DARTsort 0.3.5__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- dartsort/__init__.py +68 -0
- dartsort/cli.py +105 -0
- dartsort/clustering/__init__.py +3 -0
- dartsort/clustering/cluster_util.py +392 -0
- dartsort/clustering/clustering.py +765 -0
- dartsort/clustering/clustering_features.py +202 -0
- dartsort/clustering/density.py +1299 -0
- dartsort/clustering/forward_backward.py +219 -0
- dartsort/clustering/gmm/mixture.py +5790 -0
- dartsort/clustering/gmm/stable_features.py +993 -0
- dartsort/clustering/kmeans.py +448 -0
- dartsort/clustering/merge.py +501 -0
- dartsort/clustering/modes.py +214 -0
- dartsort/clustering/refine_util.py +191 -0
- dartsort/clustering/relocate.py +109 -0
- dartsort/clustering/split.py +1285 -0
- dartsort/config.py +288 -0
- dartsort/detect/__init__.py +2 -0
- dartsort/detect/detect.py +449 -0
- dartsort/detect/detect_filters.py +37 -0
- dartsort/evaluate/__init__.py +1 -0
- dartsort/evaluate/analysis.py +594 -0
- dartsort/evaluate/comparison.py +534 -0
- dartsort/evaluate/hybrid_util.py +599 -0
- dartsort/evaluate/noise_recording_tools.py +184 -0
- dartsort/evaluate/sim_template_tools.py +842 -0
- dartsort/evaluate/simkit.py +840 -0
- dartsort/evaluate/simlib.py +270 -0
- dartsort/localize/__init__.py +0 -0
- dartsort/localize/localize_torch.py +291 -0
- dartsort/localize/localize_util.py +313 -0
- dartsort/main.py +657 -0
- dartsort/peel/__init__.py +6 -0
- dartsort/peel/grab.py +208 -0
- dartsort/peel/matching.py +628 -0
- dartsort/peel/matching_util/__init__.py +3 -0
- dartsort/peel/matching_util/compressed_upsampled.py +718 -0
- dartsort/peel/matching_util/drifty.py +791 -0
- dartsort/peel/matching_util/matching_base.py +616 -0
- dartsort/peel/matching_util/pairwise.py +359 -0
- dartsort/peel/matching_util/pairwise_util.py +1317 -0
- dartsort/peel/peel_base.py +1000 -0
- dartsort/peel/running_template.py +1498 -0
- dartsort/peel/subtract.py +1123 -0
- dartsort/peel/threshold.py +471 -0
- dartsort/peel/universal.py +191 -0
- dartsort/pretrained/default_temporal_kernel.npy +0 -0
- dartsort/pretrained/detect_np1.pt +0 -0
- dartsort/pretrained/detect_np2.pt +0 -0
- dartsort/pretrained/glasbey1024.npz +0 -0
- dartsort/pretrained/offset_trained_denoiser.pt +0 -0
- dartsort/pretrained/offset_trained_denoiser_added_temp.pt +0 -0
- dartsort/pretrained/offset_trained_denoiser_added_temp_boost.pt +0 -0
- dartsort/pretrained/original_single_chan_denoiser.pt +0 -0
- dartsort/pretrained/single_chan_denoiser.pt +0 -0
- dartsort/templates/__init__.py +11 -0
- dartsort/templates/get_templates.py +771 -0
- dartsort/templates/postprocess_util.py +555 -0
- dartsort/templates/realignment.py +466 -0
- dartsort/templates/superres_util.py +204 -0
- dartsort/templates/template_util.py +518 -0
- dartsort/templates/templates.py +528 -0
- dartsort/transform/__init__.py +2 -0
- dartsort/transform/_multichan_denoiser_kit.py +650 -0
- dartsort/transform/all_transformers.py +58 -0
- dartsort/transform/amortized_localization.py +503 -0
- dartsort/transform/amplitudes.py +197 -0
- dartsort/transform/decollider.py +635 -0
- dartsort/transform/enforce_decrease.py +158 -0
- dartsort/transform/localize.py +86 -0
- dartsort/transform/matching_denoiser.py +44 -0
- dartsort/transform/pipeline.py +391 -0
- dartsort/transform/single_channel_denoiser.py +153 -0
- dartsort/transform/single_channel_templates.py +98 -0
- dartsort/transform/supervised_denoiser.py +486 -0
- dartsort/transform/temporal_pca.py +413 -0
- dartsort/transform/transform_base.py +255 -0
- dartsort/util/__init__.py +0 -0
- dartsort/util/cli_util.py +179 -0
- dartsort/util/data_util.py +1128 -0
- dartsort/util/drift_util.py +1054 -0
- dartsort/util/internal_config.py +1074 -0
- dartsort/util/interpolation_util.py +1012 -0
- dartsort/util/job_util.py +19 -0
- dartsort/util/logging_util.py +91 -0
- dartsort/util/main_util.py +235 -0
- dartsort/util/more_operators.py +269 -0
- dartsort/util/multiprocessing_util.py +211 -0
- dartsort/util/nn_util.py +461 -0
- dartsort/util/noise_util.py +1461 -0
- dartsort/util/peel_util.py +223 -0
- dartsort/util/py_util.py +213 -0
- dartsort/util/registration_util.py +128 -0
- dartsort/util/residual_util.py +30 -0
- dartsort/util/sparse_util.py +81 -0
- dartsort/util/spikeio.py +227 -0
- dartsort/util/spiketorch.py +1198 -0
- dartsort/util/testing_util/__init__.py +0 -0
- dartsort/util/testing_util/matching_debug_util.py +517 -0
- dartsort/util/testing_util/mixture_testing_util.py +291 -0
- dartsort/util/torch_optimization_util.py +156 -0
- dartsort/util/torch_util.py +75 -0
- dartsort/util/universal_util.py +269 -0
- dartsort/util/waveform_util.py +809 -0
- dartsort/vis/__init__.py +19 -0
- dartsort/vis/analysis_plots.py +392 -0
- dartsort/vis/colors.py +36 -0
- dartsort/vis/gt.py +392 -0
- dartsort/vis/layout.py +149 -0
- dartsort/vis/metrics_util.py +23 -0
- dartsort/vis/mixture.py +1489 -0
- dartsort/vis/over_time.py +514 -0
- dartsort/vis/recanim.py +429 -0
- dartsort/vis/scatterplots.py +779 -0
- dartsort/vis/sorting.py +163 -0
- dartsort/vis/unit.py +917 -0
- dartsort/vis/unit_comparison.py +1017 -0
- dartsort/vis/versus.py +300 -0
- dartsort/vis/vismain.py +537 -0
- dartsort/vis/waveforms.py +357 -0
- dartsort-0.3.5.dist-info/METADATA +93 -0
- dartsort-0.3.5.dist-info/RECORD +125 -0
- dartsort-0.3.5.dist-info/WHEEL +5 -0
- dartsort-0.3.5.dist-info/entry_points.txt +2 -0
- dartsort-0.3.5.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,219 @@
|
|
|
1
|
+
import numpy as np
|
|
2
|
+
from tqdm.auto import trange
|
|
3
|
+
|
|
4
|
+
|
|
5
|
+
def forward_backward(
|
|
6
|
+
chunk_time_ranges_s,
|
|
7
|
+
chunk_sortings,
|
|
8
|
+
log_c=5.0,
|
|
9
|
+
feature_scales=(1, 1, 50),
|
|
10
|
+
adaptive_feature_scales=False,
|
|
11
|
+
motion_est=None,
|
|
12
|
+
verbose=True,
|
|
13
|
+
min_cluster_size=25,
|
|
14
|
+
):
|
|
15
|
+
"""
|
|
16
|
+
Ensemble over HDBSCAN clustering
|
|
17
|
+
triaging/subsampling/copying/splitting big clusters not implemented since we don't use it (so far)
|
|
18
|
+
"""
|
|
19
|
+
if len(chunk_sortings) == 1:
|
|
20
|
+
return chunk_sortings[0].labels
|
|
21
|
+
|
|
22
|
+
times_seconds = chunk_sortings[0].times_seconds
|
|
23
|
+
|
|
24
|
+
min_time_s = chunk_time_ranges_s[0][0]
|
|
25
|
+
idx_all_chunks = [
|
|
26
|
+
get_indices_in_chunk(times_seconds, chunk_range)
|
|
27
|
+
for chunk_range in chunk_time_ranges_s
|
|
28
|
+
]
|
|
29
|
+
|
|
30
|
+
# put all labels into one array
|
|
31
|
+
# TODO: this does not allow for overlapping chunks.
|
|
32
|
+
labels_all = np.full_like(times_seconds, -1)
|
|
33
|
+
for ix, sorting in zip(idx_all_chunks, chunk_sortings):
|
|
34
|
+
if len(ix): # type: ignore
|
|
35
|
+
assert labels_all[ix].max() < 0 # assert non-overlapping
|
|
36
|
+
labels_all[ix] = sorting.labels[ix]
|
|
37
|
+
|
|
38
|
+
# load features that we will need
|
|
39
|
+
# needs to be all features here
|
|
40
|
+
amps = chunk_sortings[0].denoised_ptp_amplitudes
|
|
41
|
+
xyza = chunk_sortings[0].point_source_localizations
|
|
42
|
+
|
|
43
|
+
x = xyza[:, 0]
|
|
44
|
+
z_reg = xyza[:, 2]
|
|
45
|
+
|
|
46
|
+
if adaptive_feature_scales:
|
|
47
|
+
feature_scales = (
|
|
48
|
+
1,
|
|
49
|
+
1,
|
|
50
|
+
np.median(np.abs(x - np.median(x)))
|
|
51
|
+
/ np.median(np.abs(np.log(log_c + amps) - np.median(np.log(log_c + amps)))),
|
|
52
|
+
)
|
|
53
|
+
|
|
54
|
+
if motion_est is not None:
|
|
55
|
+
z_reg = motion_est.correct_s(times_seconds, z_reg)
|
|
56
|
+
|
|
57
|
+
if verbose is True:
|
|
58
|
+
tbar = trange(len(chunk_sortings) - 1, desc="Ensembling chunks")
|
|
59
|
+
else:
|
|
60
|
+
tbar = range(len(chunk_sortings) - 1)
|
|
61
|
+
for k in tbar:
|
|
62
|
+
idx_1 = np.flatnonzero(
|
|
63
|
+
np.logical_and(
|
|
64
|
+
times_seconds >= min_time_s,
|
|
65
|
+
times_seconds < chunk_time_ranges_s[k][1],
|
|
66
|
+
)
|
|
67
|
+
)
|
|
68
|
+
idx_2 = idx_all_chunks[k + 1]
|
|
69
|
+
x_1 = feature_scales[0] * x[idx_1]
|
|
70
|
+
x_2 = feature_scales[0] * x[idx_2]
|
|
71
|
+
z_1 = feature_scales[1] * z_reg[idx_1]
|
|
72
|
+
z_2 = feature_scales[1] * z_reg[idx_2]
|
|
73
|
+
amps_1 = feature_scales[2] * np.log(log_c + amps[idx_1])
|
|
74
|
+
amps_2 = feature_scales[2] * np.log(log_c + amps[idx_2])
|
|
75
|
+
labels_1 = labels_all[idx_1].copy().astype("int")
|
|
76
|
+
labels_2 = chunk_sortings[k + 1].labels[idx_2]
|
|
77
|
+
|
|
78
|
+
units_1 = np.unique(labels_1)
|
|
79
|
+
units_1 = units_1[units_1 > -1]
|
|
80
|
+
units_2 = np.unique(labels_2)
|
|
81
|
+
units_2 = units_2[units_2 > -1]
|
|
82
|
+
|
|
83
|
+
features1 = np.c_[x_1, z_1, amps_1]
|
|
84
|
+
features2 = np.c_[x_2, z_2, amps_2]
|
|
85
|
+
|
|
86
|
+
if len(units_2) and len(units_1):
|
|
87
|
+
unit_label_shift = int(labels_1.max() + 1)
|
|
88
|
+
labels_2[labels_2 > -1] += unit_label_shift
|
|
89
|
+
units_2 += unit_label_shift
|
|
90
|
+
|
|
91
|
+
# FORWARD PASS
|
|
92
|
+
dist_matrix = np.zeros((units_1.shape[0], units_2.shape[0]))
|
|
93
|
+
for i, unit_1 in enumerate(units_1):
|
|
94
|
+
for j, unit_2 in enumerate(units_2):
|
|
95
|
+
idxunit1 = np.flatnonzero(labels_1 == unit_1)[-min_cluster_size:]
|
|
96
|
+
idxunit2 = np.flatnonzero(labels_2 == unit_2)[:min_cluster_size]
|
|
97
|
+
feat_1 = np.median(features1[idxunit1], axis=0)
|
|
98
|
+
feat_2 = np.median(features2[idxunit2], axis=0)
|
|
99
|
+
dist_matrix[i, j] = ((feat_1 - feat_2) ** 2).sum()
|
|
100
|
+
|
|
101
|
+
# find for chunk 2 units the closest units in chunk 1 and split chunk 1 units
|
|
102
|
+
dist_forward = dist_matrix.argmin(0)
|
|
103
|
+
units_, counts_ = np.unique(dist_forward, return_counts=True)
|
|
104
|
+
|
|
105
|
+
for unit_to_split in units_[counts_ > 1]:
|
|
106
|
+
units_to_match_to = (
|
|
107
|
+
np.flatnonzero(dist_forward == unit_to_split) + unit_label_shift
|
|
108
|
+
)
|
|
109
|
+
|
|
110
|
+
idxunit2 = np.flatnonzero(labels_2 == units_to_match_to[0])
|
|
111
|
+
features_to_match_to = np.median(features2[idxunit2], axis=0)
|
|
112
|
+
|
|
113
|
+
for u in units_to_match_to[1:]:
|
|
114
|
+
idxunit2 = np.flatnonzero(labels_2 == u)
|
|
115
|
+
features_to_match_to = np.c_[
|
|
116
|
+
features_to_match_to, np.median(features2[idxunit2], axis=0)
|
|
117
|
+
]
|
|
118
|
+
|
|
119
|
+
spikes_to_update = np.flatnonzero(labels_1 == unit_to_split)
|
|
120
|
+
feat_s = features1[spikes_to_update]
|
|
121
|
+
labels_1[spikes_to_update] = units_to_match_to[
|
|
122
|
+
((features_to_match_to.T[:, None] - feat_s[None]) ** 2)
|
|
123
|
+
.sum(2)
|
|
124
|
+
.argmin(0)
|
|
125
|
+
]
|
|
126
|
+
|
|
127
|
+
# Relabel labels_1 and labels_2
|
|
128
|
+
for unit_to_relabel in units_:
|
|
129
|
+
if counts_[np.flatnonzero(units_ == unit_to_relabel)][0] == 1:
|
|
130
|
+
idx_to_relabel = np.flatnonzero(labels_1 == unit_to_relabel)
|
|
131
|
+
labels_1[idx_to_relabel] = units_2[dist_forward == unit_to_relabel]
|
|
132
|
+
|
|
133
|
+
# BACKWARD PASS
|
|
134
|
+
units_not_matched = np.unique(labels_1)
|
|
135
|
+
units_not_matched = units_not_matched[units_not_matched > -1]
|
|
136
|
+
units_not_matched = units_not_matched[units_not_matched < unit_label_shift]
|
|
137
|
+
|
|
138
|
+
if len(units_not_matched):
|
|
139
|
+
all_units_to_match_to = (
|
|
140
|
+
dist_matrix[units_not_matched].argmin(1) + unit_label_shift
|
|
141
|
+
)
|
|
142
|
+
for unit_to_split in np.unique(all_units_to_match_to):
|
|
143
|
+
units_to_match_to = np.concatenate(
|
|
144
|
+
(
|
|
145
|
+
units_not_matched[all_units_to_match_to == unit_to_split],
|
|
146
|
+
[unit_to_split],
|
|
147
|
+
)
|
|
148
|
+
)
|
|
149
|
+
|
|
150
|
+
features_to_match_to = np.median(
|
|
151
|
+
features1[labels_1 == units_to_match_to[0]], axis=0
|
|
152
|
+
)
|
|
153
|
+
for u in units_to_match_to[1:]:
|
|
154
|
+
features_to_match_to = np.c_[
|
|
155
|
+
features_to_match_to,
|
|
156
|
+
np.median(features1[labels_1 == u], axis=0),
|
|
157
|
+
]
|
|
158
|
+
|
|
159
|
+
spikes_to_update = np.flatnonzero(labels_2 == unit_to_split)
|
|
160
|
+
features2[spikes_to_update]
|
|
161
|
+
labels_2[spikes_to_update] = units_to_match_to[
|
|
162
|
+
(
|
|
163
|
+
(
|
|
164
|
+
features_to_match_to.T[:, None]
|
|
165
|
+
- features2[spikes_to_update][None]
|
|
166
|
+
)
|
|
167
|
+
** 2
|
|
168
|
+
)
|
|
169
|
+
.sum(2)
|
|
170
|
+
.argmin(0)
|
|
171
|
+
]
|
|
172
|
+
|
|
173
|
+
# Do we need to "regularize" and make sure the distance intra units after merging is smaller than the distance inter units before merging
|
|
174
|
+
# all_labels_1 = np.unique(labels_1)
|
|
175
|
+
# all_labels_1 = all_labels_1[all_labels_1 > -1]
|
|
176
|
+
|
|
177
|
+
# features_all_1 = np.c_[
|
|
178
|
+
# np.median(x_1[labels_1 == all_labels_1[0]]),
|
|
179
|
+
# np.median(z_1[labels_1 == all_labels_1[0]]),
|
|
180
|
+
# np.median(amps_1[labels_1 == all_labels_1[0]]),
|
|
181
|
+
# ]
|
|
182
|
+
# for u in all_labels_1[1:]:
|
|
183
|
+
# features_all_1 = np.concatenate(
|
|
184
|
+
# (
|
|
185
|
+
# features_all_1,
|
|
186
|
+
# np.c_[
|
|
187
|
+
# np.median(x_1[labels_1 == u]),
|
|
188
|
+
# np.median(z_1[labels_1 == u]),
|
|
189
|
+
# np.median(amps_1[labels_1 == u]),
|
|
190
|
+
# ],
|
|
191
|
+
# )
|
|
192
|
+
# )
|
|
193
|
+
|
|
194
|
+
# distance_inter = (
|
|
195
|
+
# (features_all_1[:, :, None] - features_all_1.T[None]) ** 2
|
|
196
|
+
# ).sum(1)
|
|
197
|
+
|
|
198
|
+
labels_12 = np.concatenate((labels_1, labels_2))
|
|
199
|
+
_, labels_12[labels_12 > -1] = np.unique(
|
|
200
|
+
labels_12[labels_12 > -1], return_inverse=True
|
|
201
|
+
) # Make contiguous
|
|
202
|
+
idx_all = np.flatnonzero(
|
|
203
|
+
times_seconds < min_time_s + chunk_time_ranges_s[k + 1][1]
|
|
204
|
+
)
|
|
205
|
+
labels_all = -1 * np.ones(
|
|
206
|
+
times_seconds.shape[0]
|
|
207
|
+
) # discard all spikes at the end for now
|
|
208
|
+
labels_all[idx_all] = labels_12.astype("int")
|
|
209
|
+
|
|
210
|
+
return labels_all
|
|
211
|
+
|
|
212
|
+
|
|
213
|
+
def get_indices_in_chunk(times_s, chunk_time_range_s):
|
|
214
|
+
if chunk_time_range_s is None:
|
|
215
|
+
return slice(None)
|
|
216
|
+
|
|
217
|
+
return np.flatnonzero(
|
|
218
|
+
(times_s >= chunk_time_range_s[0]) & (times_s < chunk_time_range_s[1])
|
|
219
|
+
)
|