def score_map(map_filename, atlas_data, labels):
map_data = nb.load(map_filename).get_data()
parcel_means = labeled_comprehension(map_data, atlas_data, list(labels),
np.mean, float, np.nan)
parcel_variance = labeled_comprehension(map_data, atlas_data, list(labels),
np.var, float, np.nan)
within_variance = parcel_variance.mean()
between_variance = parcel_means.var()
return within_variance, between_variance
def score_map(map_filename, atlas_data, labels):
map_data = nb.load(map_filename).get_data()
parcel_means = labeled_comprehension(map_data,
atlas_data,
list(labels),
np.mean,
float,
np.nan)
parcel_variance = labeled_comprehension(map_data,
atlas_data,
list(labels),
np.var,
float,
np.nan)
within_variance = parcel_variance.mean()
between_variance = parcel_means.var()
return within_variance, between_variance
def _hacky_make_image(labeled_img, u_labels, measures, m_key, dtype=np.int16):
out = np.zeros(labeled_img.shape, dtype=dtype).ravel()
if m_key is None:
measures = [{"key": m} for m in measures]
m_key = "key"
def value_grab(a, b):
out[b] = measures[a[0] - 1][m_key]
return None
sci_meas.labeled_comprehension(labeled_img,
labeled_img,
u_labels,
value_grab,
float,
0,
pass_positions=True)
return out.reshape(labeled_img.shape)
def band_label_properties(labels,
band,
ind=None,
func=np.mean,
outdtype=np.float,
default=0.0):
if type(ind) == type(None):
ind = np.unique(labels.compressed())
proparr = measurements.labeled_comprehension(band, labels, ind, func,
outdtype, default)
return pd.Series(proparr, index=ind)
def module_main(ctx):
label_pairs = a3.inputs['label pair list']
intensity_image = a3.MultiDimImageFloat_to_ndarray(
a3.inputs['intensity image'])
labeled_image = a3.MultiDimImageUInt32_to_ndarray(a3.inputs['labeled'])
ids_1 = label_pairs[:, 0]
cnt_1 = labeled_comprehension(intensity_image, labeled_image, ids_1, len,
int, -1)
print(np.c_[ids_1, cnt_1])
print('voxel counting done 🍀')
def _extract_features(self, labels, intensity):
unique_l = np.unique(labels)
unique_l = unique_l[unique_l != 0]
props = {
feature_name:
labeled_comprehension(intensity,
labels,
unique_l,
self._features_functions[feature_name],
out_dtype=float,
default=np.nan)
for feature_name in self.features
}
props['label'] = unique_l
return props
def spin_parcels(*,
lhannot,
rhannot,
version='fsaverage',
n_rotate=1000,
spins=None,
drop=None,
verbose=False,
**kwargs):
"""
Rotates parcels in `{lh,rh}annot` and re-assigns based on maximum overlap
Vertex labels are rotated with :func:`netneurotools.stats.gen_spinsamples`
and a new label is assigned to each *parcel* based on the region maximally
overlapping with its boundaries.
Parameters
----------
{lh,rh}annot : str
Path to .annot file containing labels to parcels on the {left,right}
hemisphere
version : str, optional
Specifies which version of `fsaverage` provided annotation files
correspond to. Must be one of {'fsaverage', 'fsaverage3', 'fsaverage4',
'fsaverage5', 'fsaverage6'}. Default: 'fsaverage'
n_rotate : int, optional
Number of rotations to generate. Default: 1000
spins : array_like, optional
Pre-computed spins to use instead of generating them on the fly. If not
provided will use other provided parameters to create them. Default:
None
drop : list, optional
Specifies regions in {lh,rh}annot that are not present in `data`. NaNs
will be inserted in place of the these regions in the returned data. If
not specified, parcels defined in `netneurotools.freesurfer.FSIGNORE`
are assumed to not be present. Default: None
seed : {int, np.random.RandomState instance, None}, optional
Seed for random number generation. Default: None
verbose : bool, optional
Whether to print occasional status messages. Default: False
return_cost : bool, optional
Whether to return cost array (specified as Euclidean distance) for each
coordinate for each rotation. Default: True
kwargs : key-value pairs
Keyword arguments passed to `netneurotools.stats.gen_spinsamples`
Returns
-------
spinsamples : (N, `n_rotate`) numpy.ndarray
Resampling matrix to use in permuting data parcellated with labels from
{lh,rh}annot, where `N` is the number of parcels. Indices of -1
indicate that the parcel was completely encompassed by regions in
`drop` and should be ignored.
cost : (N, `n_rotate`,) numpy.ndarray
Cost (specified as Euclidean distance) of re-assigning each coordinate
for every rotation in `spinsamples`. Only provided if `return_cost` is
True.
"""
def overlap(vals):
""" Returns most common non-negative value in `vals`; -1 if all neg
"""
vals = np.asarray(vals)
vals, counts = np.unique(vals[vals > 0], return_counts=True)
try:
return vals[counts.argmax()]
except ValueError:
return -1
if drop is None:
drop = FSIGNORE
drop = _decode_list(drop)
# get vertex-level labels (set drop labels to - values)
vertices, end = [], 0
for n, annot in enumerate([lhannot, rhannot]):
labels, ctab, names = read_annot(annot)
names = _decode_list(names)
todrop = set(names) & set(drop)
inds = [names.index(f) - n for n, f in enumerate(todrop)]
labs = np.arange(len(names) - len(inds)) + (end - (len(inds) * n))
insert = np.arange(-1, -(len(inds) + 1), -1)
vertices.append(np.insert(labs, inds, insert)[labels])
end += len(names)
vertices = np.hstack(vertices)
labels = np.unique(vertices)
mask = labels > -1
# get spins + cost (if requested)
spins, cost = _get_fsaverage_spins(version=version,
spins=spins,
n_rotate=n_rotate,
verbose=verbose,
**kwargs)
if len(vertices) != len(spins):
raise ValueError('Provided annotation files have a different '
'number of vertices than the specified fsaverage '
'surface.\n ANNOTATION: {} vertices\n '
'FSAVERAGE: {} vertices'.format(
len(vertices), len(spins)))
# spin and assign regions based on max overlap
regions = np.zeros((len(labels[mask]), n_rotate), dtype='int32')
for n in range(n_rotate):
if verbose:
msg = f'Calculating parcel overlap: {n:>5}/{n_rotate}'
print(msg, end='\b' * len(msg), flush=True)
regions[:, n] = labeled_comprehension(vertices[spins[:, n]], vertices,
labels, overlap, int, -1)[mask]
if kwargs.get('return_cost'):
return regions, cost
return regions
def erode(input_image, erosion_levels, min_size, manual_expected_size):
######
#- calculate erosion maps
#- for all nuclei calculate area and determine unique ID
#- now link all nuclei in trees for all largest nuclei
#- find node with lowest cost for each tree
#- create map with all lowest costs
#print(list(erosion_levels))
binary = input_image / 255 < 0.5
lvl_labels = [] #image with labels
lvl_ids = []
lvl_areas = []
lvl_contours = []
lvl_nodes = []
lvl_children = []
max_id = 0
binary = input_image / 255 < 0.5
binary = binary_fill_holes(binary)
mask = binary
for lvl in erosion_levels:
if lvl == 0:
er = binary
else:
er = (binary_erosion(binary, iterations=lvl))
remove_small_objects(er, min_size=min_size, in_place=True)
lb, distance, mask = watershed_erosion_edt(mask, er)
lb_zero = lb == 0
lb_unique = lb + max_id
lb_unique[lb_zero] = 0
lvl_labels.append(lb_unique)
ids = np.unique(lb_unique)
ids = ids[1:] #remove 0 label
nb_labels = len(ids)
if (nb_labels == 0):
lvl_areas.append([])
else:
lvl_areas.append(
labeled_comprehension(binary,
lb,
range(1, nb_labels + 1),
func=np.sum,
out_dtype=float,
default=0))
lvl_ids.append(ids)
max_id = max_id + nb_labels
#calculate contour for all detected cells
for lvl_i in range(len(erosion_levels)):
labels_i = lvl_labels[lvl_i]
contours = []
for j, id_j in enumerate(lvl_ids[lvl_i]):
mask_j = labels_i == id_j
cnt = cv2.findContours(np.uint8(mask_j), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_NONE)[-2]
arclen = cv2.arcLength(cnt[0], True)
contours.append(arclen)
lvl_contours.append(contours)
#find children for all (future) nodes
for lvl_i in range(len(erosion_levels) - 1):
if (len(lvl_ids[lvl_i]) == 0):
lvl_children.append([])
else:
c_lbls = labeled_comprehension(lvl_labels[lvl_i + 1],
lvl_labels[lvl_i],
lvl_ids[lvl_i],
out_dtype=list,
func=my_unique,
default=0)
lvl_children.append(c_lbls)
#create actual nodes
for lvl_i in range(len(erosion_levels)):
nodes = []
for j, id_j in enumerate(lvl_ids[lvl_i]):
area = lvl_areas[lvl_i][j]
contour = lvl_contours[lvl_i][j]
ff = form_factor(area, contour)
node = Node(id_j, area=area, contour=contour, formfactor=ff)
nodes.append(node)
lvl_nodes.append(nodes)
#link nodes
for lvl_i in range(len(erosion_levels) - 1):
for j, id_j in enumerate(lvl_ids[lvl_i]):
children_ids = lvl_children[lvl_i][j]
parent_node = lvl_nodes[lvl_i][j]
children_node_indexes = np.where(
np.isin(lvl_ids[lvl_i + 1], children_ids))
children_node_indexes = children_node_indexes[0].astype('int')
children_nodes = np.take(lvl_nodes[lvl_i + 1],
children_node_indexes)
parent_node.children = children_nodes
global expected_size
if manual_expected_size == 0:
expected_size = np.median(lvl_areas[0])
else:
expected_size = manual_expected_size
ids_final_img = []
final_nodes = []
for node in lvl_nodes[0]:
ids = traverse_tree(node)
if type(ids) == type(list()):
for node in ids:
final_nodes.append(node)
else:
final_nodes.append(node)
ids_final_img = final_nodes
ids_final_img = [node.name for node in ids_final_img]
final_labels = np.zeros((1024, 1024))
for labels in lvl_labels:
indices_to_take = np.where(np.isin(labels, ids_final_img))
final_labels[indices_to_take] = labels[indices_to_take]
labels, _ = label(final_labels) #,compactness = 100)
labels = watershed(image=binary,
markers=labels,
mask=binary,
watershed_line=False) #,compactness = 100)
return labels
def addDQ(self, adinputs=None, **params):
"""
This primitive is used to add a DQ extension to the input AstroData
object. The value of a pixel in the DQ extension will be the sum of the
following: (0=good, 1=bad pixel (found in bad pixel mask), 2=pixel is
in the non-linear regime, 4=pixel is saturated). This primitive will
trim the BPM to match the input AstroData object(s).
Parameters
----------
suffix: str
suffix to be added to output files
static_bpm: str
Name of bad pixel mask ("default" -> use default from look-up table)
If set to None, no static_bpm will be added.
user_bpm: str
Name of the bad pixel mask created by the user from flats and
darks. It is an optional BPM that can be added to the static one.
illum_mask: bool
add illumination mask?
"""
log = self.log
log.debug(gt.log_message("primitive", self.myself(), "starting"))
timestamp_key = self.timestamp_keys["addDQ"]
sfx = params["suffix"]
# Getting all the filenames first prevents reopening the same file
# for each science AD
static_bpm_list = params['static_bpm']
user_bpm_list = params['user_bpm']
if static_bpm_list == "default":
static_bpm_list = [self._get_bpm_filename(ad) for ad in adinputs]
for ad, static, user in zip(*gt.make_lists(
adinputs, static_bpm_list, user_bpm_list, force_ad=True)):
if ad.phu.get(timestamp_key):
log.warning('No changes will be made to {}, since it has '
'already been processed by addDQ'.format(
ad.filename))
continue
if static is None:
# So it can be zipped with the AD
final_static = [None] * len(ad)
else:
log.fullinfo("Using {} as static BPM".format(static.filename))
final_static = gt.clip_auxiliary_data(ad,
aux=static,
aux_type='bpm',
return_dtype=DQ.datatype)
if user is None:
final_user = [None] * len(ad)
else:
log.fullinfo("Using {} as user BPM".format(user.filename))
final_user = gt.clip_auxiliary_data(ad,
aux=user,
aux_type='bpm',
return_dtype=DQ.datatype)
for ext, static_ext, user_ext in zip(ad, final_static, final_user):
extver = ext.hdr['EXTVER']
if ext.mask is not None:
log.warning(
'A mask already exists in extver {}'.format(extver))
continue
non_linear_level = ext.non_linear_level()
saturation_level = ext.saturation_level()
# Need to create the array first for 3D raw F2 data, with 2D BPM
ext.mask = np.zeros_like(ext.data, dtype=DQ.datatype)
if static_ext is not None:
ext.mask |= static_ext.data
if user_ext is not None:
ext.mask |= user_ext.data
if saturation_level:
log.fullinfo('Flagging saturated pixels in {}:{} '
'above level {:.2f}'.format(
ad.filename, extver, saturation_level))
ext.mask |= np.where(ext.data >= saturation_level,
DQ.saturated, 0).astype(DQ.datatype)
if non_linear_level:
if saturation_level:
if saturation_level > non_linear_level:
log.fullinfo('Flagging non-linear pixels in {}:{} '
'above level {:.2f}'.format(
ad.filename, extver,
non_linear_level))
ext.mask |= np.where(
(ext.data >= non_linear_level) &
(ext.data < saturation_level), DQ.non_linear,
0).astype(DQ.datatype)
# Readout modes of IR detectors can result in
# saturated pixels having values below the
# saturation level. Flag those. Assume we have an
# IR detector here because both non-linear and
# saturation levels are defined and nonlin<sat
regions, nregions = measurements.label(
ext.data < non_linear_level)
# In all my tests, region 1 has been the majority
# of the image; however, I cannot guarantee that
# this is always the case and therefore we should
# check the size of each region
region_sizes = measurements.labeled_comprehension(
ext.data, regions, np.arange(1, nregions + 1),
len, int, 0)
# First, assume all regions are saturated, and
# remove any very large ones. This is much faster
# than progressively adding each region to DQ
hidden_saturation_array = np.where(
regions > 0, 4, 0).astype(DQ.datatype)
for region in range(1, nregions + 1):
# Limit of 10000 pixels for a hole is a bit arbitrary
if region_sizes[region - 1] > 10000:
hidden_saturation_array[regions ==
region] = 0
ext.mask |= hidden_saturation_array
elif saturation_level < non_linear_level:
log.warning('{}:{} has saturation level less than '
'non-linear level'.format(
ad.filename, extver))
else:
log.fullinfo('Saturation and non-linear levels '
'are the same for {}:{}. Only '
'flagging saturated pixels'.format(
ad.filename, extver))
else:
log.fullinfo('Flagging non-linear pixels in {}:{} '
'above level {:.2f}'.format(
ad.filename, extver,
non_linear_level))
ext.mask |= np.where(ext.data >= non_linear_level,
DQ.non_linear,
0).astype(DQ.datatype)
# Handle latency if reqested
if params.get("latency", False):
try:
adinputs = self.addLatencyToDQ(adinputs,
time=params["time"],
non_linear=params["non_linear"])
except AttributeError:
log.warning(
"addLatencyToDQ() not defined in primitivesClass " +
self.__class__.__name__)
# Add the illumination mask if requested
if params['add_illum_mask']:
adinputs = self.addIllumMaskToDQ(adinputs,
illum_mask=params["illum_mask"])
# Timestamp and update filenames
for ad in adinputs:
gt.mark_history(ad, primname=self.myself(), keyword=timestamp_key)
ad.update_filename(suffix=sfx, strip=True)
return adinputs
def addDQ(self, adinputs=None, **params):
"""
This primitive is used to add a DQ extension to the input AstroData
object. The value of a pixel in the DQ extension will be the sum of the
following: (0=good, 1=bad pixel (found in bad pixel mask), 2=pixel is
in the non-linear regime, 4=pixel is saturated). This primitive will
trim the BPM to match the input AstroData object(s).
Parameters
----------
suffix: str
suffix to be added to output files
static_bpm: str
Name of bad pixel mask ("default" -> use default from look-up table)
If set to None, no static_bpm will be added.
user_bpm: str
Name of the bad pixel mask created by the user from flats and
darks. It is an optional BPM that can be added to the static one.
illum_mask: bool
add illumination mask?
"""
log = self.log
log.debug(gt.log_message("primitive", self.myself(), "starting"))
timestamp_key = self.timestamp_keys["addDQ"]
sfx = params["suffix"]
# Getting all the filenames first prevents reopening the same file
# for each science AD
static_bpm_list = params['static_bpm']
user_bpm_list = params['user_bpm']
if static_bpm_list == "default":
static_bpm_list = [self._get_bpm_filename(ad) for ad in adinputs]
for ad, static, user in zip(*gt.make_lists(adinputs, static_bpm_list,
user_bpm_list, force_ad=True)):
if ad.phu.get(timestamp_key):
log.warning('No changes will be made to {}, since it has '
'already been processed by addDQ'.format(ad.filename))
continue
if static is None:
# So it can be zipped with the AD
final_static = [None] * len(ad)
else:
log.fullinfo("Using {} as static BPM".format(static.filename))
final_static = gt.clip_auxiliary_data(ad, aux=static,
aux_type='bpm', return_dtype=DQ.datatype)
if user is None:
final_user = [None] * len(ad)
else:
log.fullinfo("Using {} as user BPM".format(user.filename))
final_user = gt.clip_auxiliary_data(ad, aux=user,
aux_type='bpm', return_dtype=DQ.datatype)
for ext, static_ext, user_ext in zip(ad, final_static, final_user):
extver = ext.hdr['EXTVER']
if ext.mask is not None:
log.warning('A mask already exists in extver {}'.
format(extver))
continue
non_linear_level = ext.non_linear_level()
saturation_level = ext.saturation_level()
# Need to create the array first for 3D raw F2 data, with 2D BPM
ext.mask = np.zeros_like(ext.data, dtype=DQ.datatype)
if static_ext is not None:
ext.mask |= static_ext.data
if user_ext is not None:
ext.mask |= user_ext.data
if saturation_level:
log.fullinfo('Flagging saturated pixels in {}:{} '
'above level {:.2f}'.
format(ad.filename, extver, saturation_level))
ext.mask |= np.where(ext.data >= saturation_level,
DQ.saturated, 0).astype(DQ.datatype)
if non_linear_level:
if saturation_level:
if saturation_level > non_linear_level:
log.fullinfo('Flagging non-linear pixels in {}:{} '
'above level {:.2f}'.
format(ad.filename, extver,
non_linear_level))
ext.mask |= np.where((ext.data >= non_linear_level) &
(ext.data < saturation_level),
DQ.non_linear, 0).astype(DQ.datatype)
# Readout modes of IR detectors can result in
# saturated pixels having values below the
# saturation level. Flag those. Assume we have an
# IR detector here because both non-linear and
# saturation levels are defined and nonlin<sat
regions, nregions = measurements.label(
ext.data < non_linear_level)
# In all my tests, region 1 has been the majority
# of the image; however, I cannot guarantee that
# this is always the case and therefore we should
# check the size of each region
region_sizes = measurements.labeled_comprehension(
ext.data, regions, np.arange(1, nregions+1),
len, int, 0)
# First, assume all regions are saturated, and
# remove any very large ones. This is much faster
# than progressively adding each region to DQ
hidden_saturation_array = np.where(regions > 0,
4, 0).astype(DQ.datatype)
for region in range(1, nregions+1):
# Limit of 10000 pixels for a hole is a bit arbitrary
if region_sizes[region-1] > 10000:
hidden_saturation_array[regions==region] = 0
ext.mask |= hidden_saturation_array
elif saturation_level < non_linear_level:
log.warning('{}:{} has saturation level less than '
'non-linear level'.format(ad.filename, extver))
else:
log.fullinfo('Saturation and non-linear levels '
'are the same for {}:{}. Only '
'flagging saturated pixels'.
format(ad.filename, extver))
else:
log.fullinfo('Flagging non-linear pixels in {}:{} '
'above level {:.2f}'.
format(ad.filename, extver,
non_linear_level))
ext.mask |= np.where(ext.data >= non_linear_level,
DQ.non_linear, 0).astype(DQ.datatype)
# Handle latency if reqested
if params.get("latency", False):
try:
adinputs = self.addLatencyToDQ(adinputs, time=params["time"],
non_linear=params["non_linear"])
except AttributeError:
log.warning("addLatencyToDQ() not defined in primitivesClass "
+ self.__class__.__name__)
# Add the illumination mask if requested
if params['add_illum_mask']:
adinputs = self.addIllumMaskToDQ(adinputs, illum_mask=params["illum_mask"])
# Timestamp and update filenames
for ad in adinputs:
gt.mark_history(ad, primname=self.myself(), keyword=timestamp_key)
ad.update_filename(suffix=sfx, strip=True)
return adinputs
def _largest_connected_component(mask):
lbls, nlbls = ndims.label(mask)
vols = ndims.labeled_comprehension(mask, lbls, range(1, nlbls + 1), np.sum,
float, 0)
mask[lbls != np.argmax(vols) + 1] = 0
return mask
def apply_feature_extraction(instance_stack, tiff_stack, p_map, channels):
labels_ring_stack = []
results = pd.DataFrame()
for frame_nb in tqdm.tqdm(range(np.shape(instance_stack)[0])):
p_map_frame = p_map[frame_nb, :, :]
tiff_frame = tiff_stack[frame_nb, :, :, :]
instance_frame = instance_stack[frame_nb, :, :]
nb_centers = np.max(instance_frame)
to_zip = [] #all the features get appended here
to_col = [] #all the names get appended here
## EXTRACT FEATURES ##
## Store frame number
frame_number_rep = np.repeat([frame_nb], nb_centers)
to_zip.append(frame_number_rep)
to_col.append("frame")
## Nuclear centers
p_map_frame_binary = p_map_frame < (255 / 2)
centers = center_of_mass(p_map_frame_binary,
labels=instance_frame,
index=range(1, nb_centers + 1))
centers_x = np.array(centers)[:, 1] #X/Y are inverted, take care!
centers_y = np.array(centers)[:, 0] # ... are they?? TODO
to_zip.append(centers_x)
to_zip.append(centers_y)
to_col.append("x")
to_col.append("y")
## Mean certainty of nucleus segmentation
mean_p_nuc = labeled_comprehension(p_map_frame,
labels=instance_frame,
index=range(1, nb_centers + 1),
func=np.mean,
out_dtype='float32',
default=float("nan"))
to_zip.append(mean_p_nuc)
to_col.append("mean_p_nuc")
## Create cytosolic ring
labels_ring = extract_ring(instance_frame)
## Calculate areas of nucleus and ring
size_nuc = labeled_comprehension(p_map_frame_binary,
labels=instance_frame,
index=range(1, nb_centers + 1),
func=np.sum,
out_dtype='float32',
default=float("nan"))
ring_binary = np.zeros_like(labels_ring)
ring_binary[labels_ring > 0] = 1
size_ring = labeled_comprehension(ring_binary,
labels=labels_ring,
index=range(1, nb_centers + 1),
func=np.sum,
out_dtype='float32',
default=float("nan"))
to_zip.append(size_nuc)
to_zip.append(centers_x)
to_col.append("size_nuc")
to_col.append("size_ring")
## Extract features from additional channels:
channels_other = {k: v
for (k, v) in channels.items()
if k != "H2B"} #for all channels that are not H2B
for k, v in channels_other.items():
#mean intensity of nucleus
mean_nuc = labeled_comprehension(tiff_frame[:, :, v],
labels=instance_frame,
index=range(1, nb_centers + 1),
func=np.mean,
out_dtype='float32',
default=float("nan"))
#mean intensity of cytosolic ring
mean_ring = labeled_comprehension(tiff_frame[:, :, v],
labels=labels_ring,
index=range(1, nb_centers + 1),
func=np.mean,
out_dtype='float32',
default=float("nan"))
#their ratio
ratio = (mean_ring / mean_nuc).astype('float32')
to_zip.append(mean_nuc)
to_zip.append(mean_ring)
to_zip.append(ratio)
to_col.append("mean_nuc_" + k)
to_col.append("mean_ring_" + k)
to_col.append("ratio_" + k)
## STORE FEATURES TO PANDAS DF, ONE ROW / NUCLEUS
#features = list(zip(centers_x,centers_y,nuclear_area,ring_area,frame_number_rep, range(1, nb_centers+1),
# mean_nucleus_c1, mean_ring_c1, ratio_c1,
# mean_p_nucleus))
to_zip.append(range(1, nb_centers + 1))
to_col.append("label_frame")
features = list(zip(*to_zip))
results = results.append(features) #assign return value as it is a PD
labels_ring_stack.append(
labels_ring) #dont assign return value as it is a list
#columns=['y','x','size_nuc','size_ring','frame','label_frame',
# 'mean_nuc_c1','mean_ring_c1','ratio_c1',
# 'mean_p_nuc']
results.columns = to_col
#results = results.convert_dtypes() #convert to "best" dtype
# downsample precision form 64bit to 32bit
# results = results.astype({'y':'float32','x':'float32','size_nuc':'float32','size_ring':'float32','frame':'float32', 'label_frame':'float32',
# 'mean_nuc_c1':'float32','mean_ring_c1':'float32','ratio_c1':'float32',
# 'mean_p_nuc':'float32'})
results.astype('float32')
labels_ring_stack = np.asarray(labels_ring_stack)
return results, labels_ring_stack
def spin_parcels(*,
lhannot,
rhannot,
version='fsaverage',
n_rotate=1000,
drop=None,
seed=None,
return_cost=False,
**kwargs):
"""
Rotates parcels in `{lh,rh}annot` and re-assigns based on maximum overlap
Vertex labels are rotated with :func:`netneurotools.stats.gen_spinsamples`
and a new label is assigned to each *parcel* based on the region maximally
overlapping with its boundaries.
Parameters
----------
{lh,rh}annot : str
Path to .annot file containing labels to parcels on the {left,right}
hemisphere
version : str, optional
Specifies which version of `fsaverage` provided annotation files
correspond to. Must be one of {'fsaverage', 'fsaverage3', 'fsaverage4',
'fsaverage5', 'fsaverage6'}. Default: 'fsaverage'
n_rotate : int, optional
Number of rotations to generate. Default: 1000
drop : list, optional
Specifies regions in {lh,rh}annot that are not present in `data`. NaNs
will be inserted in place of the these regions in the returned data. If
not specified, 'unknown' and 'corpuscallosum' are assumed to not be
present. Default: None
return_cost : bool, optional
Whether to return cost array (specified as Euclidean distance) for each
coordinate for each rotation Default: True
kwargs : key-value, optional
Key-value pairs passed to :func:`netneurotools.stats.gen_spinsamples`
Returns
-------
spinsamples : (N, `n_rotate`) numpy.ndarray
Resampling matrix to use in permuting data parcellated with labels from
{lh,rh}annot, where `N` is the number of parcels. Indices of -1
indicate that the parcel was completely encompassed by regions in
`drop` and should be ignored.
cost : (N, `n_rotate`,) numpy.ndarray
Cost (specified as Euclidean distance) of re-assigning each coordinate
for every rotation in `spinsamples`. Only provided if `return_cost` is
True.
"""
def overlap(vals):
""" Returns most common non-negative value in `vals`; -1 if all neg
"""
vals = np.asarray(vals)
vals, counts = np.unique(vals[vals > 0], return_counts=True)
try:
return vals[counts.argmax()]
except ValueError:
return -1
if drop is None:
drop = [
'unknown',
'corpuscallosum', # default FreeSurfer
'Background+FreeSurfer_Defined_Medial_Wall' # common alternative
]
drop = _decode_list(drop)
# get vertex-level labels (set drop labels to - values)
vertices, end = [], 0
for n, annot in enumerate([lhannot, rhannot]):
labels, ctab, names = read_annot(annot)
names = _decode_list(names)
todrop = set(names) & set(drop)
inds = [names.index(f) - n for n, f in enumerate(todrop)]
labs = np.arange(len(names) - len(inds)) + (end - (len(inds) * n))
insert = np.arange(-1, -(len(inds) + 1), -1)
vertices.append(np.insert(labs, inds, insert)[labels])
end += len(names)
vertices = np.hstack(vertices)
labels = np.unique(vertices)
mask = labels > -1
# get coordinates and hemisphere designation for spin generation
coords, hemiid = _get_fsaverage_coords(version, 'sphere')
if len(vertices) != len(coords):
raise ValueError('Provided annotation files have a different number '
'of vertices than the specified fsaverage surface.\n'
' ANNOTATION: {} vertices\n'
' FSAVERAGE: {} vertices'.format(
len(vertices), len(coords)))
# spin and assign regions based on max overlap
spins, cost = gen_spinsamples(coords, hemiid, n_rotate=n_rotate, **kwargs)
regions = np.zeros((len(labels[mask]), n_rotate), dtype='int32')
for n in range(n_rotate):
regions[:, n] = labeled_comprehension(vertices[spins[:, n]], vertices,
labels, overlap, int, -1)[mask]
if return_cost:
return regions, cost
return regions
def band_label_properties(labels, band, ind=None, func=np.mean,
outdtype=np.float, default=0.0):
if type(ind) == type(None):
ind = np.unique(labels.compressed())
proparr = measurements.labeled_comprehension(band, labels, ind, func, outdtype, default)
return pd.Series(proparr, index=ind)