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 +1,357 @@
|
|
|
1
|
+
import matplotlib.pyplot as plt
|
|
2
|
+
from matplotlib.collections import LineCollection
|
|
3
|
+
from matplotlib.colors import to_rgba
|
|
4
|
+
from matplotlib.patches import Rectangle
|
|
5
|
+
import numpy as np
|
|
6
|
+
import torch
|
|
7
|
+
|
|
8
|
+
from .colors import glasbey1024
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def geomplot(
|
|
12
|
+
waveforms,
|
|
13
|
+
*,
|
|
14
|
+
max_channel=None,
|
|
15
|
+
max_channels=None,
|
|
16
|
+
channel_index=None,
|
|
17
|
+
channels=None,
|
|
18
|
+
geom=None,
|
|
19
|
+
ax=None,
|
|
20
|
+
z_extension=1.0,
|
|
21
|
+
x_extension=0.8,
|
|
22
|
+
show_zero=True,
|
|
23
|
+
show_trough=True,
|
|
24
|
+
trough_offset=42,
|
|
25
|
+
show_zero_kwargs=None,
|
|
26
|
+
max_abs_amp=None,
|
|
27
|
+
show_chan_label=False,
|
|
28
|
+
annotate_z=True,
|
|
29
|
+
chan_labels=None,
|
|
30
|
+
xlim_factor=1,
|
|
31
|
+
subar=False,
|
|
32
|
+
msbar=False,
|
|
33
|
+
bar_color="k",
|
|
34
|
+
bar_background="w",
|
|
35
|
+
zlim: str | None = "tight",
|
|
36
|
+
c=None,
|
|
37
|
+
color=None,
|
|
38
|
+
colors=None,
|
|
39
|
+
return_chans=False,
|
|
40
|
+
linestyles=None,
|
|
41
|
+
linewidths=None,
|
|
42
|
+
randomize=False,
|
|
43
|
+
random_seed=0,
|
|
44
|
+
**plot_kwargs,
|
|
45
|
+
):
|
|
46
|
+
"""Plot waveforms according to geometry using channel index"""
|
|
47
|
+
assert geom is not None
|
|
48
|
+
ax = ax or plt.gca()
|
|
49
|
+
|
|
50
|
+
# args to numpy if necessary
|
|
51
|
+
if torch.is_tensor(waveforms):
|
|
52
|
+
waveforms = waveforms.numpy(force=True)
|
|
53
|
+
if torch.is_tensor(max_channels):
|
|
54
|
+
max_channels = max_channels.numpy(force=True)
|
|
55
|
+
if torch.is_tensor(channels):
|
|
56
|
+
channels = channels.numpy(force=True)
|
|
57
|
+
if torch.is_tensor(geom):
|
|
58
|
+
geom = geom.numpy(force=True)
|
|
59
|
+
if torch.is_tensor(c):
|
|
60
|
+
c = c.numpy(force=True)
|
|
61
|
+
if max_channel is not None:
|
|
62
|
+
max_channels = np.array([max_channel])
|
|
63
|
+
max_channels = np.broadcast_to(max_channels, (len(waveforms),))
|
|
64
|
+
|
|
65
|
+
# randomize if asked to
|
|
66
|
+
if randomize:
|
|
67
|
+
rg = np.random.default_rng(random_seed)
|
|
68
|
+
o = rg.permutation(len(waveforms))
|
|
69
|
+
if waveforms is not None:
|
|
70
|
+
waveforms = waveforms[o]
|
|
71
|
+
if max_channels is not None:
|
|
72
|
+
max_channels = max_channels[o]
|
|
73
|
+
if channels is not None:
|
|
74
|
+
channels = channels[o]
|
|
75
|
+
if c is not None and hasattr(c, "__len__") and len(c) == len(o):
|
|
76
|
+
c = c[o]
|
|
77
|
+
if colors is not None and len(colors) == len(o):
|
|
78
|
+
colors = colors[o]
|
|
79
|
+
|
|
80
|
+
# -- validate shapes
|
|
81
|
+
if waveforms.ndim == 2:
|
|
82
|
+
waveforms = waveforms[None]
|
|
83
|
+
assert waveforms.ndim == 3
|
|
84
|
+
if c is not None and (hasattr(c, "__len__") and len(c) > 1):
|
|
85
|
+
assert len(c) == len(waveforms)
|
|
86
|
+
if channels is None:
|
|
87
|
+
if max_channels is None and channel_index is None:
|
|
88
|
+
max_channels = np.zeros(waveforms.shape[0], dtype=int)
|
|
89
|
+
channel_index = (
|
|
90
|
+
np.arange(geom.shape[0])[None, :]
|
|
91
|
+
* np.ones(geom.shape[0], dtype=int)[:, None]
|
|
92
|
+
)
|
|
93
|
+
max_channels = np.atleast_1d(max_channels)
|
|
94
|
+
n_channels, C = channel_index.shape
|
|
95
|
+
assert geom.shape == (n_channels, 2)
|
|
96
|
+
T = waveforms.shape[1]
|
|
97
|
+
if waveforms.shape != (*max_channels.shape, T, C):
|
|
98
|
+
raise ValueError(
|
|
99
|
+
f"Bad shapes: {waveforms.shape=}, {max_channels.shape=}, {C=}"
|
|
100
|
+
)
|
|
101
|
+
channels = channel_index[max_channels]
|
|
102
|
+
else:
|
|
103
|
+
n_channels = geom[np.isfinite(geom).all(1)].shape[0]
|
|
104
|
+
T = waveforms.shape[1]
|
|
105
|
+
assert channels.shape[0] == waveforms.shape[0]
|
|
106
|
+
assert channels.shape[1] == waveforms.shape[-1]
|
|
107
|
+
|
|
108
|
+
# -- figure out units for plotting
|
|
109
|
+
valid = np.isfinite(geom).all(1)
|
|
110
|
+
z_uniq, z_ix = np.unique(geom[valid, 1], return_inverse=True)
|
|
111
|
+
for i in z_ix:
|
|
112
|
+
x_uniq = np.unique(geom[valid][z_ix == i, 0])
|
|
113
|
+
if x_uniq.size > 1:
|
|
114
|
+
break
|
|
115
|
+
else:
|
|
116
|
+
x_uniq = np.unique(geom[valid, 0])
|
|
117
|
+
inter_chan_x = 1
|
|
118
|
+
if x_uniq.size > 1:
|
|
119
|
+
inter_chan_x = x_uniq[1] - x_uniq[0]
|
|
120
|
+
inter_chan_z = z_uniq[1] - z_uniq[0]
|
|
121
|
+
max_abs_amp = max_abs_amp or np.nanmax(np.abs(waveforms))
|
|
122
|
+
geom_scales = [
|
|
123
|
+
T / inter_chan_x / x_extension,
|
|
124
|
+
max_abs_amp / inter_chan_z / z_extension,
|
|
125
|
+
]
|
|
126
|
+
geom_plot = geom[valid] * geom_scales
|
|
127
|
+
t_domain = np.linspace(-T // 2, T // 2, num=T)
|
|
128
|
+
|
|
129
|
+
# -- and, plot
|
|
130
|
+
draw = []
|
|
131
|
+
draw_colors = []
|
|
132
|
+
unique_chans = set()
|
|
133
|
+
xmin, xmax = np.inf, -np.inf
|
|
134
|
+
if linestyles is not None:
|
|
135
|
+
ls = []
|
|
136
|
+
plot_kwargs["linestyles"] = ls
|
|
137
|
+
if linewidths is not None:
|
|
138
|
+
lw = []
|
|
139
|
+
plot_kwargs["linewidths"] = lw
|
|
140
|
+
for j, (wf, chans) in enumerate(zip(waveforms, channels)):
|
|
141
|
+
for i, cc in enumerate(chans):
|
|
142
|
+
if cc == n_channels:
|
|
143
|
+
continue
|
|
144
|
+
|
|
145
|
+
draw.append(np.c_[geom_plot[cc, 0] + t_domain, geom_plot[cc, 1] + wf[:, i]])
|
|
146
|
+
xmin = min(geom_plot[cc, 0] + t_domain.min(), xmin)
|
|
147
|
+
xmax = max(geom_plot[cc, 0] + t_domain.max(), xmax)
|
|
148
|
+
unique_chans.add(cc)
|
|
149
|
+
if colors is not None:
|
|
150
|
+
draw_colors.append(to_rgba(colors[j]))
|
|
151
|
+
elif color is not None:
|
|
152
|
+
draw_colors.append(to_rgba(color))
|
|
153
|
+
elif c is not None:
|
|
154
|
+
cj = c[j] if (hasattr(c, "__len__") and len(c) > 1) else c
|
|
155
|
+
draw_colors.append(to_rgba(cj))
|
|
156
|
+
if linestyles is not None:
|
|
157
|
+
ls.append(linestyles[j])
|
|
158
|
+
if linewidths is not None:
|
|
159
|
+
lw.append(linewidths[j])
|
|
160
|
+
dx = xmax - xmin
|
|
161
|
+
xpad = dx / 2 - xlim_factor * dx / 2
|
|
162
|
+
ax.set_xlim([xmin + xpad, xmax - xpad])
|
|
163
|
+
|
|
164
|
+
ann_offset = np.array([0, 0.33 * inter_chan_z]) * geom_scales
|
|
165
|
+
chan_labels = (
|
|
166
|
+
chan_labels if chan_labels is not None else list(map(str, range(len(geom))))
|
|
167
|
+
)
|
|
168
|
+
for c in unique_chans:
|
|
169
|
+
if show_zero_kwargs is None:
|
|
170
|
+
show_zero_kwargs = dict(color="gray", lw=0.8, linestyle="--")
|
|
171
|
+
if show_zero:
|
|
172
|
+
ax.axhline(geom_plot[c, 1], **show_zero_kwargs)
|
|
173
|
+
if show_chan_label:
|
|
174
|
+
ax.annotate(chan_labels[c], geom_plot[c] + ann_offset, size=6, color="gray")
|
|
175
|
+
if show_trough:
|
|
176
|
+
ax.axvline(geom_plot[c, 0] + t_domain[trough_offset], **show_zero_kwargs)
|
|
177
|
+
lines = LineCollection(
|
|
178
|
+
np.array(draw),
|
|
179
|
+
colors=np.array(draw_colors) if draw_colors else None,
|
|
180
|
+
**plot_kwargs,
|
|
181
|
+
)
|
|
182
|
+
lines = ax.add_collection(lines)
|
|
183
|
+
if annotate_z:
|
|
184
|
+
unique_z = np.unique(geom[:, 1][list(unique_chans)])
|
|
185
|
+
unique_zp = np.unique(geom_plot[:, 1][list(unique_chans)])
|
|
186
|
+
for z, zp in zip(unique_z, unique_zp):
|
|
187
|
+
ax.text(
|
|
188
|
+
xmin,
|
|
189
|
+
zp,
|
|
190
|
+
f"{z:f}".rstrip("0").rstrip("."),
|
|
191
|
+
size=6,
|
|
192
|
+
color="gray",
|
|
193
|
+
clip_on=True,
|
|
194
|
+
)
|
|
195
|
+
|
|
196
|
+
if subar:
|
|
197
|
+
if isinstance(subar, bool):
|
|
198
|
+
# auto su if True, but you can pass int/float too.
|
|
199
|
+
subars = (1, 2, 5, 10, 20, 30, 50)
|
|
200
|
+
for j in range(len(subars)):
|
|
201
|
+
if subars[j] > 1.2 * max_abs_amp:
|
|
202
|
+
break
|
|
203
|
+
subar = subars[max(0, j - 1)]
|
|
204
|
+
min_z = min(geom_plot[c, 1] for c in unique_chans)
|
|
205
|
+
if msbar:
|
|
206
|
+
min_z += max_abs_amp
|
|
207
|
+
if bar_background:
|
|
208
|
+
ax.add_patch(
|
|
209
|
+
Rectangle(
|
|
210
|
+
[
|
|
211
|
+
xmax - T // 4 - 2,
|
|
212
|
+
min_z - max_abs_amp / 2 - subar / 10,
|
|
213
|
+
],
|
|
214
|
+
4 + 7 + 2 + T // 8,
|
|
215
|
+
subar + subar / 5,
|
|
216
|
+
fc=bar_background,
|
|
217
|
+
zorder=11,
|
|
218
|
+
alpha=0.8,
|
|
219
|
+
)
|
|
220
|
+
)
|
|
221
|
+
ax.add_patch(
|
|
222
|
+
Rectangle(
|
|
223
|
+
[
|
|
224
|
+
xmax - T // 4,
|
|
225
|
+
min_z - max_abs_amp / 2,
|
|
226
|
+
],
|
|
227
|
+
4,
|
|
228
|
+
subar,
|
|
229
|
+
fc=bar_color,
|
|
230
|
+
zorder=12,
|
|
231
|
+
)
|
|
232
|
+
)
|
|
233
|
+
ax.text(
|
|
234
|
+
xmax - T // 4 + 5,
|
|
235
|
+
min_z - max_abs_amp / 2 + subar / 2,
|
|
236
|
+
f"{subar} s.u.",
|
|
237
|
+
transform=ax.transData,
|
|
238
|
+
fontsize=5,
|
|
239
|
+
ha="left",
|
|
240
|
+
va="center",
|
|
241
|
+
rotation=-90,
|
|
242
|
+
color=bar_color,
|
|
243
|
+
zorder=12,
|
|
244
|
+
)
|
|
245
|
+
|
|
246
|
+
if msbar:
|
|
247
|
+
min_z = min(geom_plot[c, 1] for c in unique_chans)
|
|
248
|
+
ax.plot(
|
|
249
|
+
[
|
|
250
|
+
geom_plot[:, 0].max() - 30,
|
|
251
|
+
geom_plot[:, 0].max(),
|
|
252
|
+
],
|
|
253
|
+
2 * [min_z - max_abs_amp],
|
|
254
|
+
color=bar_color,
|
|
255
|
+
lw=2,
|
|
256
|
+
zorder=890,
|
|
257
|
+
)
|
|
258
|
+
ax.text(
|
|
259
|
+
geom_plot[:, 0].max() - 15,
|
|
260
|
+
min_z - max_abs_amp + max_abs_amp / 10,
|
|
261
|
+
"1ms",
|
|
262
|
+
transform=ax.transData,
|
|
263
|
+
fontsize=5,
|
|
264
|
+
ha="center",
|
|
265
|
+
va="bottom",
|
|
266
|
+
color=bar_color,
|
|
267
|
+
)
|
|
268
|
+
|
|
269
|
+
if zlim is None:
|
|
270
|
+
ax.autoscale_view()
|
|
271
|
+
elif zlim == "auto":
|
|
272
|
+
min_z = min(geom_plot[c, 1] for c in unique_chans)
|
|
273
|
+
max_z = max(geom_plot[c, 1] for c in unique_chans)
|
|
274
|
+
if np.isfinite([min_z, max_z]).all():
|
|
275
|
+
ax.set_ylim([min_z - 2 * max_abs_amp, max_z + 2 * max_abs_amp])
|
|
276
|
+
elif zlim == "tight":
|
|
277
|
+
min_z = min(geom_plot[c, 1] for c in unique_chans)
|
|
278
|
+
max_z = max(geom_plot[c, 1] for c in unique_chans)
|
|
279
|
+
if np.isfinite([min_z, max_z]).all():
|
|
280
|
+
ax.set_ylim([min_z - max_abs_amp, max_z + max_abs_amp])
|
|
281
|
+
elif isinstance(zlim, float):
|
|
282
|
+
min_z = min(geom_plot[c, 1] for c in unique_chans)
|
|
283
|
+
max_z = max(geom_plot[c, 1] for c in unique_chans)
|
|
284
|
+
if np.isfinite([min_z, max_z]).all():
|
|
285
|
+
ax.set_ylim([min_z - max_abs_amp * zlim, max_z + max_abs_amp * zlim])
|
|
286
|
+
elif zlim is False:
|
|
287
|
+
pass
|
|
288
|
+
|
|
289
|
+
if return_chans:
|
|
290
|
+
return lines, unique_chans
|
|
291
|
+
|
|
292
|
+
return lines
|
|
293
|
+
|
|
294
|
+
|
|
295
|
+
def geomplot_templates(
|
|
296
|
+
axis,
|
|
297
|
+
unit_ids,
|
|
298
|
+
unit_templates,
|
|
299
|
+
channel_index,
|
|
300
|
+
registered_geom,
|
|
301
|
+
title="",
|
|
302
|
+
main_channel=None,
|
|
303
|
+
linestyles=None,
|
|
304
|
+
legend_loc="best",
|
|
305
|
+
color_reroll_seed=None,
|
|
306
|
+
color_flat=False,
|
|
307
|
+
):
|
|
308
|
+
unit_ids = np.asarray(unit_ids)
|
|
309
|
+
carr = np.asarray(glasbey1024)
|
|
310
|
+
if color_reroll_seed is not None:
|
|
311
|
+
rg = np.random.default_rng(color_reroll_seed)
|
|
312
|
+
carr = carr[rg.permutation(len(carr))]
|
|
313
|
+
if color_flat:
|
|
314
|
+
colors = carr[np.arange(len(unit_ids))]
|
|
315
|
+
else:
|
|
316
|
+
colors = carr[unit_ids % len(glasbey1024)]
|
|
317
|
+
if main_channel is None:
|
|
318
|
+
chan = np.ptp(unit_templates[0], 0).argmax()
|
|
319
|
+
else:
|
|
320
|
+
chan = main_channel
|
|
321
|
+
channels = channel_index[chan]
|
|
322
|
+
unit_templates = np.pad(
|
|
323
|
+
unit_templates,
|
|
324
|
+
[(0, 0), (0, 0), (0, 1)],
|
|
325
|
+
constant_values=np.nan,
|
|
326
|
+
)
|
|
327
|
+
unit_templates = unit_templates[:, :, channels]
|
|
328
|
+
maxamp = np.nanmax(np.abs(unit_templates))
|
|
329
|
+
|
|
330
|
+
if linestyles is None:
|
|
331
|
+
linestyles = '-' * len(unit_ids)
|
|
332
|
+
|
|
333
|
+
labels = []
|
|
334
|
+
handles = []
|
|
335
|
+
for uid, color, template, ls in reversed(list(zip(unit_ids, colors, unit_templates, linestyles))):
|
|
336
|
+
lines = geomplot(
|
|
337
|
+
template[None],
|
|
338
|
+
max_channels=[chan],
|
|
339
|
+
channel_index=channel_index,
|
|
340
|
+
geom=registered_geom,
|
|
341
|
+
ax=axis,
|
|
342
|
+
show_zero=False,
|
|
343
|
+
max_abs_amp=maxamp,
|
|
344
|
+
subar=True,
|
|
345
|
+
bar_color="k",
|
|
346
|
+
bar_background="w",
|
|
347
|
+
zlim="tight",
|
|
348
|
+
color=color,
|
|
349
|
+
linestyle=ls,
|
|
350
|
+
)
|
|
351
|
+
labels.append(str(uid))
|
|
352
|
+
handles.append(lines)
|
|
353
|
+
axis.legend(handles=handles, labels=labels, fancybox=False, loc=legend_loc)
|
|
354
|
+
axis.set_xticks([])
|
|
355
|
+
axis.set_yticks([])
|
|
356
|
+
if title:
|
|
357
|
+
axis.set_title(title)
|
|
@@ -0,0 +1,93 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: DARTsort
|
|
3
|
+
Version: 0.3.5
|
|
4
|
+
Summary: DARTsort
|
|
5
|
+
Author-email: Charlie Windolf <ciw2107@columbia.edu>
|
|
6
|
+
Project-URL: Homepage, https://github.com/cwindolf/dartsort
|
|
7
|
+
Project-URL: Bug Tracker, https://github.com/cwindolf/dartsort/issues
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
10
|
+
Classifier: Operating System :: OS Independent
|
|
11
|
+
Requires-Python: >=3.11
|
|
12
|
+
Description-Content-Type: text/markdown
|
|
13
|
+
Requires-Dist: cupy
|
|
14
|
+
Requires-Dist: h5py
|
|
15
|
+
Requires-Dist: linear_operator
|
|
16
|
+
Requires-Dist: numba
|
|
17
|
+
Requires-Dist: numpy>=1.20; python_version < "3.13"
|
|
18
|
+
Requires-Dist: numpy>=2.0.0; python_version >= "3.13"
|
|
19
|
+
Requires-Dist: opt-einsum
|
|
20
|
+
Requires-Dist: pandas
|
|
21
|
+
Requires-Dist: packaging
|
|
22
|
+
Requires-Dist: probeinterface
|
|
23
|
+
Requires-Dist: pydantic
|
|
24
|
+
Requires-Dist: scipy>=1.13
|
|
25
|
+
Requires-Dist: scikit-learn
|
|
26
|
+
Requires-Dist: spikeinterface>=0.101.2
|
|
27
|
+
Requires-Dist: torch>=2.0
|
|
28
|
+
Requires-Dist: tqdm
|
|
29
|
+
Provides-Extra: vis
|
|
30
|
+
Requires-Dist: matplotlib; extra == "vis"
|
|
31
|
+
Requires-Dist: seaborn; extra == "vis"
|
|
32
|
+
Provides-Extra: dev
|
|
33
|
+
Requires-Dist: pytest; extra == "dev"
|
|
34
|
+
Requires-Dist: pytest-cov; extra == "dev"
|
|
35
|
+
Provides-Extra: full
|
|
36
|
+
Requires-Dist: matplotlib; extra == "full"
|
|
37
|
+
Requires-Dist: seaborn; extra == "full"
|
|
38
|
+
Requires-Dist: pytest; extra == "full"
|
|
39
|
+
Requires-Dist: pytest-cov; extra == "full"
|
|
40
|
+
Requires-Dist: ipywidgets; extra == "full"
|
|
41
|
+
Requires-Dist: ipykernel; extra == "full"
|
|
42
|
+
Requires-Dist: black; extra == "full"
|
|
43
|
+
|
|
44
|
+
[](https://github.com/cwindolf/dartsort/actions/)
|
|
45
|
+
[](https://coveralls.io/github/cwindolf/dartsort)
|
|
46
|
+
|
|
47
|
+
# dartsort
|
|
48
|
+
|
|
49
|
+
## :warning: Work in progress code repository
|
|
50
|
+
|
|
51
|
+
We do not currently recommend DARTsort for production spike sorting purposes. We are in the process of implementing a robust and documented pipeline in [`src/dartsort`](src/dartsort), and we will update this page accordingly.
|
|
52
|
+
|
|
53
|
+
A workflow described in our preprint (https://www.biorxiv.org/content/10.1101/2023.08.11.553023v1) is in [uhd_pipeline.py](scripts/uhd_pipeline.py), which is implemented using the legacy code in [`src/spike_psvae`](src/spike_psvae).
|
|
54
|
+
|
|
55
|
+
|
|
56
|
+
## Suggested install steps
|
|
57
|
+
|
|
58
|
+
If you don't already have Python and PyTorch 2 installed, we recommend doing this with the Miniforge distribution of `conda`. You can find info and installers for your platform [at Miniforge's GitHub repository](https://github.com/conda-forge/miniforge). After installing Miniforge, `conda` will be available on your computer for installing Python packages, as well as the newer and faster conda replacement tool `mamba`. We recommend using `mamba` instead of `conda` below, since the installation tends to be a lot faster with `mamba`.
|
|
59
|
+
|
|
60
|
+
To install DARTsort, first clone this GitHub repository.
|
|
61
|
+
|
|
62
|
+
After cloning the repository, create and activate the `mamba`/`conda` environment from the configuration file provided as follows:
|
|
63
|
+
|
|
64
|
+
```bash
|
|
65
|
+
$ mamba env create -f environment.yml
|
|
66
|
+
$ mamba activate dartsort
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
Next, visit https://pytorch.org/get-started/locally/ and follow the `PyTorch` install instructions for your specific OS and hardware needs.
|
|
70
|
+
We also need to install `linear_operator` from the `gpytorch` channel.
|
|
71
|
+
For example, on a Linux workstation or cluster with NVIDIA GPUs available, one might use (dropping in `mamba` for `conda` commands):
|
|
72
|
+
|
|
73
|
+
```bash
|
|
74
|
+
# Example -- see https://pytorch.org/get-started/locally/ to find your platform's command.
|
|
75
|
+
(dartsort) $ mamba install pytorch torchvision torchaudio pytorch-cuda=11.8 linear_operator -c pytorch -c nvidia -c gpytorch
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
Finally, install the remaining `pip` dependencies and `dartsort` itself:
|
|
79
|
+
|
|
80
|
+
```bash
|
|
81
|
+
(dartsort) $ pip install -r requirements-full.txt
|
|
82
|
+
(dartsort) $ pip install -e .
|
|
83
|
+
```
|
|
84
|
+
|
|
85
|
+
To enable DARTsort's default motion correction algorithm [DREDge](https://www.biorxiv.org/content/10.1101/2023.10.24.563768), clone [its GitHub repository](https://github.com/evarol/dredge), and then `cd dredge/` and install the DREDge package with `pip install -e .`.
|
|
86
|
+
|
|
87
|
+
Soon we will have a package on PyPI so that these last steps will be just a `pip install dartsort`.
|
|
88
|
+
|
|
89
|
+
To make sure everything is working:
|
|
90
|
+
|
|
91
|
+
```bash
|
|
92
|
+
$ (dartsort) pytest tests/*
|
|
93
|
+
```
|
|
@@ -0,0 +1,125 @@
|
|
|
1
|
+
dartsort/__init__.py,sha256=YX92dyjRtWw1Ij1UDrUONwsAmpuB9oGYhSFOuh3ToE4,1689
|
|
2
|
+
dartsort/cli.py,sha256=s9lhxid6O9lkrH6q_YHqWmyGNU2P5JeQK-Ezwb2AyEo,3328
|
|
3
|
+
dartsort/config.py,sha256=nsEul1fqCBp7zg6tPiV3Ke7i9JhEyUu77eF5-dPLIv4,11206
|
|
4
|
+
dartsort/main.py,sha256=kIAwH5-opusITxGEDPNJBH1H3Nowo5nl3UdcJiaJ_u8,22867
|
|
5
|
+
dartsort/clustering/__init__.py,sha256=kAeBigizIDS9_Sc8ctDzIzOUMjA8z2I6A-kdLb3zias,250
|
|
6
|
+
dartsort/clustering/cluster_util.py,sha256=rWBq25zRF--yY8VcpXRPmZqaDpt_pkB9ILWUNhAYpr0,12980
|
|
7
|
+
dartsort/clustering/clustering.py,sha256=eI8jbuCttppjHZkM0xyqaJo3uM4NZkN5EQv96SdmAlA,25308
|
|
8
|
+
dartsort/clustering/clustering_features.py,sha256=eQA-HY6EeL7iVd_Zcn9fcbsxwD6fGUQDFslAt5cY4_s,6806
|
|
9
|
+
dartsort/clustering/density.py,sha256=sA-bfaXQmZ_XaKLm2imY8gV9yoE72BuksglOjIS8vPA,43039
|
|
10
|
+
dartsort/clustering/forward_backward.py,sha256=oDocF8sx8y6xZ5p_JNJ7NYXIRR-FJUGL4wGMT4Y7dlE,8609
|
|
11
|
+
dartsort/clustering/kmeans.py,sha256=ucOlwdS_Xbr7l8WVxbNZrX8V43J_6VkGByR8bt1mEkI,14204
|
|
12
|
+
dartsort/clustering/merge.py,sha256=v06GfJt3N-jJKPHYmaRglOzq51Kc1t55WW570ujLsAM,17774
|
|
13
|
+
dartsort/clustering/modes.py,sha256=RP8CrO_ZQEp--gp4_M7VvObOzw9Z9OG5j6O7Jy2X-Uc,7396
|
|
14
|
+
dartsort/clustering/refine_util.py,sha256=RI-NgyvmV_wzrxVznSd6abcAUjgkO8Hm2PTgcZ80kfM,6625
|
|
15
|
+
dartsort/clustering/relocate.py,sha256=uw0M82VyJcNF-AIhx2lfeVMd3YHG5AAEaX-34QD8v0w,3407
|
|
16
|
+
dartsort/clustering/split.py,sha256=U-h1QxSpvooMhe-q9Wu10lyQ9wOqw0RvsY2VMfjO7DQ,50767
|
|
17
|
+
dartsort/clustering/gmm/mixture.py,sha256=MF4a9dvrrV5gdAdbZNzjOH2WuCw5g91SVzhZZWmm-14,210561
|
|
18
|
+
dartsort/clustering/gmm/stable_features.py,sha256=Iu53H5av342pmC3df1vSXY8cvKnQXpYgE8BzPQR7-2I,38123
|
|
19
|
+
dartsort/detect/__init__.py,sha256=gVobIkjrOxISrCCUIxZw0nZ2rpX_NwwruguW0d35IOU,132
|
|
20
|
+
dartsort/detect/detect.py,sha256=bEY7grhtBVihQcXvaPx9nqmekhE2l0EgMoYjCVVYdlA,14933
|
|
21
|
+
dartsort/detect/detect_filters.py,sha256=oHQDmCUqtkYsvePt0sAbDVQJOS5295ORBA6TozS6zGc,1143
|
|
22
|
+
dartsort/evaluate/__init__.py,sha256=tOfT8u3YqWghkKlpbrvCqPH9yX633Sg7ZhrysXAEQEY,37
|
|
23
|
+
dartsort/evaluate/analysis.py,sha256=h8VwOIU0aSoOiBKa0E8q-Q5xJdU2BpgkE87lHnHUIco,21778
|
|
24
|
+
dartsort/evaluate/comparison.py,sha256=MMoSRySr0zmnswbw1GzsG6H2q-cooXOjzXDBXvsCqZY,20268
|
|
25
|
+
dartsort/evaluate/hybrid_util.py,sha256=mEHOZTagRP20gpDrSv113XoHDB6TDuY_RAYiEbAAHkI,19713
|
|
26
|
+
dartsort/evaluate/noise_recording_tools.py,sha256=B94uAANguyDh-4xZOAFr9xbiX7irrU2MQR6_aDPLmlg,6588
|
|
27
|
+
dartsort/evaluate/sim_template_tools.py,sha256=-R6qA8rOkY5XB6mbcNjxWOC_4UNVzZqxU_jBUq9kSe4,28400
|
|
28
|
+
dartsort/evaluate/simkit.py,sha256=8FuwsdxIKx-ol8XR_7QVK7BiLFDAJFr_IDcT065FiQY,31716
|
|
29
|
+
dartsort/evaluate/simlib.py,sha256=q2d1Cn4oKU872FTkb-Tg9Qrk42r6z32Tw2_fiJdb9ig,8894
|
|
30
|
+
dartsort/localize/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
31
|
+
dartsort/localize/localize_torch.py,sha256=sFFoq7kfuwneBDK_1jIbK-oCfWijmcSjfmxeFojRBM8,10588
|
|
32
|
+
dartsort/localize/localize_util.py,sha256=THpFFSn4veNXQ3iH9ZRnLhAc_KPuNhNX5Q2-fZ-ioLc,9602
|
|
33
|
+
dartsort/peel/__init__.py,sha256=0ABV1LjM7m9oLku-ProBagWu9OtIhfuGd3xQWkRcW54,281
|
|
34
|
+
dartsort/peel/grab.py,sha256=i-z-Hv_XMHsdcxrWYKg9tVMvc1R9GpG8qDwcMWHo6KI,7054
|
|
35
|
+
dartsort/peel/matching.py,sha256=RLqbZ5WPBUC_MKkkGhX6DgRpgcwTJmXzPPSmF5nHiSs,24441
|
|
36
|
+
dartsort/peel/peel_base.py,sha256=cV4kvofZAKun1joI5Kb9Yr_UsAVZ6xqeWFZy1Uv-Faw,37889
|
|
37
|
+
dartsort/peel/running_template.py,sha256=D5vaUJ0fwGsi4u8N0JOOVdYmRIj4gRxHXTXs7BQ0tlw,53441
|
|
38
|
+
dartsort/peel/subtract.py,sha256=Jgmi5xoO2ofM9HAVkPk6TmxSMUvSkVAVy_-msFwPC4k,44445
|
|
39
|
+
dartsort/peel/threshold.py,sha256=YPUrBoQzzlwJRDz2sO-BrjfoCRqPqbI-BC1lq5Q_cXQ,17214
|
|
40
|
+
dartsort/peel/universal.py,sha256=UjVpsHYIAEF_HK7Uem4DLpZnWZm1kjQ9-C1Ddg8Xgu4,7866
|
|
41
|
+
dartsort/peel/matching_util/__init__.py,sha256=_8HjNRDgEEqMra43JFw-k_fRtfjwJXSRjzwCZoQ0wB8,87
|
|
42
|
+
dartsort/peel/matching_util/compressed_upsampled.py,sha256=ZulnsizaBp1q05M8lfuTaNQYvhAGEwaGRlWmlMOdNig,28898
|
|
43
|
+
dartsort/peel/matching_util/drifty.py,sha256=UEQEOmDcj_OEc4U4--OLjpmI5Pr7lzk0u1UXWZL7i9c,28271
|
|
44
|
+
dartsort/peel/matching_util/matching_base.py,sha256=upeoS8gkR630-CvzFDH_KirI_gJTey4EewjiF5VlLAI,19224
|
|
45
|
+
dartsort/peel/matching_util/pairwise.py,sha256=ou0bJIRKcW6l3Ywpwack6RXMk0x3MyBGlZp43Gr-sFQ,14115
|
|
46
|
+
dartsort/peel/matching_util/pairwise_util.py,sha256=mlKx_UGNNB2F99gkyXa7YtUAai96EeLhw_UwdBQEGJc,47677
|
|
47
|
+
dartsort/pretrained/default_temporal_kernel.npy,sha256=ofu2YIyXzkG8P3X0DqVDUhUSURuvBVUFjgaNRtgoKDU,380
|
|
48
|
+
dartsort/pretrained/detect_np1.pt,sha256=2D3wMm0jOgFleqdnbM_ODhLm85O5mDthERG2poCuqSo,10125
|
|
49
|
+
dartsort/pretrained/detect_np2.pt,sha256=eK2iGc4GP-VMB_htI14vJuzw_XxCH1JipPXTi807ADI,10253
|
|
50
|
+
dartsort/pretrained/glasbey1024.npz,sha256=MY3mfqOulwn7JcCMh72W7GeHkjbb09z0QwTSeH8HF5E,7117
|
|
51
|
+
dartsort/pretrained/offset_trained_denoiser.pt,sha256=oCPRpeTaiH5RtzUWxHBXiYWSMRs-oVAA7Id-KGVVv1k,422807
|
|
52
|
+
dartsort/pretrained/offset_trained_denoiser_added_temp.pt,sha256=dnU0H3ySGf-ME2ox7-kl_g5AU0PH1O190j0addYGCT0,422807
|
|
53
|
+
dartsort/pretrained/offset_trained_denoiser_added_temp_boost.pt,sha256=esUDfRv_iN3rzsyaEHNz5nPjjxCSAyV2cAHK6aAmLEY,422807
|
|
54
|
+
dartsort/pretrained/original_single_chan_denoiser.pt,sha256=299yPKVMgS183UMYB8uSOQ_3IHTK50gnHAS34fWlWGk,425063
|
|
55
|
+
dartsort/pretrained/single_chan_denoiser.pt,sha256=esUDfRv_iN3rzsyaEHNz5nPjjxCSAyV2cAHK6aAmLEY,422807
|
|
56
|
+
dartsort/templates/__init__.py,sha256=nQCw-Yv_jffxPSceL6IT2IfVvFZyxGPP68kljL_7iN8,404
|
|
57
|
+
dartsort/templates/get_templates.py,sha256=gjMfSqVgisgTHAdFKJxMob7TWuLaPCFNm430Ui-ms28,25728
|
|
58
|
+
dartsort/templates/postprocess_util.py,sha256=DBN2ngw3e8EqqpG9FpH_s5CvtPym4PypQIqfrdHUZ9A,19702
|
|
59
|
+
dartsort/templates/realignment.py,sha256=Dc3SrOQ2hJiXQVCBjRUQwmMm6o_ylyMmNWk3CWic3G0,15743
|
|
60
|
+
dartsort/templates/superres_util.py,sha256=2elGbzNNydW2evyrZ2oyBtk3FTJbP4aEjDWQuQumKz8,6842
|
|
61
|
+
dartsort/templates/template_util.py,sha256=oo2XRX9i6ws_eybfxUlxno9LCNOzoUl9iJKCdFUIN50,19051
|
|
62
|
+
dartsort/templates/templates.py,sha256=xiqpsAZspW4plyYhpWe_I1YU44Iz-33Xz3Dgtavx0dQ,18434
|
|
63
|
+
dartsort/transform/__init__.py,sha256=Iz-ZSisELqlyv3mEM-cp2o60OxCVORv0KbsIPiQ5kSU,71
|
|
64
|
+
dartsort/transform/_multichan_denoiser_kit.py,sha256=cY4v7ERYk5IJrlJ2ajEHinJ4vRwTeqnRlmFs1S088wA,19791
|
|
65
|
+
dartsort/transform/all_transformers.py,sha256=SGriOBMISjvXHTNgNJ66Q4Z1anwsX23lCnlQ2Xnujks,1612
|
|
66
|
+
dartsort/transform/amortized_localization.py,sha256=2I_iFGcFdq_Ps5BMc7Fvl_jE2Ft90ZcTEbffFho3zWw,20117
|
|
67
|
+
dartsort/transform/amplitudes.py,sha256=xN1yg7uIKDooCj_95N9YMhj5aZO-0mE4hSZHcfxdUpg,6664
|
|
68
|
+
dartsort/transform/decollider.py,sha256=8S6x_-2DvsMTvHeGlYPo5czyH63wodSWXM9fObh9vys,23607
|
|
69
|
+
dartsort/transform/enforce_decrease.py,sha256=z5A9yYMSpvcUKOXzp9_QtEgFzsU4hCA8sGdRDfvoTOE,5862
|
|
70
|
+
dartsort/transform/localize.py,sha256=Fr5mraWJ68IAzoDnB6P9I53IDOREiS1nnWoqd_0qYDY,2798
|
|
71
|
+
dartsort/transform/matching_denoiser.py,sha256=fNREFUx578Rm_XcUuarXitc6Zy-VcEHTx06lQt2hqoE,1793
|
|
72
|
+
dartsort/transform/pipeline.py,sha256=Xh7d5cKD-hXM5zVqA9NQvnRaVG44Rm9o6SCyD72zmFU,14108
|
|
73
|
+
dartsort/transform/single_channel_denoiser.py,sha256=pknEM8Gwi81twHtD5aVImDOPcgth02MVwIM4tIF2-jQ,4735
|
|
74
|
+
dartsort/transform/single_channel_templates.py,sha256=tNH91SUB8IDs_-zvf1vn3BJJ45GIUUI8BlAFR0oTYpY,3636
|
|
75
|
+
dartsort/transform/supervised_denoiser.py,sha256=MFJaGtEvglsre2i6zFPQUWb2VYnp8HKaBHj5rlsYBUQ,19048
|
|
76
|
+
dartsort/transform/temporal_pca.py,sha256=9FNqCGYmHYLu3m70Qo1UDQNIqRPNbOpnspkbCY-Fx-8,14599
|
|
77
|
+
dartsort/transform/transform_base.py,sha256=iKEKY6NxHG7Gjeq2ZrYyxNj_4_9Cnfuc6yD6xHemtfs,7961
|
|
78
|
+
dartsort/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
79
|
+
dartsort/util/cli_util.py,sha256=L5OyiutwMSwo-qFKZeziQgTbkXDTeMt2E00GBKyt7PU,5745
|
|
80
|
+
dartsort/util/data_util.py,sha256=VxYoBI25d6VOingdjnQzCDh90VNJFqxgVjA04g7sETw,41294
|
|
81
|
+
dartsort/util/drift_util.py,sha256=xdLI4MQ2jQGET9thwmz0uwh_E_MCE7-5CdEMyT_PCko,37442
|
|
82
|
+
dartsort/util/internal_config.py,sha256=F5nZkDhvtmDMQZ1T9CgzSRvngmLgiQXE9oNkZitM6n0,38672
|
|
83
|
+
dartsort/util/interpolation_util.py,sha256=Az0wj8MLhIm9m66KZ4wbdQ9_URH8dpXtAJVNWp47KHg,34870
|
|
84
|
+
dartsort/util/job_util.py,sha256=8UdFmgbsm2l_1LML66cgKokPPrV4hLSOiDCHOCH-YNE,551
|
|
85
|
+
dartsort/util/logging_util.py,sha256=xN42UeH8FNDEGaXm0ttsl_-24nXvxgwmbBpXdu8CF6E,2539
|
|
86
|
+
dartsort/util/main_util.py,sha256=LX1991r5g2O5mB9HAa72vJatTLCHMUqrmiYtkhvsrN8,8274
|
|
87
|
+
dartsort/util/more_operators.py,sha256=A1y5JyLqgn8VedPh6Dq35NHvMdCWdDZes6rnCrPzDNo,9609
|
|
88
|
+
dartsort/util/multiprocessing_util.py,sha256=fN34C-xwltm080OJGOgU646iAsX-B6B9xw90hxiMkXg,5834
|
|
89
|
+
dartsort/util/nn_util.py,sha256=zulJrLzASm7XBgerQ0FNkVKpzrS5L41_SpRz-y5NiTM,14118
|
|
90
|
+
dartsort/util/noise_util.py,sha256=ZC9swbl_pXRR8kGiwuwBQ-2qMQfgN1phzmf3Yptf7EM,56081
|
|
91
|
+
dartsort/util/peel_util.py,sha256=oHLgAb5Vc1GWmHZkAbRRXenLwHafvKcSFrdpjgP8k4Q,6968
|
|
92
|
+
dartsort/util/py_util.py,sha256=mNVbTJV5FZ7Bc2s_37Jmg8IgYCuqbdfH4zFy_NrN5YE,5759
|
|
93
|
+
dartsort/util/registration_util.py,sha256=FXM3UsuJqKrrIBKYX84RZa__2SgVsUAoB2QbQ1zNWcg,3834
|
|
94
|
+
dartsort/util/residual_util.py,sha256=pH6gLN0g8KhdQftr6tiQRvhP8JdHbmbGGWVzrh1hUNk,1056
|
|
95
|
+
dartsort/util/sparse_util.py,sha256=Bx86kz-oOCbuHmc-Y7nDLbvgMudWAl8YSWwEd19_I-o,2269
|
|
96
|
+
dartsort/util/spikeio.py,sha256=JTPNIdVps0W13862aSZAPEt0kDpSvpGA6VPnhX3Xayg,7226
|
|
97
|
+
dartsort/util/spiketorch.py,sha256=FdaPCR4S3oGN2H8nIj_S9p5ANE4Mwoqa9JRXhlIwkx4,35608
|
|
98
|
+
dartsort/util/torch_optimization_util.py,sha256=rEcYU5pgCbWElVitJHMaF2oF_vK_xz0EsPCe84jvXa0,5396
|
|
99
|
+
dartsort/util/torch_util.py,sha256=Y07fh8EFToG0BV0y0qe_akuu1ZFWY_g_RhdleiU4sP0,2262
|
|
100
|
+
dartsort/util/universal_util.py,sha256=f9Gayib81ZN9Kp0A3odxa6hX5hF_sD6a8bEX_8Ejw-k,8797
|
|
101
|
+
dartsort/util/waveform_util.py,sha256=8n3w-q7vQyk0WuBozjX9HmDRmP4vAbzqzl5yT6t50mg,26766
|
|
102
|
+
dartsort/util/testing_util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
103
|
+
dartsort/util/testing_util/matching_debug_util.py,sha256=9dbPKZDox9wQHjrswkyAXn-PorXsYLKkbE_esyzDNlI,18048
|
|
104
|
+
dartsort/util/testing_util/mixture_testing_util.py,sha256=Q68_XK25HxDxYpjaWH7OZPrSfPttgQH01d7Sh6Va56c,9264
|
|
105
|
+
dartsort/vis/__init__.py,sha256=iTGP0Li6pt9-8qydmKgCKU0oKIaTkeKPbUi7GA93BaI,487
|
|
106
|
+
dartsort/vis/analysis_plots.py,sha256=yXbJIDT4T-vjHjumoLDUz8TeI7571Hlpw_nLj0VrDj8,11976
|
|
107
|
+
dartsort/vis/colors.py,sha256=BNZ7WcKYqpepz1rAPoC97JG3HXgzqnbJheHCFy5NuWQ,988
|
|
108
|
+
dartsort/vis/gt.py,sha256=DmJNWhCMf5FX-dBRb52UqwjG8mvjAIb-bLQ4T9pxAuE,12236
|
|
109
|
+
dartsort/vis/layout.py,sha256=1_EXeGBzdtYwSIyGt6UyB_evRBO8deqiwhJpMyy2HGw,4800
|
|
110
|
+
dartsort/vis/metrics_util.py,sha256=uasBbHyguZuWIl-_oLPFLxbDWbrVtQtkQSn6nG-5n0E,700
|
|
111
|
+
dartsort/vis/mixture.py,sha256=fnvwDdjMwM8LJYOM70wdfcfwg5b76HVWKiM6sh31N8c,49732
|
|
112
|
+
dartsort/vis/over_time.py,sha256=LHteYiflOWy1VOQ8qJkIHwRTUkYSh8y1DrrRhCQUeUA,16257
|
|
113
|
+
dartsort/vis/recanim.py,sha256=V6E9M34A25wxczHHT6z4POT7fJoGmD2Kdq6dZP22zhs,14434
|
|
114
|
+
dartsort/vis/scatterplots.py,sha256=-0bNguyqzM8lTo496L4Y-5SG9mygyHZrOQppftTICc8,24436
|
|
115
|
+
dartsort/vis/sorting.py,sha256=kEqqIMUkOsksGlYNzunugjL4Gs1aUCKRDEb2e-vdoG0,4490
|
|
116
|
+
dartsort/vis/unit.py,sha256=A8pm3mycE3TtpLZLjrrS1HtkxpwdeQwuPZVNsPQW5Z8,28129
|
|
117
|
+
dartsort/vis/unit_comparison.py,sha256=tJ5KXC-w3U8IIARKpSTVvWiDxosbwd2ewbRpKsywoUc,35699
|
|
118
|
+
dartsort/vis/versus.py,sha256=DU_JpPag19uM3vTsyPRVXhIHSrmIxft4P1ZBi5jUvPk,10120
|
|
119
|
+
dartsort/vis/vismain.py,sha256=g3rDtRv55JzSHEwRJgGANHtlAvlaYcMSUmqMyR1POHY,18027
|
|
120
|
+
dartsort/vis/waveforms.py,sha256=0X5LLikAf2u8yi2uSdIjC4vkgO74ZjImf9qxHEDohDc,11358
|
|
121
|
+
dartsort-0.3.5.dist-info/METADATA,sha256=0eua52JWcuJ47BKv2KMXRaK1k_1JaCkGDsckZcucTos,4263
|
|
122
|
+
dartsort-0.3.5.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
|
|
123
|
+
dartsort-0.3.5.dist-info/entry_points.txt,sha256=JtQMccq1-GIVSQ_wBqXt54fd7SO4EEHb3BZLxt0-snA,55
|
|
124
|
+
dartsort-0.3.5.dist-info/top_level.txt,sha256=357pmwl-ljvdYIW51fPg0lKWxc2DWfx7qNKhIt60eUU,9
|
|
125
|
+
dartsort-0.3.5.dist-info/RECORD,,
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
dartsort
|