def testGetSimilarNodesToQueryNode(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) sketch_matrix = SketchMatrix(25, 265, ch_matrix) similar_nodes_exp = np.array([0, 5, 7]) similar_nodes, _ = similar_nodes_mining.get_similar_nodes( "n_7", dummy_hypergraph, sketch_matrix, 0, [], r_in=3, r_out=2, r_all=0) equality = similar_nodes_exp == similar_nodes if type(equality) is not bool: equality = equality.all() self.assertTrue( equality, "Wrong similar nodes were extracted (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 testCharacteristicMatrix_ReadWrite(self): file_name = "test_files/characteristic_matrix.tmp" dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph) rballs_database, _ = similar_nodes_mining.extract_rballs_database(dummy_hypergraph, r_in=2, r_out=2, r_all=0) nodes_count = dummy_hypergraph.number_of_nodes() ch_matrix = CharacteristicMatrix(rballs_database, nodes_count, wl_iterations=4) ch_matrix.save_to_file(file_name) read_ch_matrix = CharacteristicMatrix.load_from_file(file_name) self.assertEqual(read_ch_matrix, ch_matrix, "The read characteristic matrix is different from the saved one.")
def calculate_ch_matrix(): in_files = helpers.datasets[dataset]["files"] print "Converting RDF to NetworkX graph started at", time.strftime( time_format) start = time.time() graph, node_id_map = rdf.convert_rdf_to_nx_graph(in_files, discard_classes=False) print "Converting RDF to NetworkX graph took", time.time() - start, "s" print "-----------------------------------------" print "Saving NodeID map started at", time.strftime(time_format) start = time.time() inout.save_to_file(node_id_map, path + "{0}_node_id_map".format(dataset)) print "Saving NodeID map took", time.time() - start, "s" print "-----------------------------------------" print "Building hypergraph started at", time.strftime(time_format) start = time.time() hypergraph = Hypergraph(graph) print "Building hypergraph took", time.time() - start, "s" print "-----------------------------------------" print "Saving hypergraph started at", time.strftime(time_format) start = time.time() hypergraph.save_to_file(path + "{0}_hgraph".format(dataset)) print "Saving hypergraph took", time.time() - start, "s" print "-----------------------------------------" print "Building characteristic matrix started at", time.strftime( time_format) start = time.time() rballs_database, index_node_map = similar_nodes_mining.extract_rballs_database( hypergraph, r_in=r_in, r_out=r_out, r_all=r_all) ch_matrix = CharacteristicMatrix(rballs_database, hypergraph.number_of_nodes(), wl_iterations=wl_iterations, print_progress=True) print "Building characteristic matrix took", time.time() - start, "s" print "-----------------------------------------" print "Saving Column index to Node map started at", time.strftime( time_format) start = time.time() inout.save_to_file(index_node_map, path + "{0}_index_node_map".format(dataset)) print "Saving Column index to Node map took", time.time() - start, "s" print "-----------------------------------------" print "Saving characteristic matrix started at", time.strftime(time_format) start = time.time() ch_matrix.save_to_file(path + "{0}_ch_matrix".format(dataset)) print "Saving characteristic matrix took", time.time() - start, "s" print "-----------------------------------------" return ch_matrix, hypergraph, index_node_map, node_id_map
def testCharacteristicMatrix(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) self.assertEqual(self.raw_ch_matrix_exp, ch_matrix.sparse_matrix, "The computed characteristic matrix is wrong.")
def testSketchMatrix_ReadWrite(self): file_name = "test_files/sketch_matrix.tmp" dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph) rballs_database, _ = similar_nodes_mining.extract_rballs_database(dummy_hypergraph, r_in=2, r_out=2, r_all=0) nodes_count = dummy_hypergraph.number_of_nodes() ch_matrix = CharacteristicMatrix(rballs_database, nodes_count, wl_iterations=4) sketch_matrix = SketchMatrix(5, 20, ch_matrix) sketch_matrix.save_to_file(file_name) read_sketch_matrix = SketchMatrix.load_from_file(file_name) equality = (read_sketch_matrix.matrix == sketch_matrix.matrix).all() self.assertTrue(equality, "The read sketch matrix is different from the saved one.")
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 testGetSimilarNodesToQueryNode(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) sketch_matrix = SketchMatrix(25, 265, ch_matrix) similar_nodes_exp = np.array([0, 5, 7]) similar_nodes, _ = similar_nodes_mining.get_similar_nodes("n_7", dummy_hypergraph, sketch_matrix, 0, [], r_in=3, r_out=2, r_all=0) equality = similar_nodes_exp == similar_nodes if type(equality) is not bool: equality = equality.all() self.assertTrue(equality, "Wrong similar nodes were extracted (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 testCharacteristicMatrix_ReadWrite(self): file_name = "test_files/characteristic_matrix.tmp" dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph) rballs_database, _ = similar_nodes_mining.extract_rballs_database( dummy_hypergraph, r_in=2, r_out=2, r_all=0) nodes_count = dummy_hypergraph.number_of_nodes() ch_matrix = CharacteristicMatrix(rballs_database, nodes_count, wl_iterations=4) ch_matrix.save_to_file(file_name) read_ch_matrix = CharacteristicMatrix.load_from_file(file_name) self.assertEqual( read_ch_matrix, ch_matrix, "The read characteristic matrix is different from the saved one.")
def testSketchMatrix_ReadWrite(self): file_name = "test_files/sketch_matrix.tmp" dummy_hypergraph = Hypergraph(example_graphs.snm_dummy_graph) rballs_database, _ = similar_nodes_mining.extract_rballs_database( dummy_hypergraph, r_in=2, r_out=2, r_all=0) nodes_count = dummy_hypergraph.number_of_nodes() ch_matrix = CharacteristicMatrix(rballs_database, nodes_count, wl_iterations=4) sketch_matrix = SketchMatrix(5, 20, ch_matrix) sketch_matrix.save_to_file(file_name) read_sketch_matrix = SketchMatrix.load_from_file(file_name) equality = (read_sketch_matrix.matrix == sketch_matrix.matrix).all() self.assertTrue( equality, "The read sketch matrix is different from the saved one.")
def calculate_ch_matrix(): in_files = helpers.datasets[dataset]["files"] print "Converting RDF to NetworkX graph started at", time.strftime(time_format) start = time.time() graph, node_id_map = rdf.convert_rdf_to_nx_graph(in_files, discard_classes=False) print "Converting RDF to NetworkX graph took", time.time() - start, "s" print "-----------------------------------------" print "Saving NodeID map started at", time.strftime(time_format) start = time.time() inout.save_to_file(node_id_map, path + "{0}_node_id_map".format(dataset)) print "Saving NodeID map took", time.time() - start, "s" print "-----------------------------------------" print "Building hypergraph started at", time.strftime(time_format) start = time.time() hypergraph = Hypergraph(graph) print "Building hypergraph took", time.time() - start, "s" print "-----------------------------------------" print "Saving hypergraph started at", time.strftime(time_format) start = time.time() hypergraph.save_to_file(path + "{0}_hgraph".format(dataset)) print "Saving hypergraph took", time.time() - start, "s" print "-----------------------------------------" print "Building characteristic matrix started at", time.strftime(time_format) start = time.time() rballs_database, index_node_map = similar_nodes_mining.extract_rballs_database(hypergraph, r_in=r_in, r_out=r_out, r_all=r_all) ch_matrix = CharacteristicMatrix(rballs_database, hypergraph.number_of_nodes(), wl_iterations=wl_iterations, print_progress=True) print "Building characteristic matrix took", time.time() - start, "s" print "-----------------------------------------" print "Saving Column index to Node map started at", time.strftime(time_format) start = time.time() inout.save_to_file(index_node_map, path + "{0}_index_node_map".format(dataset)) print "Saving Column index to Node map took", time.time() - start, "s" print "-----------------------------------------" print "Saving characteristic matrix started at", time.strftime(time_format) start = time.time() ch_matrix.save_to_file(path + "{0}_ch_matrix".format(dataset)) print "Saving characteristic matrix took", time.time() - start, "s" print "-----------------------------------------" return ch_matrix, hypergraph, index_node_map, node_id_map
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 loo_crossval(hypergraph, wl_iter_range, r_in_range, r_out_range, r_all_range, output_dir, k_L_range=None, infl_point_range=None, p_range=None): best_model = sgm_crossval.model(-1, -1, base_model=model(-1, -1, -1)) for r_in in r_in_range: for r_out in r_out_range: for r_all in r_all_range: base_model = model(r_in, r_out, r_all) rballs_database, _ = similar_nodes_mining.extract_rballs_database(hypergraph, r_in=r_in, r_out=r_out, r_all=r_all, center_default_color=True) rballs_database = [(r_id, list(graphs), t) for r_id, graphs, t in rballs_database] # execute generator if k_L_range: current_model = sgm_crossval.loo_crossval_sketch(rballs_database, wl_iter_range, k_L_range, output_dir, base_model=base_model) elif infl_point_range: current_model = sgm_crossval.loo_crossval_threshold(rballs_database, wl_iter_range, infl_point_range, output_dir, base_model=base_model) else: current_model = sgm_crossval.loo_crossval_pnn(rballs_database, wl_iter_range, p_range, output_dir, base_model=base_model) if current_model["quality"] > best_model["quality"]: best_model = current_model models_file = open(output_dir + "models", "a") models_file.write(str(best_model) + ",\n") models_file.close() return best_model
def testCharacteristicMatrix(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) self.assertEqual(self.raw_ch_matrix_exp, ch_matrix.sparse_matrix, "The computed characteristic matrix is wrong.")