def loo_crossval_naive(graph_database, wl_iter_range, param_2_range, quality_function, output_dir, base_model={}, shingles_type="features", window_size=5, accumulate_wl_shingles=True):
'''Similar to loo_crossval_sketch but computes directly the Jaccard
similarities between the columns in the characteristic matrix,
without using a sketch matrix. Not applicable for big datasets.
'''
best_model = model_p(-1, -1, -1, base_model=base_model)
cols_count = len(graph_database)
models_file = open(output_dir + "models_naive", "a")
for wl_iterations in wl_iter_range:
ch_matrix = CharacteristicMatrix(graph_database, cols_count, wl_iterations=wl_iterations, shingles_type=shingles_type, window_size=window_size, accumulate_wl_shingles=accumulate_wl_shingles)
jaccard_similarity_matrix = ch_matrix.compute_jaccard_similarity_matrix()
for p in param_2_range:
avg_quality = 0.
for i in range(cols_count):
avg_quality += float(quality_function(i, jaccard_similarity_matrix, p))
avg_quality /= cols_count
current_model = model_p(avg_quality, wl_iterations, p, base_model=base_model)
print current_model
models_file.write(str(current_model) + ",\n")
models_file.flush()
if avg_quality > best_model["quality"]:
best_model = current_model
if not base_model:
# print best model when there are no outer parameters
models_file.write("Best model: " + str(best_model) + "\n")
models_file.close()
return best_model
def testCharacteristicMatrix_JaccardSimMatrix(self):
dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph)
rballs_database, _ = similar_nodes_mining.extract_rballs_database(dummy_hypergraph, r_in=3, r_out=2, r_all=0)
nodes_count = dummy_hypergraph.number_of_nodes()
ch_matrix = CharacteristicMatrix(rballs_database, nodes_count, wl_iterations=0)
ch_matrix_jaccard_sim = ch_matrix.compute_jaccard_similarity_matrix()
equality = (self.ch_matrix_jaccard_sim_exp == ch_matrix_jaccard_sim).all()
self.assertTrue(equality, "The computed Jaccard similarity matrix is wrong.")
def testSimilarNodesMining(self):
dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph)
rballs_database, _ = similar_nodes_mining.extract_rballs_database(dummy_hypergraph, r_in=3, r_out=2, r_all=0)
nodes_count = dummy_hypergraph.number_of_nodes()
ch_matrix = CharacteristicMatrix(rballs_database, nodes_count, wl_iterations=0)
ch_matrix_jaccard_sim = ch_matrix.compute_jaccard_similarity_matrix()
similarity_matrix_exp = np.array(ch_matrix_jaccard_sim >= 0.8, dtype=np.float32)
sketch_matrix = SketchMatrix(25, 265, ch_matrix)
similarity_matrix = similar_nodes_mining.get_node_similarity_matrix(sketch_matrix)
equality = (similarity_matrix_exp == similarity_matrix).all()
self.assertTrue(equality, "The computed similarity matrix is wrong (Keep in mind that the sketch_matrix is probabilistic, therefore, it may not be always correct. The test may pass in another run.).")
def testCharacteristicMatrix_JaccardSimMatrix(self):
dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph)
rballs_database, _ = similar_nodes_mining.extract_rballs_database(
dummy_hypergraph, r_in=3, r_out=2, r_all=0)
nodes_count = dummy_hypergraph.number_of_nodes()
ch_matrix = CharacteristicMatrix(rballs_database,
nodes_count,
wl_iterations=0)
ch_matrix_jaccard_sim = ch_matrix.compute_jaccard_similarity_matrix()
equality = (
self.ch_matrix_jaccard_sim_exp == ch_matrix_jaccard_sim).all()
self.assertTrue(equality,
"The computed Jaccard similarity matrix is wrong.")
def loo_crossval_naive(graph_database,
wl_iter_range,
param_2_range,
quality_function,
output_dir,
base_model={},
shingles_type="features",
window_size=5,
accumulate_wl_shingles=True):
'''Similar to loo_crossval_sketch but computes directly the Jaccard
similarities between the columns in the characteristic matrix,
without using a sketch matrix. Not applicable for big datasets.
'''
best_model = model_p(-1, -1, -1, base_model=base_model)
cols_count = len(graph_database)
models_file = open(output_dir + "models_naive", "a")
for wl_iterations in wl_iter_range:
ch_matrix = CharacteristicMatrix(
graph_database,
cols_count,
wl_iterations=wl_iterations,
shingles_type=shingles_type,
window_size=window_size,
accumulate_wl_shingles=accumulate_wl_shingles)
jaccard_similarity_matrix = ch_matrix.compute_jaccard_similarity_matrix(
)
for p in param_2_range:
avg_quality = 0.
for i in range(cols_count):
avg_quality += float(
quality_function(i, jaccard_similarity_matrix, p))
avg_quality /= cols_count
current_model = model_p(avg_quality,
wl_iterations,
p,
base_model=base_model)
print current_model
models_file.write(str(current_model) + ",\n")
models_file.flush()
if avg_quality > best_model["quality"]:
best_model = current_model
if not base_model:
# print best model when there are no outer parameters
models_file.write("Best model: " + str(best_model) + "\n")
models_file.close()
return best_model
def testSimilarNodesMining(self):
dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph)
rballs_database, _ = similar_nodes_mining.extract_rballs_database(
dummy_hypergraph, r_in=3, r_out=2, r_all=0)
nodes_count = dummy_hypergraph.number_of_nodes()
ch_matrix = CharacteristicMatrix(rballs_database,
nodes_count,
wl_iterations=0)
ch_matrix_jaccard_sim = ch_matrix.compute_jaccard_similarity_matrix()
similarity_matrix_exp = np.array(ch_matrix_jaccard_sim >= 0.8,
dtype=np.float32)
sketch_matrix = SketchMatrix(25, 265, ch_matrix)
similarity_matrix = similar_nodes_mining.get_node_similarity_matrix(
sketch_matrix)
equality = (similarity_matrix_exp == similarity_matrix).all()
self.assertTrue(
equality,
"The computed similarity matrix is wrong (Keep in mind that the sketch_matrix is probabilistic, therefore, it may not be always correct. The test may pass in another run.)."
)
