def filter_paired_landmarks(item, path_dataset, path_reference, col_source,
col_target):
""" filter all relevant landmarks which were used and copy them to experiment
The case is that in certain challenge stage users had provided just a subset
of all image landmarks which could be laos shuffled. The idea is to filter identify
all user used (provided in dataset) landmarks and filter them from temporary
reference dataset.
:param dict|Series item: experiment DataFrame
:param str path_dataset: path to provided landmarks
:param str path_reference: path to the complete landmark collection
:param str col_source: column name of landmarks to be transformed
:param str col_target: column name of landmarks to be compared
:return tuple(float,ndarray,ndarray): match ratio, filtered ref and move landmarks
>>> p_data = update_path('data-images')
>>> p_csv = os.path.join(p_data, 'pairs-imgs-lnds_histol.csv')
>>> df = pd.read_csv(p_csv)
>>> ratio, lnds_ref, lnds_move = filter_paired_landmarks(dict(df.iloc[0]), p_data, p_data,
... ImRegBenchmark.COL_POINTS_MOVE, ImRegBenchmark.COL_POINTS_REF)
>>> ratio
1.0
>>> lnds_ref.shape == lnds_move.shape
True
"""
path_ref = update_path(item[col_source], pre_path=path_reference)
if not os.path.isfile(path_ref):
raise FileNotFoundError('missing landmarks: %s' % path_ref)
path_load = update_path(item[col_source], pre_path=path_dataset)
if not os.path.isfile(path_load):
raise FileNotFoundError('missing landmarks: %s' % path_load)
pairs = common_landmarks(load_landmarks(path_ref),
load_landmarks(path_load),
threshold=1)
if not pairs.size:
logging.warning(
'there is not pairing between landmarks or dataset and user reference'
)
return 0., np.empty([0]), np.empty([0])
pairs = sorted(pairs.tolist(), key=lambda p: p[1])
ind_ref = np.asarray(pairs)[:, 0]
nb_common = min([
len(load_landmarks(update_path(item[col], pre_path=path_reference)))
for col in (col_target, col_source)
])
ind_ref = ind_ref[ind_ref < nb_common]
path_lnd_ref = update_path(item[col_target], pre_path=path_reference)
lnds_filter_ref = load_landmarks(path_lnd_ref)[ind_ref]
path_lnd_move = update_path(item[col_source], pre_path=path_reference)
lnds_filter_move = load_landmarks(path_lnd_move)[ind_ref]
ratio_matches = len(ind_ref) / float(nb_common)
if ratio_matches > 1:
raise ValueError(
'suspicious ratio for %i paired and %i common landmarks' %
(len(pairs), nb_common))
return ratio_matches, lnds_filter_ref, lnds_filter_move
def filter_landmarks(idx_row, path_output, path_dataset, path_reference):
""" filter all relevant landmarks which were used and copy them to experiment
:param (idx, {}|Series) idx_row: experiment DataFrame
:param str path_output: path to output folder
:param str path_dataset: path to provided landmarks
:param str path_reference: path to the complete landmark collection
:return (idx, float): record index and match ratio
"""
idx, row = idx_row
path_ref = update_path_(row[COL_POINTS_MOVE], path_reference)
path_load = update_path_(row[COL_POINTS_MOVE], path_dataset)
pairs = common_landmarks(load_landmarks(path_ref),
load_landmarks(path_load),
threshold=1)
pairs = sorted(pairs.tolist(), key=lambda p: p[1])
ind_ref = np.asarray(pairs)[:, 0]
# moving and reference landmarks
for col in [COL_POINTS_REF, COL_POINTS_MOVE]:
path_in = update_path_(row[col], path_reference)
path_out = update_path_(row[col], path_output)
create_folder(os.path.dirname(path_out), ok_existing=True)
save_landmarks(path_out, load_landmarks(path_in)[ind_ref])
# save ratio of found landmarks
len_lnds_ref = len(
load_landmarks(update_path_(row[COL_POINTS_REF], path_reference)))
ratio_matches = len(pairs) / float(len_lnds_ref)
return idx, ratio_matches
