def loadLabel (self, filename, verbose=True):
''' Get the solution/truth values'''
if verbose: print("========= Reading " + filename)
start = time.time()
if self.use_pickle and os.path.exists (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle")):
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "r") as pickle_file:
vprint (verbose, "Loading pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
return pickle.load(pickle_file)
if 'task' not in self.info.keys():
self.getTypeProblem(filename)
# IG: Here change to accommodate the new multiclass label format
if self.info['task'] == 'multilabel.classification':
label = data_io.data(filename)
elif self.info['task'] == 'multiclass.classification':
label = data_io.data(filename)
# IG: I changed that because it was too confusing.
#label = data_converter.convert_to_num(data_io.data(filename))
else:
label = np.ravel(data_io.data(filename)) # get a column vector
#label = np.array([np.ravel(data_io.data(filename))]).transpose() # get a column vector
if self.use_pickle:
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "wb") as pickle_file:
vprint (verbose, "Saving pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
p = pickle.Pickler(pickle_file)
p.fast = True
p.dump(label)
end = time.time()
if verbose: print( "[+] Success in %5.2f sec" % (end - start))
return label
def loadLabel (self, filename, verbose=True):
''' Get the solution/truth values'''
if verbose: print("========= Reading " + filename)
start = time.time()
if self.use_pickle and os.path.exists (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle")):
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "r") as pickle_file:
vprint (verbose, "Loading pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
return pickle.load(pickle_file)
if 'task' not in self.info.keys():
self.getTypeProblem(filename)
# IG: Here change to accommodate the new multiclass label format
if self.info['task'] == 'multilabel.classification':
label = data_io.data(filename)
elif self.info['task'] == 'multiclass.classification':
label = data_converter.convert_to_num(data_io.data(filename))
else:
label = np.ravel(data_io.data(filename)) # get a column vector
#label = np.array([np.ravel(data_io.data(filename))]).transpose() # get a column vector
if self.use_pickle:
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "wb") as pickle_file:
vprint (verbose, "Saving pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
p = pickle.Pickler(pickle_file)
p.fast = True
p.dump(label)
end = time.time()
if verbose: print( "[+] Success in %5.2f sec" % (end - start))
return label
# Inventory the datasets (new style, datasets in subdirectories)
input_dir = argv[1]
datanames = data_io.inventory_data(input_dir)
# The output directory will contain the scores, create it if it does not exist
output_dir = argv[2]
data_io.mkdir(output_dir)
if len(datanames) == 0:
print("****** No data found ******")
# Loop over datasets
for basename in datanames:
print("****** Processing " + basename.capitalize() + " ******")
# Fake predictions on validation and test data
X = data_io.data(
path.join(input_dir, basename, basename + '_valid.data'))
Yvalid = random.rand(X.shape[0])
X = data_io.data(
path.join(input_dir, basename, basename + '_test.data'))
Ytest = random.rand(X.shape[0])
# Write results to files
data_io.write(path.join(output_dir, basename + '_valid.predict'),
Yvalid)
data_io.write(path.join(output_dir, basename + '_test.predict'), Ytest)
# Lots of debug code...
data_io.show_io(input_dir, output_dir)
data_io.show_version()
exit(0)
