def load_type(self, filename, verbose=True):
"""Get the variable types."""
if verbose:
print('========= Reading ' + filename)
start = time.time()
type_list = []
if os.path.isfile(filename):
if competition_c_functions_is_there:
type_list = file_to_array(
filename,
verbose=False)
else:
type_list = file_to_array(filename, verbose=False)
else:
n = self.info['feat_num']
type_list = [self.info['feat_type']] * n
type_list = np.array(type_list).ravel()
end = time.time()
if verbose:
print('[+] Success in %5.2f sec' % (end - start))
return type_list
def _data_binary_sparse(filename, feat_type):
# This function takes as an argument a file representing a binary sparse
# matrix
# binary_sparse_matrix[i][j] = a means matrix[i][j] = 1
# It converts it into a numpy array an returns this array.
inner_data = file_to_array(filename)
nbr_samples = len(inner_data)
# the construction is easier w/ dok_sparse
dok_sparse = scipy.sparse.dok_matrix((nbr_samples, len(feat_type)))
print('Converting {} to dok sparse matrix'.format(filename))
for row in range(nbr_samples):
for feature in inner_data[row]:
dok_sparse[row, int(feature) - 1] = 1
print('Converting {} to csr sparse matrix'.format(filename))
return dok_sparse.tocsr()
