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 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 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 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 load_ch_matrix():
print "Reading NodeID map started at", time.strftime(time_format)
start = time.time()
node_id_map = inout.load_from_file(path + "{0}_node_id_map".format(dataset))
print "Reading NodeID map took", time.time() - start, "s"
print "-----------------------------------------"
print "Reading hypergraph started at", time.strftime(time_format)
start = time.time()
hypergraph = Hypergraph.load_from_file(path + "{0}_hgraph".format(dataset))
print "Reading hypergraph took", time.time() - start, "s"
print "-----------------------------------------"
print "Reading characteristic matrix started at", time.strftime(time_format)
start = time.time()
ch_matrix = CharacteristicMatrix.load_from_file(path + "{0}_ch_matrix".format(dataset))
print "Reading characteristic matrix took", time.time() - start, "s"
print "-----------------------------------------"
print "Reading Column index to Node map started at", time.strftime(time_format)
start = time.time()
index_node_map = inout.load_from_file(path + "{0}_index_node_map".format(dataset))
print "Reading Column index to Node map took", time.time() - start, "s"
print "-----------------------------------------"
return ch_matrix, hypergraph, index_node_map, node_id_map
def load_ch_matrix():
print "Reading NodeID map started at", time.strftime(time_format)
start = time.time()
node_id_map = inout.load_from_file(path +
"{0}_node_id_map".format(dataset))
print "Reading NodeID map took", time.time() - start, "s"
print "-----------------------------------------"
print "Reading hypergraph started at", time.strftime(time_format)
start = time.time()
hypergraph = Hypergraph.load_from_file(path + "{0}_hgraph".format(dataset))
print "Reading hypergraph took", time.time() - start, "s"
print "-----------------------------------------"
print "Reading characteristic matrix started at", time.strftime(
time_format)
start = time.time()
ch_matrix = CharacteristicMatrix.load_from_file(
path + "{0}_ch_matrix".format(dataset))
print "Reading characteristic matrix took", time.time() - start, "s"
print "-----------------------------------------"
print "Reading Column index to Node map started at", time.strftime(
time_format)
start = time.time()
index_node_map = inout.load_from_file(path +
"{0}_index_node_map".format(dataset))
print "Reading Column index to Node map took", time.time() - start, "s"
print "-----------------------------------------"
return ch_matrix, hypergraph, index_node_map, node_id_map
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 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 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 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 loo_crossval_sketch(graph_database,
wl_iter_range,
k_L_range,
output_dir,
base_model={},
cols_count=None,
shingles_type="features",
window_size=5):
'''Leave-one-out cross-validation.
:param graph_database: Defined the same way as for CharacteristicMatrix constructor (but cannot be a generator).
:param wl_iter_range: Range of Weisfeiler-Lehman iterations to be considered in the cross-validation.
:param k_L_range: A range of (k, L) tuples for the sketch matrix to be considered in the cross-validation.
# :param quality_function: a function with signature (G, sketch_matrix), where G is a list of graphs
# representing a single entity in the database and sketch_matrix is a sketch matrix. The function
# should return a real value. The cross-validation will find the model that maximizes this function.
:param output_dir: A local directory, that will be used to save the sketch matrices of all models.
:param base_model: A base model that is going to be extended by the new parameters.
:return The best model as a dictionary.
'''
def quality(i, sketch_matrix):
col_i = sketch_matrix.get_column(i)
similar_cols = list(sketch_matrix.get_similar_columns(col_i))
if i in similar_cols:
similar_cols.remove(i)
similar_targets = map(lambda c: graph_database[c][2], similar_cols)
true_target_i = graph_database[i][2]
estimated_target_i = statistics.predict_target_majority(
similar_targets)
# print "Col:", i, ", Target:", true_target_i, ", Est. target: ", estimated_target_i
# print "Similar cols:", similar_cols
# print "Similar targets:", similar_targets
# print "--------------------------------------"
# fp = open(output_dir + "classification_sketch", "a")
# fp.write("Col: {0}, Target: {1}, Est. target: {2}\n".format(i, true_target_i, estimated_target_i))
# fp.write("Similar cols: {0}\n".format(similar_cols))
# fp.write("Similar targets: {0}\n".format(similar_targets))
# fp.write("--------------------------------------\n")
# fp.close()
if type(true_target_i) is list:
return int(estimated_target_i in true_target_i) # zero-one loss
else:
return int(true_target_i == estimated_target_i) # zero-one loss
best_model = model_infl_point(-1, -1, base_model=base_model)
if not cols_count:
cols_count = len(graph_database)
models_file = open(output_dir + "models_sketch", "a")
for wl_iterations in wl_iter_range:
# start = time.time()
ch_matrix = CharacteristicMatrix(graph_database,
cols_count,
wl_iterations=wl_iterations,
print_progress=True,
shingles_type=shingles_type,
window_size=window_size)
# print "Building characteristic matrix for wl_iter =", wl_iterations, "took:", time.time() - start
for k, L in k_L_range:
# start = time.time()
sketch_matrix = SketchMatrix(k, L, ch_matrix)
# print "Building sketch matrix for k={0} and L={1} took:".format(k, L), time.time() - start
# sketch_matrix.save_to_file(output_dir + "sketch_matrix_wl{0}_k{1}_L{2}".format(wl_iterations, k, L))
# start = time.time()
avg_quality = 0.
for i in range(cols_count):
avg_quality += float(quality(i, sketch_matrix))
avg_quality /= cols_count
# print "Classification took:", time.time() - start
current_model = model_infl_point(avg_quality,
wl_iterations,
k,
L,
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 d_fold_crossval(data,
cols_count,
d,
k_L_range,
output_dir,
base_model={},
multilabel=False,
multilabel_prediction_threshold=0.4):
'''Cross-validation in d-folds.
:param data: Input data, where each record is a tuple of the form (target, props), where props is a sparse vector.
:param cols_count: Number of records in data.
:param d: Number of cross-validation folds.
:param k_L_range: A range of (k, L) tuples for the sketch matrix to be considered in the cross-validation.
:param output_dir: A local directory, that will be used to save the sketch matrices of all models.
:param base_model: A base model that is going to be extended by the new parameters.
:param multilabel: (default False) If True, a record may have multiple different integer target labels.
If False, the target labels are binary.
:return: The best model as a dictionary.
'''
def quality(sketch_matrix, train_sketch, test_sketch, train_targets,
test_targets):
k = sketch_matrix.k
L = sketch_matrix.L
train_cols_count = np.shape(train_sketch)[1]
if multilabel:
test_targets_pred = []
else:
test_targets_proba = np.empty(len(test_targets))
for i in range(np.shape(test_sketch)[1]):
col_i = test_sketch[:, i:i + 1]
similar_cols = SketchMatrix._get_similar_columns(
col_i, train_sketch, k, L, train_cols_count)
similar_targets = itertools.chain(
*map(lambda c: train_targets[c], similar_cols))
# similar_targets = list(itertools.chain(*map(lambda c: train_targets[c], similar_cols)))
if multilabel:
target_proportions = statistics.get_multilabel_target_proportions(
similar_targets,
np.shape(similar_cols)[0])
targets_pred = filter(
lambda target: target_proportions[target] >
multilabel_prediction_threshold, target_proportions)
test_targets_pred.append(targets_pred)
# print "Col:", i, ", Target:", test_targets[i], ", Est. target: ", targets_pred
# print "Similar cols:", similar_cols
# print "Similar targets:", similar_targets
# print "--------------------------------------"
# _acc, _prec, _recall, _f1 = statistics.multi_label_scores([test_targets[i]], [targets_pred])
# fp = open(output_dir + "classification_sketch", "a")
# fp.write("Col: {0}, Target: {1}, Est. target: {2}\n".format(i, test_targets[i], targets_pred))
# fp.write("Accuracy: {0}, Precision: {1}, Recall: {2}, F1: {3}\n".format(_acc, _prec, _recall, _f1))
# fp.write("Similar cols: {0}\n".format(list(similar_cols)))
# fp.write("Similar targets: {0}\n".format(similar_targets))
# fp.write("--------------------------------------\n")
# fp.close()
else:
estimated_target_proba_i = statistics.predict_binary_target_proba(
similar_targets)
test_targets_proba[i] = estimated_target_proba_i
if multilabel:
# TODO: compute also AUC?
acc, prec, recall, f1 = statistics.multi_label_scores(
test_targets, test_targets_pred)
return -1., acc, prec, recall, f1
else:
return all_scores(test_targets, test_targets_proba)
best_model = model_score([-1., -1., -1., -1., -1.], base_model=base_model)
models_file = open(output_dir + "models_sketch", "a")
start = time.time()
ch_matrix = CharacteristicMatrix(records=data,
cols_count=cols_count,
print_progress=True)
targets = ch_matrix.target_values
print "Building characteristic matrix took:", time.time() - start
for k, L in k_L_range:
start = time.time()
sketch_matrix = SketchMatrix(k, L, ch_matrix)
print "Building sketch matrix for k={0} and L={1} took:".format(
k, L), time.time() - start
# sketch_matrix.save_to_file(output_dir + "sketch_matrix_wl{0}_k{1}_L{2}".format(wl_iterations, k, L))
start = time.time()
avg_score = d_folds(d, sketch_matrix, cols_count, quality, targets)
print "Classification took:", time.time() - start
current_model = model_score(avg_score, k, L, base_model=base_model)
print current_model
models_file.write(str(current_model) + ",\n")
models_file.flush()
if avg_score[0] > best_model["auc"]:
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
