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 build_svmlight_chemical_data(in_files, wl_iterations, output_dir, format_rdf=False, compounds_targets_file=None, uri_prefix=None,
shingles_type="features", window_size=5, accumulate_wl_shingles=True, fingerprints=False,
sort_rdf_nodes_before_processing=True, state_input_file=None, state_output_file=None,
save_just_last_wl_it=False):
if format_rdf:
assert type(in_files) is list
assert bool(compounds_targets_file)
assert bool(uri_prefix)
else:
if type(in_files) is list:
in_files = in_files[0]
files = []
for i in range(wl_iterations + 1):
files.append(open(output_dir + "svm_light_data_wl_{0}".format(i), "w"))
if state_input_file:
state = inout.load_from_file(state_input_file)
state['files'] = files
else:
wl_state = {"wl_state": None}
shingle_id_map = {}
if not fingerprints:
if accumulate_wl_shingles:
wl_state["next_shingle_id"] = 1
else:
for i in range(wl_iterations + 1):
wl_state["wl_{0}_next_shingle_id".format(i)] = 1
state = {
"files": files,
"wl_state": wl_state,
"shingle_id_map": shingle_id_map,
"rdf_colors": {'colors': None, 'next_color_id': None}
}
def process_compound(chem_record):
process_record(chem_record, wl_iterations, state, binary_target_labels=True,
shingles_type=shingles_type, window_size=window_size, accumulate_wl_shingles=accumulate_wl_shingles,
fingerprints=fingerprints, save_just_last_wl_it=save_just_last_wl_it)
if format_rdf:
chem_database, state['rdf_colors'] = prepare_rdf_chemical_data(in_files, compounds_targets_file, uri_prefix, process_compound,
sort_rdf_nodes_before_processing=sort_rdf_nodes_before_processing,
rdf_colors_state=state['rdf_colors'])
else:
chem_database = read_chemical_compounts(in_files, process_compound)
for i, _ in enumerate(chem_database):
print i
for f in files:
f.close()
del state['files']
if state_output_file:
inout.save_to_file(state, state_output_file)
print "Done."
def load_sketch_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 "Reading sketch matrix started at", time.strftime(time_format)
start = time.time()
sketch_matrix = SketchMatrix.load_from_file(path + "{0}_sketch".format(dataset))
print "Reading sketch 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 sketch_matrix, index_node_map, node_id_map
def load_sketch_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 "Reading sketch matrix started at", time.strftime(time_format)
start = time.time()
sketch_matrix = SketchMatrix.load_from_file(path +
"{0}_sketch".format(dataset))
print "Reading sketch 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 sketch_matrix, index_node_map, node_id_map
def read_r_balls_database(r_balls_directory, r_balls_count):
for i in range(r_balls_count):
record = inout.load_from_file(r_balls_directory + "r_ball_{0}".format(i))
yield record
def load_from_file(in_file, compressed=True):
return inout.load_from_file(in_file, compressed)
def read_r_balls_database(r_balls_directory, r_balls_count):
for i in range(r_balls_count):
record = inout.load_from_file(r_balls_directory +
"r_ball_{0}".format(i))
yield record
def load_from_file(in_file, compressed=True):
return inout.load_from_file(in_file, compressed)
