def _get_shared_data(): # pragma: no cover
"""multiprocessing helper function to extract numpy arrays from
shared RawArray types used to shared data across process."""
s_counts = _to_np_array(mp_params['s_counts'])
prune_count_matrix = _to_np_array(
mp_arr=mp_params['prune_count_matrix'],
shape=mp_params['pcm_shape'],
)
psx = _to_np_array(
mp_arr=mp_params['psx'],
dtype='float32',
shape=mp_params['psx_shape'],
)
multi_label = mp_params['multi_label']
if multi_label: # Shared data is passed as one-hot encoded matrix
print('before', mp_params['s'])
s = onehot2int(
_to_np_array(
mp_arr=mp_params['s'],
shape=(psx.shape[0], psx.shape[1]),
))
print('after', s)
else:
s = _to_np_array(mp_params['s'])
return s, s_counts, prune_count_matrix, psx, multi_label
def find_noisy_labels(prediction, labels, out, multi_label):
# create folder if not exists
os.makedirs(out, exist_ok=True)
# sort files by Images names
pred_df = pd.read_csv(prediction)
pred_df = pred_df.sort_values(by=['Images'])
label_df = pd.read_csv(labels)
label_df = label_df.sort_values(by=['Images'])
label_df[list(label_df)[1:]] = 1 * (label_df[list(label_df)[1:]] >= 0.5)
# print(label_df)
assert len(pred_df) == len(
label_df), "Mismatch between predictions and labels"
psx = np.array(pred_df[list(pred_df)[1:]])
_labels = np.array(label_df[list(label_df)[1:]])
if multi_label:
correctly_formatted_labels = onehot2int(_labels)
label_errors_bool = cleanlab.pruning.get_noise_indices(
s=correctly_formatted_labels,
psx=psx,
prune_method='prune_by_noise_rate',
sorted_index_method=None,
multi_label=True)
label_errors_idx = cleanlab.pruning.order_label_errors(
label_errors_bool=label_errors_bool,
psx=psx,
labels=correctly_formatted_labels,
sorted_index_method='normalized_margin')
nb_dict = {
'Images': list(),
'Labels': list(),
'Prediction': list(),
'Indices': list()
}
for i in label_errors_idx:
nb_dict['Images'].append(label_df.iloc[i]['Images'])
nb_dict['Labels'].append(','.join(list(map(str, _labels[i, :]))))
nb_dict['Prediction'].append(','.join(list(map(str, psx[i, :]))))
nb_dict['Indices'].append(i)
nb_df = pd.DataFrame(nb_dict)
nb_df.to_csv('noise_labels_multi.csv', index=False)
else:
header = list(pred_df.keys())[1:]
for t in range(len(header)):
pred_t = np.array(pred_df[header[t]])
disease = header[t]
# if disease not in list(label_df.keys()):
# raise ValueError("{} does not exists in ground truth labels!")
label_t = np.array(label_df[disease])
# generate noise labels
binary = list()
for i in range(len(pred_t)):
binary.append([1 - pred_t[i], pred_t[i]])
binary = np.array(binary)
label_errors_bool = cleanlab.pruning.get_noise_indices(
s=copy.deepcopy(label_t),
psx=binary,
prune_method='prune_by_noise_rate',
sorted_index_method=None)
label_errors_idx = cleanlab.pruning.order_label_errors(
label_errors_bool=label_errors_bool,
psx=binary,
labels=copy.deepcopy(label_t),
sorted_index_method='normalized_margin')
nb_dict = {
'Images': list(),
header[t]: list(),
'Prob': list(),
'Indices': list()
}
for i in label_errors_idx:
nb_dict['Images'].append(label_df.iloc[i]['Images'])
nb_dict[header[t]].append(label_t[i])
nb_dict['Prob'].append(float(pred_t[i]))
nb_dict['Indices'].append(i)
nb_df = pd.DataFrame(nb_dict)
nb_df.to_csv(os.path.join(out, '{}.csv'.format(header[t])),
index=False)