def slice_clusters(params, result, to_remove=[], to_merge=[], extension='', light=False):
import h5py, shutil
file_out_suff = params.get('data', 'file_out_suff')
data_file = params.data_file
N_e = params.getint('data', 'N_e')
N_total = params.nb_channels
N_t = params.getint('detection', 'N_t')
template_shift = params.getint('detection', 'template_shift')
if comm.rank == 0:
print_and_log(['Node 0 is slicing clusters'], 'debug', logger)
if to_merge != []:
for count in xrange(len(to_merge)):
remove = to_merge[count][1]
to_remove += [remove]
all_elements = [[] for i in xrange(N_e)]
for target in numpy.unique(to_remove):
elec = result['electrodes'][target]
nic = target - numpy.where(result['electrodes'] == elec)[0][0]
mask = result['clusters_' + str(elec)] > -1
tmp = numpy.unique(result['clusters_' + str(elec)][mask])
all_elements[elec] += list(numpy.where(result['clusters_' + str(elec)] == tmp[nic])[0])
for elec in xrange(N_e):
if not light:
result['data_' + str(elec)] = numpy.delete(result['data_' + str(elec)], all_elements[elec], axis=0)
result['clusters_' + str(elec)] = numpy.delete(result['clusters_' + str(elec)], all_elements[elec])
result['times_' + str(elec)] = numpy.delete(result['times_' + str(elec)], all_elements[elec])
result['peaks_' + str(elec)] = numpy.delete(result['peaks_' + str(elec)], all_elements[elec])
else:
result['clusters_' + str(elec)] = numpy.delete(result['clusters_' + str(elec)], all_elements[elec])
myfile = h5py.File(file_out_suff + '.clusters.hdf5', 'r', libver='earliest')
data = myfile.get('data_' + str(elec))[:]
result['data_' + str(elec)] = numpy.delete(data, all_elements[elec], axis=0)
data = myfile.get('times_' + str(elec))[:]
result['times_' + str(elec)] = numpy.delete(data, all_elements[elec])
data = myfile.get('peaks_' + str(elec))[:]
result['peaks_' + str(elec)] = numpy.delete(data, all_elements[elec])
myfile.close()
result['electrodes'] = numpy.delete(result['electrodes'], numpy.unique(to_remove))
cfile = h5py.File(file_out_suff + '.clusters-new.hdf5', 'w', libver='earliest')
to_write = ['data_', 'clusters_', 'times_', 'peaks_']
for ielec in xrange(N_e):
write_datasets(cfile, to_write, result, ielec)
write_datasets(cfile, ['electrodes'], result)
cfile.close()
if os.path.exists(file_out_suff + '.clusters%s.hdf5' %extension):
os.remove(file_out_suff + '.clusters%s.hdf5' %extension)
shutil.move(file_out_suff + '.clusters-new.hdf5', file_out_suff + '.clusters%s.hdf5' %extension)
comm.Barrier()
def generate_matlab_mapping(probe):
p = {}
positions = []
nodes = []
for key in probe['channel_groups'].keys():
p.update(probe['channel_groups'][key]['geometry'])
nodes += probe['channel_groups'][key]['channels']
positions += [p[channel] for channel in probe['channel_groups'][key]['channels']]
idx = numpy.argsort(nodes)
positions = numpy.array(positions)[idx]
t = tempfile.NamedTemporaryFile().name + '.hdf5'
cfile = h5py.File(t, 'w')
to_write = {'positions' : positions/10., 'permutation' : numpy.sort(nodes), 'nb_total' : numpy.array([probe['total_nb_channels']])}
write_datasets(cfile, to_write.keys(), to_write)
cfile.close()
return t
def slice_clusters(params,
result,
to_remove=[],
to_merge=[],
extension='',
input_extension='',
light=False,
method='safe'):
"""Slice clusters in HDF5 templates.
Arguments:
params
to_remove: list (optional)
to_merge: list | numpy.ndarray (optional)
extension: string (optional)
The default value is ''.
input_extension: string (optional)
The default value is ''.
light: boolean (optional)
"""
file_out_suff = params.get('data', 'file_out_suff')
data_file = params.data_file
N_e = params.getint('data', 'N_e')
N_total = params.nb_channels
hdf5_compress = params.getboolean('data', 'hdf5_compress')
N_t = params.getint('detection', 'N_t')
template_shift = params.getint('detection', 'template_shift')
if comm.rank == 0:
print_and_log(['Node 0 is slicing clusters'], 'debug', logger)
old_templates = load_data(params,
'templates',
extension=input_extension)
_, N_tm = old_templates.shape
# Determine the template indices to delete.
to_delete = list(to_remove)
if to_merge != []:
for count in xrange(len(to_merge)):
remove = to_merge[count][1]
to_delete += [remove]
# Determine the indices to keep.
all_templates = set(numpy.arange(N_tm // 2))
to_keep = numpy.array(list(all_templates.difference(to_delete)))
all_elements = [[] for i in xrange(N_e)]
for target in numpy.unique(to_delete):
elec = result['electrodes'][target]
nic = target - numpy.where(result['electrodes'] == elec)[0][0]
mask = result['clusters_' + str(elec)] > -1
tmp = numpy.unique(result['clusters_' + str(elec)][mask])
all_elements[elec] += list(
numpy.where(result['clusters_' + str(elec)] == tmp[nic])[0])
myfilename = file_out_suff + '.clusters{}.hdf5'.format(input_extension)
myfile = h5py.File(myfilename, 'r', libver='earliest')
for elec in xrange(N_e):
if not light:
result['data_' + str(elec)] = numpy.delete(result['data_' +
str(elec)],
all_elements[elec],
axis=0)
result['clusters_' + str(elec)] = numpy.delete(
result['clusters_' + str(elec)], all_elements[elec])
result['times_' + str(elec)] = numpy.delete(
result['times_' + str(elec)], all_elements[elec])
result['peaks_' + str(elec)] = numpy.delete(
result['peaks_' + str(elec)], all_elements[elec])
else:
result['clusters_' + str(elec)] = numpy.delete(
result['clusters_' + str(elec)], all_elements[elec])
data = myfile.get('data_' + str(elec))[:]
result['data_' + str(elec)] = numpy.delete(data,
all_elements[elec],
axis=0)
data = myfile.get('times_' + str(elec))[:]
result['times_' + str(elec)] = numpy.delete(
data, all_elements[elec])
data = myfile.get('peaks_' + str(elec))[:]
result['peaks_' + str(elec)] = numpy.delete(
data, all_elements[elec])
myfile.close()
if method == 'safe':
result['electrodes'] = numpy.delete(result['electrodes'],
numpy.unique(to_delete))
elif method == 'new':
result['electrodes'] = result['electrodes'][to_keep]
else:
raise ValueError("Unexpected method value: {}".format(method))
cfilename = file_out_suff + '.clusters{}.hdf5'.format('-new')
cfile = h5py.File(cfilename, 'w', libver='earliest')
to_write = ['data_', 'clusters_', 'times_', 'peaks_']
for ielec in xrange(N_e):
write_datasets(cfile,
to_write,
result,
ielec,
compression=hdf5_compress)
write_datasets(cfile, ['electrodes'], result)
cfile.close()
# Rename output file.
temporary_path = cfilename
output_path = file_out_suff + '.clusters{}.hdf5'.format(extension)
if os.path.exists(output_path):
os.remove(output_path)
shutil.move(temporary_path, output_path)
return
def main(params, nb_cpu, nb_gpu, use_gpu):
# Part 1: Whitening
numpy.random.seed(420)
# params = detect_memory(params)
_ = init_logging(params.logfile)
logger = logging.getLogger('circus.whitening')
#################################################################
data_file = params.data_file
N_e = params.getint('data', 'N_e')
hdf5_compress = params.getboolean('data', 'hdf5_compress')
N_total = params.nb_channels
N_t = params.getint('detection', 'N_t')
dist_peaks = params.getint('detection', 'dist_peaks')
template_shift = params.getint('detection', 'template_shift')
file_out_suff = params.get('data', 'file_out_suff')
spike_thresh = params.getfloat('detection', 'spike_thresh')
spike_width = params.getfloat('detection', 'spike_width')
matched_filter = params.getboolean('detection', 'matched-filter')
matched_thresh = params.getfloat('detection', 'matched_thresh')
fudge = params.getfloat('whitening', 'fudge')
sign_peaks = params.get('detection', 'peaks')
do_temporal_whitening = params.getboolean('whitening', 'temporal')
do_spatial_whitening = params.getboolean('whitening', 'spatial')
ignore_spikes = params.getboolean('whitening', 'ignore_spikes')
chunk_size = detect_memory(params, whitening=True)
plot_path = os.path.join(params.get('data', 'file_out_suff'), 'plots')
nodes, edges = get_nodes_and_edges(params)
safety_time = params.getint('whitening', 'safety_time')
safety_space = params.getboolean('whitening', 'safety_space')
sort_waveforms = params.getboolean('whitening', 'sort_waveforms')
nb_temp_white = min(max(20, comm.size), N_e)
max_silence_1 = int(20 * params.rate // comm.size)
max_silence_2 = 5000
inv_nodes = numpy.zeros(N_total, dtype=numpy.int32)
inv_nodes[nodes] = numpy.arange(len(nodes))
jitter_range = params.getint('detection', 'jitter_range')
template_shift_2 = template_shift + jitter_range
use_hanning = params.getboolean('detection', 'hanning')
rejection_threshold = params.getfloat('detection', 'rejection_threshold')
noise_window = params.getint('detection', 'noise_time')
data_file.open()
#################################################################
if use_hanning:
hanning_filter = numpy.hanning(N_t)
if comm.rank == 0:
print_and_log(
["Analyzing data to get whitening matrices and thresholds..."],
'default', logger)
nodes_indices = {}
for elec in numpy.arange(N_e):
nodes_indices[elec] = inv_nodes[edges[nodes[elec]]]
if use_gpu:
import cudamat as cmt
# # Need to properly handle multi GPU per MPI nodes?
if nb_gpu > nb_cpu:
gpu_id = int(comm.rank // nb_cpu)
else:
gpu_id = 0
cmt.cuda_set_device(gpu_id)
cmt.init()
cmt.cuda_sync_threads()
nb_chunks, last_chunk_len = data_file.analyze(chunk_size)
if nb_chunks < comm.size:
res = io.data_stats(params, show=False)
chunk_size = int(res * params.rate // comm.size)
if comm.rank == 0:
print_and_log(
["Too much cores, automatically resizing the data chunks"],
'debug', logger)
nb_chunks, last_chunk_len = data_file.analyze(chunk_size)
# I guess this is more relevant, to take signals from all over the recordings.
if nb_chunks > comm.size:
all_chunks = numpy.random.permutation(
numpy.arange(nb_chunks - 1, dtype=numpy.int32))
else:
all_chunks = numpy.random.permutation(
numpy.arange(nb_chunks, dtype=numpy.int32))
all_electrodes = numpy.random.permutation(N_e)
numpy.random.seed(comm.rank)
for gidx in [all_chunks[comm.rank]]:
# print "Node", comm.rank, "is analyzing chunk", gidx, "/", nb_chunks, " ..."
local_chunk, t_offset = data_file.get_data(gidx,
chunk_size,
nodes=nodes)
local_shape = len(local_chunk)
# print "Node", comm.rank, "computes the median absolute deviations in a random chunk"
thresholds = numpy.zeros(N_e, dtype=numpy.float32)
for i in range(N_e):
u = numpy.median(local_chunk[:, i], 0)
thresholds[i] = numpy.median(numpy.abs(local_chunk[:, i] - u), 0)
gdata = gather_array(thresholds, comm)
if comm.rank == 0:
gdata = gdata.reshape((comm.size, N_e))
thresholds = numpy.mean(gdata, 0)
bfile = h5py.File(file_out_suff + '.basis.hdf5',
'w',
libver='earliest')
io.write_datasets(bfile, ['thresholds'],
{'thresholds': thresholds},
compression=hdf5_compress)
bfile.close()
comm.Barrier()
thresholds = io.load_data(params, 'thresholds')
local_borders = (template_shift, local_shape - template_shift)
found_peaktimes = []
if ignore_spikes:
# Extracting the peaks.
local_peaktimes = [np.empty(0, dtype=numpy.uint32)]
for i in range(N_e):
peaktimes = scipy.signal.find_peaks(numpy.abs(local_chunk[:,
i]),
height=thresholds[i],
width=spike_width,
wlen=N_t)[0]
peaktimes = peaktimes.astype(numpy.uint32)
# print "Removing the useless borders..."
idx = (peaktimes >= local_borders[0]) & (peaktimes <
local_borders[1])
peaktimes = numpy.compress(idx, peaktimes)
found_peaktimes.append(peaktimes)
else:
for i in range(N_e):
found_peaktimes.append(numpy.zeros(0, dtype=numpy.uint32))
all_peaktimes = numpy.concatenate(found_peaktimes)
local_peaktimes = numpy.unique(all_peaktimes)
if len(local_peaktimes) > 0:
diff_times = local_peaktimes[-1] - local_peaktimes[0]
all_times = numpy.zeros((N_e, diff_times + 1), dtype=numpy.bool)
padded_peaks = (local_peaktimes - local_peaktimes[0]).astype(
numpy.int32)
min_times = numpy.maximum(padded_peaks - safety_time, 0)
max_times = numpy.minimum(padded_peaks + safety_time + 1,
diff_times + 1)
test_extremas = numpy.zeros((N_e, diff_times + 1),
dtype=numpy.bool)
for i in range(N_e):
test_extremas[i,
found_peaktimes[i] - local_peaktimes[0]] = True
argmax_peak = numpy.random.permutation(
numpy.arange(len(local_peaktimes)))
all_idx = numpy.take(local_peaktimes, argmax_peak)
# print "Selection of the peaks with spatio-temporal masks..."
for idx, peak in zip(argmax_peak, all_idx):
all_elecs = numpy.where(test_extremas[:, peak -
local_peaktimes[0]])[0]
data = local_chunk[peak, all_elecs]
elec = all_elecs[numpy.argmax(numpy.abs(data))]
indices = nodes_indices[elec]
if safety_space:
all_times[indices, min_times[idx]:max_times[idx]] = True
else:
all_times[elec, min_times[idx]:max_times[idx]] = True
else:
all_times = numpy.zeros((N_e, len(local_chunk)), dtype=numpy.bool)
if do_temporal_whitening:
local_res_temp = []
for elec in all_electrodes[numpy.arange(comm.rank, nb_temp_white,
comm.size)]:
res = numpy.zeros((0, N_t), dtype=numpy.float32)
scount = 0
indices = nodes_indices[elec]
all_times_elec = numpy.any(numpy.take(all_times, indices, axis=0),
0)
esubset = numpy.where(all_times_elec == False)[0]
bound = len(esubset) - N_t
while (scount < bound) and (len(res) < max_silence_2):
myslice = esubset[scount:scount + N_t]
if numpy.all((myslice - esubset[scount]) == numpy.arange(N_t)):
scount += N_t
res = numpy.vstack((res, local_chunk[myslice, elec]))
else:
scount += 1
if len(res) > 5:
local_res_temp += [numpy.cov(res.T)]
nb_elecs = numpy.array([len(local_res_temp)], dtype=numpy.float32)
local_res_temp = numpy.array(local_res_temp, dtype=numpy.float32)
if len(local_res_temp) == 0:
local_res_temp = numpy.zeros(0, dtype=numpy.float32)
else:
local_res_temp = numpy.sum(local_res_temp, 0)
all_res_temp = gather_array(local_res_temp.ravel(), comm, 0, 1)
all_elecs = gather_array(nb_elecs, comm, 0, 1)
if do_spatial_whitening:
local_res_spac = numpy.zeros((N_e, N_e), dtype=numpy.float32)
local_silences = []
for elec in numpy.arange(comm.rank, N_e, comm.size):
indices = nodes_indices[elec]
all_times_elec = numpy.any(numpy.take(all_times, indices, axis=0),
0)
esubset = numpy.where(all_times_elec == False)[0]
local_data = local_chunk[esubset][:, indices]
local_whitening = get_whitening_matrix(
local_data, fudge=fudge).astype(numpy.float32)
pos = numpy.where(elec == indices)[0]
local_res_spac[elec, indices] = local_whitening[pos]
local_silences += [len(esubset)]
all_res_spac = gather_array(local_res_spac.ravel(), comm, 0, 1)
all_silences = gather_array(
numpy.array(local_silences, dtype=numpy.int32), comm, 0, 1,
'uint32')
if comm.rank == 0:
to_write = {}
if do_temporal_whitening:
try:
nb_silences = numpy.sum(all_elecs > 0)
all_res_temp = all_res_temp.reshape((nb_silences, N_t**2))
except Exception:
print_and_log([
"No silent periods detected: something wrong with the parameters?"
], 'error', logger)
all_res_temp = numpy.sum(all_res_temp, 0)
all_res_temp = all_res_temp.reshape(
(N_t, N_t)) / numpy.sum(all_elecs)
temporal_whitening = get_whitening_matrix(
all_res_temp.astype(numpy.double),
fudge=1e-3)[template_shift].astype(numpy.float32)
temporal_whitening /= temporal_whitening.sum()
to_write['temporal'] = temporal_whitening
have_nans = numpy.sum(numpy.isnan(temporal_whitening))
if have_nans > 0:
temporal_whitening = numpy.zeros(N_t, dtype=numpy.float32)
temporal_whitening[N_t // 2] = 1
to_write['temporal'] = temporal_whitening
print_and_log(
["Disabling temporal whitening because of NaNs found"],
'info', logger)
if do_spatial_whitening:
all_res_spac = all_res_spac.reshape(comm.size, N_e, N_e)
spatial_whitening = numpy.sum(all_res_spac, 0)
to_write['spatial'] = spatial_whitening
if ignore_spikes:
print_and_log([
"Found %gs without spikes to compute the whitening matrix..."
% (numpy.mean(all_silences) / params.rate)
], 'default', logger)
else:
print_and_log([
"Found %gs to compute the whitening matrix..." %
(numpy.mean(all_silences) / params.rate)
], 'default', logger)
have_nans = numpy.sum(numpy.isnan(spatial_whitening))
if have_nans > 0:
spatial_whitening = numpy.eye(spatial_whitening.shape[0],
dtype=numpy.float32)
to_write['spatial'] = spatial_whitening
print_and_log(
["Disabling spatial whitening because of NaNs found"],
'info', logger)
bfile = h5py.File(file_out_suff + '.basis.hdf5',
'r+',
libver='earliest')
io.write_datasets(bfile,
list(to_write.keys()),
to_write,
compression=hdf5_compress)
bfile.close()
comm.Barrier()
if do_spatial_whitening or do_temporal_whitening:
if comm.rank == 0:
print_and_log(
["Because of whitening, need to recompute the thresholds..."],
'default', logger)
if do_spatial_whitening:
spatial_whitening = io.load_data(params, 'spatial_whitening')
if use_gpu:
spatial_whitening = cmt.CUDAMatrix(spatial_whitening,
copy_on_host=False)
if do_temporal_whitening:
temporal_whitening = io.load_data(params, 'temporal_whitening')
for gidx in [all_chunks[comm.rank]]:
local_chunk, t_offset = data_file.get_data(gidx,
chunk_size,
nodes=nodes)
local_shape = len(local_chunk)
if do_spatial_whitening:
if use_gpu:
local_chunk = cmt.CUDAMatrix(local_chunk,
copy_on_host=False)
local_chunk = local_chunk.dot(spatial_whitening).asarray()
else:
local_chunk = numpy.dot(local_chunk, spatial_whitening)
if do_temporal_whitening:
local_chunk = scipy.ndimage.filters.convolve1d(
local_chunk, temporal_whitening, axis=0, mode='constant')
thresholds = numpy.zeros(N_e, dtype=numpy.float32)
for i in range(N_e):
u = numpy.median(local_chunk[:, i], 0)
thresholds[i] = numpy.median(numpy.abs(local_chunk[:, i] - u),
0)
gdata = gather_array(thresholds, comm)
if comm.rank == 0:
gdata = gdata.reshape((comm.size, N_e))
thresholds = numpy.mean(gdata, 0)
bfile = h5py.File(file_out_suff + '.basis.hdf5',
'r+',
libver='earliest')
bfile.pop('thresholds')
io.write_datasets(bfile, ['thresholds'],
{'thresholds': thresholds},
compression=hdf5_compress)
bfile.close()
comm.Barrier()
# if comm.rank == 0:
# if not os.path.exists(plot_path):
# os.makedirs(plot_path)
# N_elec = min(int(numpy.sqrt(data_file.N_e)), 5)
# plot.view_fit(filename, t_start=0, t_stop=1, fit_on=False, square=True,
# n_elec=N_elec, save=[plot_path, 'electrodes'])
# Part 2: Basis
numpy.random.seed(422)
SHARED_MEMORY = get_shared_memory_flag(params)
#################################################################
file_out = params.get('data', 'file_out')
alignment = params.getboolean('detection', 'alignment')
over_factor = params.getint('detection', 'oversampling_factor')
nb_jitter = params.getint('detection', 'nb_jitter')
spike_thresh = params.getfloat('detection', 'spike_thresh')
nodes, edges = get_nodes_and_edges(params)
_, positions = get_nodes_and_positions(params)
do_temporal_whitening = params.getboolean('whitening', 'temporal')
do_spatial_whitening = params.getboolean('whitening', 'spatial')
use_barycenter = params.getboolean('detection', 'use_barycenter')
if matched_filter:
chunk_size = detect_memory(params, whitening=True)
else:
chunk_size = detect_memory(params)
safety_time = params.getint('whitening', 'safety_time')
max_elts_elec = params.getint('whitening', 'max_elts')
output_dim = params.getfloat('whitening', 'output_dim')
inv_nodes = numpy.zeros(N_total, dtype=numpy.int32)
inv_nodes[nodes] = numpy.arange(len(nodes))
smoothing_factor = params.getfloat('detection', 'smoothing_factor')
if sign_peaks == 'both':
max_elts_elec *= 2
nb_elts = int(
params.getfloat('whitening', 'nb_elts') * N_e * max_elts_elec)
weird_thresh = params.get('detection', 'weird_thresh')
if weird_thresh != '':
ignore_artefacts = True
weird_thresh = io.load_data(params, 'weird-thresholds')
else:
ignore_artefacts = False
ignore_dead_times = params.getboolean('triggers', 'ignore_times')
if ignore_dead_times:
if SHARED_MEMORY:
all_dead_times, mpi_memory_3 = get_dead_times(params)
else:
all_dead_times = get_dead_times(params)
data_file.open()
#################################################################
if comm.rank == 0:
print_and_log(["Searching spikes to construct the PCA basis..."],
'default', logger)
nb_chunks, last_chunk_len = data_file.analyze(chunk_size)
if nb_chunks < comm.size:
res = io.data_stats(params, show=False)
chunk_size = int(res * params.rate // comm.size)
if comm.rank == 0:
print_and_log(
["Too much cores, automatically resizing the data chunks"],
'debug', logger)
nb_chunks, last_chunk_len = data_file.analyze(chunk_size)
groups = {}
for i in range(N_e):
groups[i] = 0
# I guess this is more relevant, to take signals from all over the recordings
all_chunks = numpy.random.permutation(
numpy.arange(nb_chunks, dtype=numpy.int32))
max_elts_elec //= comm.size
nb_elts //= comm.size
elt_count_pos = 0
elt_count_neg = 0
if sign_peaks in ['positive', 'both']:
times_pos = numpy.zeros(nb_elts, dtype=numpy.int32)
electrodes_pos = numpy.zeros(nb_elts, dtype=numpy.int32)
extremum_pos = numpy.zeros(nb_elts, dtype=numpy.float32)
elts_pos = numpy.zeros((N_t, nb_elts), dtype=numpy.float32)
if sign_peaks in ['negative', 'both']:
times_neg = numpy.zeros(nb_elts, dtype=numpy.int32)
electrodes_neg = numpy.zeros(nb_elts, dtype=numpy.int32)
extremum_neg = numpy.zeros(nb_elts, dtype=numpy.float32)
elts_neg = numpy.zeros((N_t, nb_elts), dtype=numpy.float32)
thresholds = io.load_data(params, 'thresholds')
mads = io.load_data(params, 'mads')
stds = io.load_data(params, 'stds')
if alignment:
cdata = numpy.linspace(-jitter_range, +jitter_range, nb_jitter)
xdata = numpy.arange(-template_shift_2, template_shift_2 + 1)
xoff = len(cdata) / 2.0
snippet_duration = template_shift_2
m_size = 2 * template_shift_2 + 1
align_factor = m_size
local_factors = align_factor * ((smoothing_factor * mads)**2)
else:
snippet_duration = template_shift
xdata = numpy.arange(-template_shift, template_shift + 1)
if rejection_threshold > 0:
reject_noise = True
noise_levels = stds * (2 * noise_window + 1)
else:
reject_noise = False
to_explore = all_chunks[comm.rank::comm.size]
upper_bounds = max_elts_elec
if comm.rank == 0:
to_explore = get_tqdm_progressbar(params, to_explore)
for gcount, gidx in enumerate(to_explore):
if (elt_count_pos + elt_count_neg) < nb_elts:
# print "Node", comm.rank, "is analyzing chunk", gidx, "/", nb_chunks, " ..."
local_chunk, t_offset = data_file.get_data(gidx,
chunk_size,
nodes=nodes)
local_shape = len(local_chunk)
if do_spatial_whitening:
if use_gpu:
local_chunk = cmt.CUDAMatrix(local_chunk,
copy_on_host=False)
local_chunk = local_chunk.dot(spatial_whitening).asarray()
else:
local_chunk = numpy.dot(local_chunk, spatial_whitening)
if do_temporal_whitening:
local_chunk = scipy.ndimage.filters.convolve1d(
local_chunk, temporal_whitening, axis=0, mode='constant')
local_borders = (snippet_duration, local_shape - snippet_duration)
if ignore_dead_times:
dead_indices = numpy.searchsorted(
all_dead_times, [t_offset, t_offset + local_shape])
# Extracting the peaks.
all_peaktimes = [numpy.empty(0, dtype=numpy.uint32)]
found_peaktimes = []
found_peak_amplitudes = []
for i in range(N_e):
height = thresholds[i]
if sign_peaks == 'negative':
peaktimes = scipy.signal.find_peaks(-local_chunk[:, i],
height=height,
distance=dist_peaks)[0]
elif sign_peaks == 'positive':
peaktimes = scipy.signal.find_peaks(local_chunk[:, i],
height=height,
distance=dist_peaks)[0]
elif sign_peaks == 'both':
peaktimes = scipy.signal.find_peaks(numpy.abs(
local_chunk[:, i]),
height=height,
distance=dist_peaks)[0]
else:
peaktimes = numpy.empty(0, dtype=numpy.uint32)
if ignore_artefacts:
artetimes = scipy.signal.find_peaks(
numpy.abs(local_chunk[:,
i]), height=weird_thresh[i])[0]
to_keep = numpy.logical_not(
numpy.in1d(peaktimes, artetimes))
peaktimes = peaktimes[to_keep]
idx = (peaktimes >= local_borders[0]) & (peaktimes <
local_borders[1])
peaktimes = peaktimes[idx]
if ignore_dead_times:
if dead_indices[0] != dead_indices[1]:
is_included = numpy.in1d(
peaktimes + t_offset,
all_dead_times[dead_indices[0]:dead_indices[1]])
peaktimes = peaktimes[~is_included]
peaktimes = peaktimes.astype(numpy.uint32)
found_peaktimes.append(peaktimes)
peak_amplitudes = local_chunk[peaktimes, i]
found_peak_amplitudes.append(peak_amplitudes)
all_peaktimes = numpy.concatenate(
found_peaktimes) # i.e. concatenate once for efficiency
all_peak_amplitudes = numpy.concatenate(found_peak_amplitudes)
local_peaktimes, local_indices = numpy.unique(all_peaktimes,
return_inverse=True)
if len(local_peaktimes) > 0:
diff_times = (local_peaktimes[-1] - local_peaktimes[0]) + 1
all_times = numpy.zeros((N_e, diff_times), dtype=numpy.bool)
padded_peaks = (local_peaktimes - local_peaktimes[0]).astype(
numpy.int32)
min_times = numpy.maximum(padded_peaks - safety_time, 0)
max_times = numpy.minimum(padded_peaks + safety_time + 1,
diff_times + 1)
test_extremas = numpy.zeros((N_e, diff_times + 1),
dtype=numpy.bool)
for i in range(N_e):
test_extremas[i, found_peaktimes[i] -
local_peaktimes[0]] = True
# Consider the peaks by decreasing extremum.
if sort_waveforms:
order = numpy.argsort(-np.abs(all_peak_amplitudes))
all_idx = numpy.take(all_peaktimes, order)
argmax_peak = local_indices[order]
else:
n_times = len(all_peaktimes)
shuffling = numpy.random.permutation(numpy.arange(n_times))
all_idx = numpy.take(all_peaktimes, shuffling)
argmax_peak = local_indices[shuffling]
# print "Selection of the peaks with spatio-temporal masks..."
for midx, peak in zip(argmax_peak, all_idx):
if (elt_count_neg + elt_count_pos) == nb_elts:
break
all_elecs = numpy.where(
test_extremas[:, peak - local_peaktimes[0]])[0]
data = local_chunk[peak, all_elecs]
#target_area = test_extremas[:, min_times[midx]:max_times[midx]].sum(1)
#all_elecs = numpy.where(target_area)[0]
#data = local_chunk[peak, all_elecs]
if sign_peaks == 'negative':
if N_e > 1:
if use_barycenter:
weighed_position = data[:, numpy.
newaxis] * positions[
all_elecs]
barycenter = weighed_position.sum(
0) / data.sum()
elec = numpy.argmin(
numpy.linalg.norm(barycenter -
positions[all_elecs],
axis=1))
else:
elec = numpy.argmin(data)
else:
elec = 0
negative_peak = True
elif sign_peaks == 'positive':
if N_e > 1:
if use_barycenter:
weighed_position = data[:, numpy.
newaxis] * positions[
all_elecs]
barycenter = weighed_position.sum(
0) / data.sum()
elec = numpy.argmax(
numpy.linalg.norm(barycenter -
positions[all_elecs],
axis=1))
else:
elec = numpy.argmax(data)
else:
elec = 0
negative_peak = False
elif sign_peaks == 'both':
if N_e == 1:
if data < 0:
negative_peak = True
elif data > 0:
negative_peak = False
elec = 0
else:
if numpy.abs(numpy.max(data)) > numpy.abs(
numpy.min(data)):
elec = numpy.argmax(data)
negative_peak = False
else:
elec = numpy.argmin(data)
negative_peak = True
elec = all_elecs[elec]
if groups[elec] < upper_bounds:
indices = nodes_indices[elec]
myslice = all_times[indices,
min_times[midx]:max_times[midx]]
if not myslice.any():
sub_mat = local_chunk[peak -
snippet_duration:peak +
snippet_duration + 1, elec]
if reject_noise:
slice_window = sub_mat[
snippet_duration -
noise_window:snippet_duration +
noise_window + 1]
value = numpy.linalg.norm(
slice_window) / noise_levels[elec]
is_noise = value < rejection_threshold
else:
is_noise = False
if not is_noise:
extrema = sub_mat[snippet_duration]
if alignment:
smoothed = True
try:
f = scipy.interpolate.UnivariateSpline(
xdata,
sub_mat,
s=local_factors[elec],
k=3)
except Exception:
smoothed = False
f = scipy.interpolate.UnivariateSpline(
xdata, sub_mat, k=3, s=0)
if negative_peak:
rmin = (numpy.argmin(f(cdata)) -
xoff) / over_factor
else:
rmin = (numpy.argmax(f(cdata)) -
xoff) / over_factor
ddata = numpy.linspace(
rmin - template_shift,
rmin + template_shift, N_t)
if smoothed:
f = scipy.interpolate.UnivariateSpline(
xdata,
sub_mat,
s=local_factors[elec],
k=3)
else:
f = scipy.interpolate.UnivariateSpline(
xdata, sub_mat, s=0, k=3)
sub_mat = f(ddata).astype(numpy.float32)
if negative_peak:
times_neg[elt_count_neg] = peak + t_offset
electrodes_neg[elt_count_neg] = elec
extremum_neg[elt_count_neg] = extrema
elts_neg[:, elt_count_neg] = sub_mat
elt_count_neg += 1
else:
times_pos[elt_count_pos] = peak + t_offset
electrodes_pos[elt_count_pos] = elec
extremum_pos[elt_count_pos] = extrema
elts_pos[:, elt_count_pos] = sub_mat
elt_count_pos += 1
groups[elec] += 1
all_times[
indices,
min_times[midx]:max_times[midx]] = True
test_extremas[elec, peak -
local_peaktimes[0]] = False
sys.stderr.flush()
print_and_log([
"Node %d has collected %d waveforms" %
(comm.rank, elt_count_pos + elt_count_neg)
], 'debug', logger)
if sign_peaks in ['negative', 'both']:
times_neg = gather_array(times_neg[:elt_count_neg],
comm,
0,
1,
dtype='int32')
electrodes_neg = gather_array(electrodes_neg[:elt_count_neg],
comm,
0,
1,
dtype='int32')
extremum_neg = gather_array(extremum_neg[:elt_count_neg], comm, 0, 1)
gdata_neg = gather_array(elts_neg[:, :elt_count_neg].T, comm, 0, 1)
if sign_peaks in ['positive', 'both']:
times_pos = gather_array(times_pos[:elt_count_pos],
comm,
0,
1,
dtype='int32')
electrodes_pos = gather_array(electrodes_pos[:elt_count_pos],
comm,
0,
1,
dtype='int32')
extremum_pos = gather_array(extremum_pos[:elt_count_pos], comm, 0, 1)
gdata_pos = gather_array(elts_pos[:, :elt_count_pos].T, comm, 0, 1)
nb_waveforms = 0
if comm.rank == 0:
# DO PCA on elts and store the basis obtained.
if sign_peaks in ['negative', 'both']:
nb_waveforms += gdata_neg.shape[0]
if sign_peaks in ['positive', 'both']:
nb_waveforms += gdata_pos.shape[0]
nb_waveforms = all_gather_array(
numpy.array([nb_waveforms], dtype=numpy.float32), comm, 0)[0]
if comm.rank == 0:
print_and_log([
"Found %d waveforms over %d requested" %
(nb_waveforms, int(nb_elts * comm.size))
], 'default', logger)
if nb_waveforms == 0:
print_and_log(
['No waveforms found! Are the data properly loaded??'],
'error', logger)
if nb_waveforms == 0:
sys.exit(0)
if comm.rank == 0:
res = {}
pca = None
pca_pos = None
pca_neg = None
warning_n_t = False
if sign_peaks in ['negative', 'both']:
res['times'] = times_neg
res['electrodes'] = electrodes_neg
res['extremum'] = extremum_neg
if len(gdata_neg) > 0:
pca = PCA(output_dim)
if use_hanning:
pca.fit(gdata_neg * hanning_filter)
else:
pca.fit(gdata_neg)
res['proj'] = pca.components_.T.astype(numpy.float32)
pca_neg = numpy.sum(pca.explained_variance_ratio_)
else:
res['proj'] = numpy.identity(int(output_dim),
dtype=numpy.float32)
res['rec'] = res['proj'].T
res['waveform'] = numpy.median(gdata_neg, 0)
# dispersion = numpy.std(gdata_neg, 0) / numpy.median(stds)
# ratio = numpy.sum(dispersion > 1.1) / float(len(dispersion))
# if ratio < 0.25:
# print_and_log(["Time window N_t in [detection] seems too large!"], 'info', logger)
# warning_n_t = True
# elif ratio == 1:
# print_and_log(["Time window N_t in [detection] seems too small!"], 'info', logger)
# warning_n_t = True
idx = numpy.random.permutation(numpy.arange(
gdata_neg.shape[0]))[:2500]
res['waveforms'] = gdata_neg[idx, :]
if sign_peaks in ['positive', 'both']:
res['times_pos'] = times_pos
res['electrodes_pos'] = electrodes_pos
res['extremum_pos'] = extremum_pos
if len(gdata_pos) > 0:
pca = PCA(output_dim)
if use_hanning:
pca.fit(gdata_pos * hanning_filter)
else:
pca.fit(gdata_pos)
res['proj_pos'] = pca.components_.T.astype(numpy.float32)
pca_pos = numpy.sum(pca.explained_variance_ratio_)
else:
res['proj_pos'] = numpy.identity(int(output_dim),
dtype=numpy.float32)
res['rec_pos'] = res['proj_pos'].T
res['waveform_pos'] = numpy.median(gdata_pos, 0)
# dispersion = numpy.std(gdata_pos, 0) / numpy.median(stds)
# ratio = numpy.sum(dispersion > 1.1) / float(len(dispersion))
# if ratio < 0.25 and not warning_n_t:
# print_and_log(["Time window N_t in [detection] seems too large!"], 'info', logger)
# elif ratio == 1 and not warning_n_t:
# print_and_log(["Time window N_t in [detection] seems too small!"], 'info', logger)
idx = numpy.random.permutation(numpy.arange(
gdata_pos.shape[0]))[:2500]
res['waveforms_pos'] = gdata_pos[idx, :]
bfile = h5py.File(file_out_suff + '.basis.hdf5',
'r+',
libver='earliest')
io.write_datasets(bfile,
list(res.keys()),
res,
compression=hdf5_compress)
if sign_peaks == 'positive':
print_and_log([
"A basis with %s dimensions has been built" %
res['proj_pos'].shape[1]
], 'info', logger)
elif sign_peaks == 'negative':
print_and_log([
"A basis with %s dimensions has been built" %
res['proj'].shape[1]
], 'info', logger)
elif sign_peaks == 'both':
print_and_log([
"Two basis with %s dimensions has been built" %
res['proj'].shape[1]
], 'debug', logger)
if pca_pos is not None:
print_and_log([
"The percentage of variance explained is %s for positive spikes"
% pca_pos
], 'debug', logger)
if pca_neg is not None:
print_and_log([
"The percentage of variance explained is %s for negative spikes"
% pca_neg
], 'debug', logger)
bfile.close()
comm.Barrier()
if matched_filter:
if comm.rank == 0:
print_and_log([
"Because of matched filters, need to recompute the thresholds..."
], 'default', logger)
if do_spatial_whitening:
spatial_whitening = io.load_data(params, 'spatial_whitening')
if use_gpu:
spatial_whitening = cmt.CUDAMatrix(spatial_whitening,
copy_on_host=False)
if do_temporal_whitening:
temporal_whitening = io.load_data(params, 'temporal_whitening')
if sign_peaks in ['negative', 'both']:
waveform_neg = io.load_data(params, 'waveform')[::-1]
waveform_neg /= (numpy.abs(numpy.sum(waveform_neg)) *
len(waveform_neg))
if sign_peaks in ['positive', 'both']:
waveform_pos = io.load_data(params, 'waveform-pos')[::-1]
waveform_pos /= (numpy.abs(numpy.sum(waveform_pos)) *
len(waveform_pos))
for gidx in [all_chunks[comm.rank]]:
local_chunk, t_offset = data_file.get_data(gidx,
chunk_size,
nodes=nodes)
local_shape = len(local_chunk)
if do_spatial_whitening:
if use_gpu:
local_chunk = cmt.CUDAMatrix(local_chunk,
copy_on_host=False)
local_chunk = local_chunk.dot(spatial_whitening).asarray()
else:
local_chunk = numpy.dot(local_chunk, spatial_whitening)
if do_temporal_whitening:
local_chunk = scipy.ndimage.filters.convolve1d(
local_chunk, temporal_whitening, axis=0, mode='constant')
local_chunk /= thresholds
if sign_peaks in ['negative', 'both']:
tmp_chunk = scipy.ndimage.filters.convolve1d(local_chunk,
waveform_neg,
axis=0,
mode='constant')
thresholds = numpy.zeros(N_e, dtype=numpy.float32)
for i in range(N_e):
u = numpy.median(tmp_chunk[:, i], 0)
thresholds[i] = numpy.median(
numpy.abs(tmp_chunk[:, i] - u), 0)
gdata = gather_array(thresholds, comm)
if comm.rank == 0:
gdata = gdata.reshape((comm.size, N_e))
thresholds = numpy.mean(gdata, 0)
bfile = h5py.File(file_out_suff + '.basis.hdf5',
'r+',
libver='earliest')
io.write_datasets(bfile, ['matched_thresholds'],
{'matched_thresholds': thresholds},
compression=hdf5_compress)
bfile.close()
comm.Barrier()
if sign_peaks in ['positive', 'both']:
tmp_chunk = scipy.ndimage.filters.convolve1d(local_chunk,
waveform_pos,
axis=0,
mode='constant')
thresholds = numpy.zeros(N_e, dtype=numpy.float32)
for i in range(N_e):
u = numpy.median(tmp_chunk[:, i], 0)
thresholds[i] = numpy.median(
numpy.abs(tmp_chunk[:, i] - u), 0)
gdata = gather_array(thresholds, comm)
if comm.rank == 0:
gdata = gdata.reshape((comm.size, N_e))
thresholds = numpy.mean(gdata, 0)
bfile = h5py.File(file_out_suff + '.basis.hdf5',
'r+',
libver='earliest')
io.write_datasets(bfile, ['matched_thresholds_pos'],
{'matched_thresholds_pos': thresholds},
compression=hdf5_compress)
bfile.close()
comm.Barrier()
data_file.close()
if SHARED_MEMORY and ignore_dead_times:
mpi_memory_3.Free()
def main(params, nb_cpu, nb_gpu, use_gpu):
numpy.random.seed(426236)
# params = detect_memory(params)
parallel_hdf5 = get_parallel_hdf5_flag(params)
_ = init_logging(params.logfile)
logger = logging.getLogger('circus.extracting')
#################################################################
data_file = params.data_file
N_e = params.getint('data', 'N_e')
N_t = params.getint('detection', 'N_t')
N_total = params.nb_channels
template_shift = params.getint('detection', 'template_shift')
chunk_size = detect_memory(params)
file_out = params.get('data', 'file_out')
file_out_suff = params.get('data', 'file_out_suff')
do_temporal_whitening = params.getboolean('whitening', 'temporal')
do_spatial_whitening = params.getboolean('whitening', 'spatial')
nodes, edges = get_nodes_and_edges(params)
safety_time = params.getint('extracting', 'safety_time')
max_elts_temp = params.getint('extracting', 'max_elts')
output_dim = params.getfloat('extracting', 'output_dim')
noise_thr = params.getfloat('extracting', 'noise_thr')
hdf5_compress = params.getboolean('data', 'hdf5_compress')
blosc_compress = params.getboolean('data', 'blosc_compress')
tmp_limits = params.get('fitting',
'amp_limits').replace('(',
'').replace(')',
'').split(',')
amp_limits = map(float, tmp_limits)
elt_count = 0
inv_nodes = numpy.zeros(N_total, dtype=numpy.int32)
inv_nodes[nodes] = numpy.arange(len(nodes))
data_file.open()
#################################################################
if comm.rank == 0:
print_and_log(["Extracting templates from already found clusters..."],
'default', logger)
thresholds = io.load_data(params, 'thresholds')
basis_proj, basis_rec = io.load_data(params, 'basis')
clusters, spiketimes, N_clusters = io.load_data(params, 'spike-cluster')
inv_clusters = numpy.zeros(clusters.max() + 1, dtype=numpy.int32)
inv_clusters[numpy.unique(clusters)] = numpy.argsort(
numpy.unique(clusters))
if use_gpu:
import cudamat as cmt
# # Need to properly handle multi GPU per MPI nodes?
if nb_gpu > nb_cpu:
gpu_id = int(comm.rank // nb_cpu)
else:
gpu_id = 0
cmt.cuda_set_device(gpu_id)
cmt.init()
cmt.cuda_sync_threads()
if do_spatial_whitening:
spatial_whitening = io.load_data(params, 'spatial_whitening')
else:
spatial_whitening = None # default assignment (PyCharm code inspection)
if do_temporal_whitening:
temporal_whitening = io.load_data(params, 'temporal_whitening')
else:
temporal_whitening = None # default assignment (PyCharm code inspection)
if use_gpu and do_spatial_whitening:
spatial_whitening = cmt.CUDAMatrix(spatial_whitening,
copy_on_host=False)
result = {}
for i in range(N_clusters):
result['data_tmp_' + str(i)] = numpy.zeros(
(0, N_e * basis_proj.shape[1]), dtype=numpy.float32)
result['times_' + str(i)] = numpy.zeros(0, dtype=numpy.int32)
nb_chunks, last_chunk_len = data_file.analyze(chunk_size)
# I guess this is more relevant, to take signals from all over the recordings.
all_chunks = numpy.random.permutation(numpy.arange(nb_chunks))
nb_templates = numpy.sum(
comm.rank == numpy.mod(numpy.arange(N_clusters), comm.size))
nb_elts = max_elts_temp * nb_templates
to_explore = all_chunks
if comm.rank == 0:
to_explore = get_tqdm_progressbar(params, to_explore)
for gidx in all_chunks:
if elt_count < nb_elts:
# print "Node", comm.rank, "is analyzing chunk", gidx, "/", nb_chunks, " ..."
local_chunk, t_offset = data_file.get_data(gidx,
chunk_size,
nodes=nodes)
local_shape = len(local_chunk)
if do_spatial_whitening:
if use_gpu:
local_chunk = cmt.CUDAMatrix(local_chunk,
copy_on_host=False)
local_chunk = local_chunk.dot(spatial_whitening).asarray()
else:
local_chunk = numpy.dot(local_chunk, spatial_whitening)
if do_temporal_whitening:
local_chunk = scipy.ndimage.filters.convolve1d(
local_chunk, temporal_whitening, axis=0, mode='constant')
# print "Extracting the peaks..."
idx = numpy.where((spiketimes >= gidx * chunk_size)
& (spiketimes < (gidx + 1) * chunk_size))[0]
local_offset = t_offset
local_peaktimes = spiketimes[idx] - local_offset
# print "Removing the useless borders..."
local_borders = (template_shift, chunk_size - template_shift)
idx = (local_peaktimes >= local_borders[0]) & (local_peaktimes <
local_borders[1])
local_peaktimes = local_peaktimes[idx]
local_clusters = inv_clusters[clusters[idx]]
if len(local_peaktimes) > 0:
all_times = numpy.zeros(
(N_e, local_peaktimes[-1] - local_peaktimes[0] + 1),
dtype=numpy.bool)
min_times = numpy.maximum(
local_peaktimes - local_peaktimes[0] - safety_time, 0)
max_times = numpy.minimum(
local_peaktimes - local_peaktimes[0] + safety_time + 1,
local_peaktimes[-1] - local_peaktimes[0])
n_times = len(local_peaktimes)
argmax_peak = numpy.random.permutation(numpy.arange(n_times))
clusters_id = local_clusters[argmax_peak]
local_peaktimes = local_peaktimes[argmax_peak]
# print "Selection of the peaks with spatio-temporal masks..."
for idx in range(len(local_peaktimes)):
if elt_count == nb_elts:
break
temp = clusters_id[idx]
if numpy.mod(temp, comm.size) == comm.rank:
elec = numpy.argmin(local_chunk[local_peaktimes[idx]])
indices = inv_nodes[edges[nodes[elec]]]
myslice = all_times[indices,
min_times[idx]:max_times[idx]]
peak = local_peaktimes[idx]
if not myslice.any():
if len(result['data_tmp_' +
str(temp)]) < max_elts_temp:
elt_count += 1
sub_mat = local_chunk[peak -
template_shift:peak +
template_shift + 1, :]
sub_mat = numpy.dot(basis_rec, sub_mat)
nx, ny = sub_mat.shape
sub_mat = sub_mat.reshape((1, nx * ny))
result['data_tmp_' + str(temp)] = numpy.vstack(
(result['data_tmp_' + str(temp)], sub_mat))
to_add = numpy.array([peak + local_offset],
dtype=numpy.int32)
result['times_' +
str(temp)] = numpy.concatenate(
(result['times_' + str(temp)],
to_add))
all_times[indices,
min_times[idx]:max_times[idx]] = True
total_nb_elts = 0
for temp in range(N_clusters):
total_nb_elts += len(result['data_tmp_' + str(temp)])
gdata = gather_array(numpy.array([total_nb_elts], dtype=numpy.float32),
comm, 0)
if comm.rank == 0:
print_and_log([
"Found %d spikes over %d requested" %
(int(numpy.sum(gdata)), int(nb_elts))
], 'default', logger)
# print "Spikes extracted in", time.time() - t_start, "s"
comm.Barrier()
local_nb_clusters = 0
for temp in range(comm.rank, N_clusters, comm.size):
if len(result['data_tmp_' + str(temp)]) > 0:
local_nb_clusters += 1
# print total_nb_clusters, "found in", time.time() - t_start, "s"
gdata3 = gather_array(
numpy.array([local_nb_clusters], dtype=numpy.float32), comm, 0)
comm.Barrier()
if comm.rank == 0:
print_and_log(["Extracting the templates..."], 'default', logger)
total_nb_clusters = int(
comm.bcast(numpy.array([int(numpy.sum(gdata3))], dtype=numpy.int32),
root=0)[0])
offsets = numpy.zeros(comm.size, dtype=numpy.int32)
for i in range(comm.size - 1):
offsets[i + 1] = comm.bcast(numpy.array([local_nb_clusters],
dtype=numpy.int32),
root=i)
if parallel_hdf5:
node_pad = numpy.sum(offsets[:comm.rank + 1])
hfile = h5py.File(file_out_suff + '.templates.hdf5',
'w',
driver='mpio',
comm=comm,
libver='earliest')
norms = hfile.create_dataset('norms',
shape=(2 * total_nb_clusters, ),
dtype=numpy.float32,
chunks=True)
electrodes = hfile.create_dataset('electrodes',
shape=(total_nb_clusters, ),
dtype=numpy.int32,
chunks=True)
amps_lims = hfile.create_dataset('limits',
shape=(total_nb_clusters, 2),
dtype=numpy.float32,
chunks=True)
g_count = node_pad
g_offset = total_nb_clusters
else:
node_pad = 0
hfile = h5py.File(file_out_suff + '.templates-%d.hdf5' % comm.rank,
'w',
libver='earliest')
electrodes = hfile.create_dataset('electrodes',
shape=(local_nb_clusters, ),
dtype=numpy.int32,
chunks=True)
norms = hfile.create_dataset('norms',
shape=(2 * local_nb_clusters, ),
dtype=numpy.float32,
chunks=True)
amps_lims = hfile.create_dataset('limits',
shape=(local_nb_clusters, 2),
dtype=numpy.float32,
chunks=True)
g_count = 0
g_offset = local_nb_clusters
cfile = h5py.File(file_out_suff + '.clusters-%d.hdf5' % comm.rank,
'w',
libver='earliest')
count_templates = node_pad
temp_x = numpy.zeros(0, dtype=numpy.int32)
temp_y = numpy.zeros(0, dtype=numpy.int32)
temp_data = numpy.zeros(0, dtype=numpy.float32)
to_explore = range(comm.rank, N_clusters, comm.size)
if comm.rank == 0:
to_explore = get_tqdm_progressbar(params, to_explore)
for temp in to_explore:
n_data = len(result['data_tmp_' + str(temp)])
if n_data > 0:
data = result['data_tmp_' + str(temp)].reshape(
n_data, basis_proj.shape[1], N_e)
first_component = numpy.median(data, axis=0)
tmp_templates = numpy.dot(first_component.T, basis_rec)
electrodes[g_count] = indices[tmpidx[0][0]]
indices = inv_nodes[edges[nodes[electrodes[-1]]]]
templates = numpy.zeros((N_e, N_t), dtype=numpy.float32)
if shift > 0:
templates[indices, shift:] = tmp_templates[:, :-shift]
elif shift < 0:
templates[indices, :shift] = tmp_templates[:, -shift:]
else:
templates[indices, :] = tmp_templates
templates = templates.flatten()
dx = templates.nonzero()[0].astype(numpy.int32)
temp_x = numpy.concatenate((temp_x, dx))
temp_y = numpy.concatenate(
(temp_y,
count_templates * numpy.ones(len(dx), dtype=numpy.int32)))
temp_data = numpy.concatenate((temp_data, templates[dx]))
norms[g_count] = numpy.sqrt(
numpy.sum(templates.flatten()**2) / (N_e * N_t))
x, y, z = data.shape
data_flat = data.reshape(x, y * z)
first_flat = first_component.reshape(y * z, 1)
amplitudes = numpy.dot(data_flat, first_flat)
amplitudes /= numpy.sum(first_flat**2)
for i in range(x):
data_flat[i, :] -= amplitudes[i] * first_flat[:, 0]
variations = 10 * numpy.median(
numpy.abs(amplitudes - numpy.median(amplitudes)))
physical_limit = noise_thr * (
-thresholds[indices[tmpidx[0][0]]]) / tmp_templates.min()
amp_min = max(physical_limit,
numpy.median(amplitudes) - variations)
amp_max = min(amp_limits[1], numpy.median(amplitudes) + variations)
amps_lims[g_count] = [amp_min, amp_max]
if len(data_flat) > 1:
pca = PCA(1)
res_pca = pca.fit_transform(data_flat.astype(numpy.double))
second_component = pca.components_.T.astype(
numpy.float32).reshape(y, z)
else:
second_component = data_flat.reshape(y, z) / numpy.sum(
data_flat**2)
tmp_templates = numpy.dot(second_component.T, basis_rec)
offset = total_nb_clusters + count_templates
sub_templates = numpy.zeros((N_e, N_t), dtype=numpy.float32)
if shift > 0:
sub_templates[indices, shift:] = tmp_templates[:, :-shift]
elif shift < 0:
sub_templates[indices, :shift] = tmp_templates[:, -shift:]
else:
sub_templates[indices, :] = tmp_templates
sub_templates = sub_templates.flatten()
dx = sub_templates.nonzero()[0].astype(numpy.int32)
temp_x = numpy.concatenate((temp_x, dx))
temp_y = numpy.concatenate(
(temp_y, offset * numpy.ones(len(dx), dtype=numpy.int32)))
temp_data = numpy.concatenate((temp_data, sub_templates[dx]))
norms[g_count + g_offset] = numpy.sqrt(
numpy.sum(sub_templates.flatten()**2) / (N_e * N_t))
count_templates += 1
g_count += 1
io.write_datasets(cfile,
to_write,
result,
ielec,
compress=hdf5_compress)
# At the end we should have a templates variable to store.
cfile.close()
del result, templates, amps_lims
comm.Barrier()
# We need to gather the sparse arrays.
temp_x = gather_array(temp_x, comm, dtype='int32', compress=blosc_compress)
temp_y = gather_array(temp_y, comm, dtype='int32', compress=blosc_compress)
temp_data = gather_array(temp_data, comm, compress=blosc_compress)
if parallel_hdf5:
if comm.rank == 0:
rs = [
h5py.File(file_out_suff + '.clusters-%d.hdf5' % i,
'r',
libver='earliest') for i in range(comm.size)
]
cfile = h5py.File(file_out_suff + '.clusters.hdf5',
'w',
libver='earliest')
io.write_datasets(cfile, ['electrodes'],
{'electrodes': electrodes[:]},
compress=hdf5_compress)
for i in range(comm.size):
for j in range(i, N_e, comm.size):
io.write_datasets(cfile,
to_write,
rs[i],
j,
compress=hdf5_compress)
rs[i].close()
os.remove(file_out_suff + '.clusters-%d.hdf5' % i)
cfile.close()
hfile.close()
else:
hfile.close()
if comm.rank == 0:
ts = [
h5py.File(file_out_suff + '.templates-%d.hdf5' % i,
'r',
libver='earliest') for i in range(comm.size)
]
rs = [
h5py.File(file_out_suff + '.clusters-%d.hdf5' % i,
'r',
libver='earliest') for i in range(comm.size)
]
result = {}
hfile = h5py.File(file_out_suff + '.templates.hdf5',
'w',
libver='earliest')
cfile = h5py.File(file_out_suff + '.clusters.hdf5',
'w',
libver='earliest')
electrodes = hfile.create_dataset('electrodes',
shape=(total_nb_clusters, ),
dtype=numpy.int32,
chunks=True)
norms = hfile.create_dataset('norms',
shape=(2 * total_nb_clusters, ),
dtype=numpy.float32,
chunks=True)
amplitudes = hfile.create_dataset('limits',
shape=(total_nb_clusters, 2),
dtype=numpy.float32,
chunks=True)
count = 0
for i in range(comm.size):
loc_temp = ts[i].get('templates')
middle = loc_temp.shape[2] // 2
norms[count:count + middle] = loc_norms[:middle]
norms[n_clusters + count:n_clusters + count +
middle] = loc_norms[middle:]
electrodes[count:count + middle] = ts[i].get('electrodes')
amplitudes[count:count + middle] = ts[i].get('limits')
count += middle
for j in range(i, N_e, comm.size):
io.write_datasets(cfile,
to_write,
rs[i],
j,
compress=hdf5_compress)
ts[i].close()
rs[i].close()
os.remove(file_out_suff + '.templates-%d.hdf5' % i)
os.remove(file_out_suff + '.clusters-%d.hdf5' % i)
io.write_datasets(cfile, ['electrodes'],
{'electrodes': electrodes[:]},
compress=hdf5_compress)
hfile.close()
cfile.close()
if comm.rank == 0:
hfile = h5py.File(file_out_suff + '.templates.hdf5',
'r+',
libver='earliest')
hfile.create_dataset('temp_x', data=temp_x)
hfile.create_dataset('temp_y', data=temp_y)
hfile.create_dataset('temp_data', data=temp_data)
hfile.create_dataset('temp_shape',
data=numpy.array(
[N_e, N_t, 2 * total_nb_clusters],
dtype=numpy.int32))
hfile.close()
comm.Barrier()
if comm.rank == 0:
print_and_log(["Merging similar templates..."], 'default', logger)
merged1 = algo.merging_cc(params, parallel_hdf5)
comm.Barrier()
if remove_mixture:
if comm.rank == 0:
print_and_log(["Removing mixtures..."], 'default', logger)
merged2 = algo.delete_mixtures(params, parallel_hdf5)
else:
merged2 = [0, 0]
if comm.rank == 0:
lines = [
"Number of global merges : %d" % merged1[1],
"Number of mixtures removed : %d" % merged2[1],
]
print_and_log(lines, 'info', logger)
comm.Barrier()
io.get_overlaps(params, erase=True, parallel_hdf5=parallel_hdf5)
data_file.close()
