes_motif(4, gpu=self._gpu, device=self._device),
{"m4"})
},
dir_path=self._dir_path)
raw_ftr.build(should_dump=True)
feature = raw_ftr['motif4']._features
if type(feature) == dict:
motif_matrix = self._to_matrix(feature)
else:
motif_matrix = feature
normed_matrix = self._log_norm(motif_matrix)
if self._motif_choice == "All_Motifs":
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
motif3_count = 1 + mp.get_3_clique_motifs(3)[
-1] # The full 3 clique is the last motif 3.
clique_motifs = [
m - motif3_count for m in mp.get_3_clique_motifs(4)
]
return normed_matrix[:, clique_motifs]
else:
return normed_matrix
def _calc_additional_features(self):
# MUST BE AFTER CALCULATING MOTIFS
if self._motif_choice is None:
raise KeyError(
"Motifs must be calculated prior to the additional features")
else:
if self._motif_choice == "All_Motifs":
motif_matrix = np.hstack(
(pickle.load(
open(os.path.join(self._dir_path, "Motif_3.pkl"),
"rb")),
pickle.load(
open(os.path.join(self._dir_path, "Motif_4.pkl"),
"rb"))))
add_ftrs = AdditionalFeatures(self._params, self._graph,
self._dir_path, motif_matrix)
elif self._motif_choice == "Motif_3":
motif_matrix = pickle.load(
open(os.path.join(self._dir_path, "Motif_3.pkl"), "rb"))
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
motif3_count = 1 + mp.get_3_clique_motifs(3)[
-1] # The full 3 clique is the last motif 3.
add_ftrs = AdditionalFeatures(self._params,
self._graph,
self._dir_path,
motif_matrix,
motifs=list(range(motif3_count)))
else:
motif_matrix = np.hstack(
(pickle.load(
open(os.path.join(self._dir_path, "Motif_3.pkl"),
"rb")),
pickle.load(
open(os.path.join(self._dir_path, "Motif_4.pkl"),
"rb"))))
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
motif3_count = 1 + mp.get_3_clique_motifs(3)[
-1] # The full 3 clique is the last motif 3.
motif4_count = 1 + mp.get_3_clique_motifs(4)[
-1] # The full 4 clique is the last motif 4.
add_ftrs = AdditionalFeatures(
self._params,
self._graph,
self._dir_path,
motif_matrix,
motifs=list(range(motif3_count, motif4_count)))
return add_ftrs.calculate_extra_ftrs()
def aggregate_results():
# Assuming validation is complete.
from additional_features import MotifProbability
from generate_graphs_2 import SIZES, PROB, DIRECTED, NUM_RUNS
if not os.path.exists("results_2"):
os.mkdir("results_2")
for size, is_directed, level in itertools.product(SIZES, DIRECTED, [3, 4]):
dump_dirname = os.path.join(
"results_2",
f"size{size}_p{PROB}_directed{is_directed}_motif{level}")
if not os.path.exists(dump_dirname):
os.mkdir(dump_dirname)
mp = MotifProbability(size=size,
edge_probability=PROB,
clique_size=0,
directed=is_directed)
expected_motifs = pd.DataFrame([
mp.motif_expected_non_clique_vertex(motif_index=idx)
for idx in get_motif_indices(level, is_directed)
]).T
expected_motifs.to_csv(os.path.join(dump_dirname,
"expected_motifs.csv"),
header=None,
index=None)
dirname = f"size{size}_p{PROB}_directed{is_directed}_runs"
for run in range(NUM_RUNS):
res_df = pd.DataFrame(
res_to_matrix(
pickle.load(
open(
os.path.join(dirname, f"run_{run}", "motifs_gpu",
f"motif{level}.pkl"), "rb"))))
if not os.path.exists(os.path.join(dump_dirname, f"run_{run}")):
os.mkdir(os.path.join(dump_dirname, f"run_{run}"))
res_df.to_csv(os.path.join(dump_dirname, f"run_{run}",
"motifs.csv"),
header=None,
index=None)
def _calc_motif3(self):
# FOR NOW, NO GPU FOR US
if os.path.exists(os.path.join(self._dir_path, "motif3.pkl")):
pkl3 = pickle.load(
open(os.path.join(self._dir_path, "motif3.pkl"), "rb"))
if type(pkl3) == dict:
motif3 = self._to_matrix(pkl3)
elif type(pkl3) == MotifsNodeCalculator:
motif3 = np.array(pkl3._features)
else:
motif3 = np.array(pkl3)
if self._motif_choice == "All_Motifs":
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
clique_motifs = mp.get_3_clique_motifs(3)
return motif3[:, clique_motifs]
else:
return motif3
raw_ftr = GraphFeatures(self._graph, {
"motif3":
FeatureMeta(nth_nodes_motif(3, gpu=self._gpu, device=self._device),
{"m3"})
},
dir_path=self._dir_path)
raw_ftr.build(should_dump=True)
feature = raw_ftr['motif3']._features
if type(feature) == dict:
motif_matrix = self._to_matrix(feature)
else:
motif_matrix = feature
normed_matrix = self._log_norm(motif_matrix)
if self._motif_choice == "All_Motifs":
mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
clique_motifs = mp.get_3_clique_motifs(3)
return normed_matrix[:, clique_motifs]
else:
return normed_matrix
if __name__ == '__main__':
# Assuming validation is complete.
from additional_features import MotifProbability
from generate_graphs_2 import SIZES, PROB, DIRECTED, NUM_RUNS
if not os.path.exists("results_2"):
os.mkdir("results_2")
for size, is_directed, level in itertools.product(SIZES, DIRECTED, [3, 4]):
dump_dirname = os.path.join(
"results_2",
f"size{size}_p{PROB}_directed{is_directed}_motif{level}")
if not os.path.exists(dump_dirname):
os.mkdir(dump_dirname)
mp = MotifProbability(size=size,
edge_probability=PROB,
clique_size=0,
directed=is_directed)
with open(os.path.join(dump_dirname, "expected_motifs.csv"),
newline='') as expected_motifs_file:
for row in expected_motifs_file:
expected_motifs = row
expected_motifs = list(expected_motifs.split(","))
for i in range(len(expected_motifs)):
expected_motifs[i] = float(expected_motifs[i])
dirname = f"size{size}_p{PROB}_directed{is_directed}_runs"
motifs = []
for run in range(NUM_RUNS):
with open(os.path.join(dump_dirname, f"run_{run}", "motifs.csv"),
newline='') as motifs_file: